[{"id": "skill:morluto/rea/.agents/skills/rea-analysis-optimization", "name": "rea-analysis-optimization", "kind": "skill", "official": false, "desc": "Optimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.", "repo": "https://github.com/morluto/rea/tree/HEAD/.agents/skills/rea-analysis-optimization", "install": ["npx skills add morluto/rea --skill rea-analysis-optimization"], "stars": 456474, "pushed": "2026-11-13T11:52:26Z", "license": "MIT", "plat": "rea-analysis-optimization", "live": "Not checked (runs locally)"}, {"id": "skill:morluto/rea/.agents/skills/rea-ci-tests-audit", "name": "rea-ci-tests-audit", "kind": "skill", "official": false, "desc": "Audit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.", "repo": "https://github.com/morluto/rea/tree/HEAD/.agents/skills/rea-ci-tests-audit", "install": ["npx skills add morluto/rea --skill rea-ci-tests-audit"], "stars": 456474, "pushed": "2026-11-13T11:52:26Z", "license": "MIT", "plat": "rea-ci-tests-audit", "live": "Not checked (runs locally)"}, {"id": "skill:mattpocock/skills/skills/engineering/diagnosing-bugs", "name": "diagnosing-bugs", "kind": "skill", "official": false, "desc": "Diagnosis loop for hard bugs and performance regressions. Use when the user says \"diagnose\"/\"debug this\", or reports something broken/throwing/failing/slow.", "repo": "https://github.com/mattpocock/skills/tree/HEAD/skills/engineering/diagnosing-bugs", "install": ["npx skills add mattpocock/skills --skill diagnosing-bugs"], "stars": 323337, "pushed": "2026-11-13T08:41:25Z", "license": "MIT", "plat": "diagnosing-bugs", "live": "Not checked (runs locally)"}, {"id": "skill:mattpocock/skills/skills/misc/migrate-to-shoehorn", "name": "migrate-to-shoehorn", "kind": "skill", "official": false, "desc": "Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.", "repo": "https://github.com/mattpocock/skills/tree/HEAD/skills/misc/migrate-to-shoehorn", "install": ["npx skills add mattpocock/skills --skill migrate-to-shoehorn"], "stars": 323337, "pushed": "2026-11-13T08:41:25Z", "license": "MIT", "plat": "typescript", "live": "Not checked (runs locally)"}, {"id": "skill:anthropics/skills/skills/webapp-testing", "name": "webapp-testing", "kind": "skill", "official": true, "desc": "Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.", "repo": "https://github.com/anthropics/skills/tree/HEAD/skills/webapp-testing", "install": ["npx skills add anthropics/skills --skill webapp-testing"], "stars": 194218, "pushed": "2026-11-06T22:32:32Z", "license": null, "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:DietrichGebert/ponytail/skills/ponytail-audit", "name": "ponytail-audit", "kind": "skill", "official": false, "desc": "Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split. Ranked, each finding explained in plain English. One-shot report, changes nothing. Use for \"audit this codebase\", \"review the whole repo\", \"find bloat\", \"what can I delete\", /ponytail-audit.", "repo": "https://github.com/DietrichGebert/ponytail/tree/HEAD/skills/ponytail-audit", "install": ["npx skills add DietrichGebert/ponytail --skill ponytail-audit"], "stars": 190451, "pushed": "2026-10-29T11:59:31Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:DietrichGebert/ponytail/.openclaw/skills/ponytail-review", "name": "ponytail-review", "kind": "skill", "official": false, "desc": "Quality review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it.", "repo": "https://github.com/DietrichGebert/ponytail/tree/HEAD/.openclaw/skills/ponytail-review", "install": ["npx skills add DietrichGebert/ponytail --skill ponytail-review"], "stars": 190451, "pushed": "2026-10-29T11:59:31Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:DietrichGebert/ponytail/skills/ponytail-review", "name": "ponytail-review", "kind": "skill", "official": false, "desc": "Quality review of a change: is the logic right, is it safe, does it hold under real load, is risky code tested, is it fast enough, and is every line needed. Reads the connected code, not only the diff. Each finding is explained in plain English. Use for \"review this\", \"code review\", \"review the last commit\", \"review my PR\", \"is this over-engineered\", /ponytail-review.", "repo": "https://github.com/DietrichGebert/ponytail/tree/HEAD/skills/ponytail-review", "install": ["npx skills add DietrichGebert/ponytail --skill ponytail-review"], "stars": 190451, "pushed": "2026-10-29T11:59:31Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:langgenius/dify/.agents/skills/e2e-cucumber-playwright", "name": "e2e-cucumber-playwright", "kind": "skill", "official": false, "desc": "Use when writing, changing, or reviewing Cucumber and Playwright tests under `e2e/`, including feature files, step definitions, support code, scenario tags, locators, and assertions. Do not use for Vitest, React Testing Library, backend tests, or generic browser automation outside the E2E suite.", "repo": "https://github.com/langgenius/dify/tree/HEAD/.agents/skills/e2e-cucumber-playwright", "install": ["npx skills add langgenius/dify --skill e2e-cucumber-playwright"], "stars": 161128, "pushed": "2026-11-14T05:14:12Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:langgenius/dify/.agents/skills/frontend-testing", "name": "frontend-testing", "kind": "skill", "official": false, "desc": "Use when writing or changing Vitest or React Testing Library tests under `web/` or `packages/dify-ui/`, or when the user explicitly requests frontend test strategy, including evaluation of an existing strategy. Do not use for frontend code-review-only requests, general testability discussion, Python tests, or Cucumber/Playwright E2E.", "repo": "https://github.com/langgenius/dify/tree/HEAD/.agents/skills/frontend-testing", "install": ["npx skills add langgenius/dify --skill frontend-testing"], "stars": 161128, "pushed": "2026-11-14T05:14:12Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:addyosmani/agent-skills/skills/browser-testing-with-devtools", "name": "browser-testing-with-devtools", "kind": "skill", "official": false, "desc": "Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.", "repo": "https://github.com/addyosmani/agent-skills/tree/HEAD/skills/browser-testing-with-devtools", "install": ["npx skills add addyosmani/agent-skills --skill browser-testing-with-devtools"], "stars": 117221, "pushed": "2026-11-14T04:33:56Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:addyosmani/agent-skills/skills/debugging-and-error-recovery", "name": "debugging-and-error-recovery", "kind": "skill", "official": false, "desc": "Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than guessing. Use when asked what broke, why a test started failing, or why code throws, even when the diff, the function, or the stack trace is pasted inline and the cause looks obvious fro", "repo": "https://github.com/addyosmani/agent-skills/tree/HEAD/skills/debugging-and-error-recovery", "install": ["npx skills add addyosmani/agent-skills --skill debugging-and-error-recovery"], "stars": 117221, "pushed": "2026-11-14T04:33:56Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:addyosmani/agent-skills/skills/test-driven-development", "name": "test-driven-development", "kind": "skill", "official": false, "desc": "Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality. Use when asked to add tests to a function, fix a bug in it or change its behavior, even when the code is pasted inline, the request does not mention tests and the answer looks obvious from reading it. The skill writes the failing test", "repo": "https://github.com/addyosmani/agent-skills/tree/HEAD/skills/test-driven-development", "install": ["npx skills add addyosmani/agent-skills --skill test-driven-development"], "stars": 117221, "pushed": "2026-11-14T04:33:56Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:paperclipai/paperclip/.agents/skills/add-product-e2e-eval", "name": "add-product-e2e-eval", "kind": "skill", "official": false, "desc": "Add or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.", "repo": "https://github.com/paperclipai/paperclip/tree/HEAD/.agents/skills/add-product-e2e-eval", "install": ["npx skills add paperclipai/paperclip --skill add-product-e2e-eval"], "stars": 113505, "pushed": "2026-11-13T09:51:38Z", "license": "MIT", "plat": "paperclip", "live": "Not checked (runs locally)"}, {"id": "skill:paperclipai/paperclip/.agents/skills/add-runner-eval", "name": "add-runner-eval", "kind": "skill", "official": false, "desc": "Add or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.", "repo": "https://github.com/paperclipai/paperclip/tree/HEAD/.agents/skills/add-runner-eval", "install": ["npx skills add paperclipai/paperclip --skill add-runner-eval"], "stars": 113505, "pushed": "2026-11-13T09:51:38Z", "license": "MIT", "plat": "paperclip", "live": "Not checked (runs locally)"}, {"id": "skill:paperclipai/paperclip/packages/skills-catalog/catalog/bundled/quality/qa-acceptance", "name": "qa-acceptance", "kind": "skill", "official": false, "desc": "Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.", "repo": "https://github.com/paperclipai/paperclip/tree/HEAD/packages/skills-catalog/catalog/bundled/quality/qa-acceptance", "install": ["npx skills add paperclipai/paperclip --skill qa-acceptance"], "stars": 113505, "pushed": "2026-11-13T09:51:38Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:nexu-io/open-design/plugins/_official/atoms/build-test", "name": "build-test", "kind": "skill", "official": false, "desc": "Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.", "repo": "https://github.com/nexu-io/open-design/tree/HEAD/plugins/_official/atoms/build-test", "install": ["npx skills add nexu-io/open-design --skill build-test"], "stars": 107550, "pushed": "2026-11-14T01:09:21Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:tt-a1i/archify/.agents/skills/test-value", "name": "test-value", "kind": "skill", "official": false, "desc": "Improve test value and feedback cost when auditing slow, flaky, redundant or brittle tests; choosing tests during implementation; or reviewing test changes before a commit or PR. Keep ordinary implementation and pre-commit use scoped to the affected behavior, not a repository-wide audit.", "repo": "https://github.com/tt-a1i/archify/tree/HEAD/.agents/skills/test-value", "install": ["npx skills add tt-a1i/archify --skill test-value"], "stars": 96261, "pushed": "2026-11-14T05:02:16Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:ComposioHQ/awesome-claude-skills/composio-skills/bugbug-automation", "name": "bugbug-automation", "kind": "skill", "official": false, "desc": "Automate Bugbug tasks via Rube MCP (Composio). Always search tools first for current schemas.", "repo": "https://github.com/ComposioHQ/awesome-claude-skills/tree/HEAD/composio-skills/bugbug-automation", "install": ["npx skills add ComposioHQ/awesome-claude-skills --skill bugbug-automation"], "stars": 79451, "pushed": "2026-09-18T07:16:11Z", "license": null, "plat": "bugbug", "live": "Not checked (runs locally)"}, {"id": "skill:ComposioHQ/awesome-claude-skills/composio-skills/bugherd-automation", "name": "bugherd-automation", "kind": "skill", "official": false, "desc": "Automate Bugherd tasks via Rube MCP (Composio). Always search tools first for current schemas.", "repo": "https://github.com/ComposioHQ/awesome-claude-skills/tree/HEAD/composio-skills/bugherd-automation", "install": ["npx skills add ComposioHQ/awesome-claude-skills --skill bugherd-automation"], "stars": 79451, "pushed": "2026-09-18T07:16:11Z", "license": null, "plat": "bugherd", "live": "Not checked (runs locally)"}, {"id": "skill:ComposioHQ/awesome-claude-skills/composio-skills/codacy-automation", "name": "codacy-automation", "kind": "skill", "official": false, "desc": "Automate Codacy tasks via Rube MCP (Composio). Always search tools first for current schemas.", "repo": "https://github.com/ComposioHQ/awesome-claude-skills/tree/HEAD/composio-skills/codacy-automation", "install": ["npx skills add ComposioHQ/awesome-claude-skills --skill codacy-automation"], "stars": 79451, "pushed": "2026-09-18T07:16:11Z", "license": null, "plat": "codacy", "live": "Not checked (runs locally)"}, {"id": "skill:code-yeongyu/oh-my-openagent/.agents/skills/codex-qa", "name": "codex-qa", "kind": "skill", "official": false, "desc": "QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real ~/.codex. The first-party method drives the real `codex app-server` against an isolated CODEX_HOME plus a LOCAL mock model (no real API call), and proves a plugin hook fired by asserting hook/started + hook/completed notifications. Also: isolated install verification, per-component hook probes, a tmux TUI smoke, and runtime log observation (RUST_LOG /", "repo": "https://github.com/code-yeongyu/oh-my-openagent/tree/HEAD/.agents/skills/codex-qa", "install": ["npx skills add code-yeongyu/oh-my-openagent --skill codex-qa"], "stars": 70897, "pushed": "2026-11-14T05:45:50Z", "license": "NOASSERTION", "plat": "codex", "live": "Not checked (runs locally)"}, {"id": "skill:code-yeongyu/oh-my-openagent/packages/shared-skills/skills/debugging", "name": "debugging", "kind": "skill", "official": false, "desc": "Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.", "repo": "https://github.com/code-yeongyu/oh-my-openagent/tree/HEAD/packages/shared-skills/skills/debugging", "install": ["npx skills add code-yeongyu/oh-my-openagent --skill debugging"], "stars": 70897, "pushed": "2026-11-14T05:45:50Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:code-yeongyu/oh-my-openagent/packages/shared-skills/skills/eval-integrity", "name": "eval-integrity", "kind": "skill", "official": false, "desc": "Assess integrity of an eval, benchmark, metric, A/B test, holdout, LLM-judge, or user-study claim when the question is whether measurement, comparison, or evidence is independent and trustworthy.", "repo": "https://github.com/code-yeongyu/oh-my-openagent/tree/HEAD/packages/shared-skills/skills/eval-integrity", "install": ["npx skills add code-yeongyu/oh-my-openagent --skill eval-integrity"], "stars": 70897, "pushed": "2026-11-14T05:45:50Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:code-yeongyu/oh-my-openagent/.agents/skills/opencode-qa", "name": "opencode-qa", "kind": "skill", "official": false, "desc": "QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a specific plugin hook/action/event fired via the SSE event stream, smoke-test the TUI under tmux, and investigate sessions in opencode's SQLite DB by id, title/name, or message text. Ships tested helper scripts (each with a --self-test) plus per-domain references. Use whenever someone wants to QA, smoke-test, verify, or debug opencode's CLI, HTTP server, plugin hooks/events, or TUI, or to find/inspect", "repo": "https://github.com/code-yeongyu/oh-my-openagent/tree/HEAD/.agents/skills/opencode-qa", "install": ["npx skills add code-yeongyu/oh-my-openagent --skill opencode-qa"], "stars": 70897, "pushed": "2026-11-14T05:45:50Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:code-yeongyu/oh-my-openagent/packages/shared-skills/skills/review-work", "name": "review-work", "kind": "skill", "official": false, "desc": "Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.", "repo": "https://github.com/code-yeongyu/oh-my-openagent/tree/HEAD/packages/shared-skills/skills/review-work", "install": ["npx skills add code-yeongyu/oh-my-openagent --skill review-work"], "stars": 70897, "pushed": "2026-11-14T05:45:50Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:code-yeongyu/oh-my-openagent/.agents/skills/senpi-qa", "name": "senpi-qa", "kind": "skill", "official": false, "desc": "QA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the REAL senpi binary in strict isolation, and write every artifact to the one canonical evidence path .omo/evidence/omo-senpi-adapter/<slug>/. The live drivers under packages/omo-senpi/scripts/qa/ create their own isolated SENPI_CODING_AGENT_DIR and ignore the caller's, so the real ~/.senpi/agent is never written. Ships scripts/resolve-evidence-dir.mjs, which is the ONLY sanctioned way to pick an evidence directory: it r", "repo": "https://github.com/code-yeongyu/oh-my-openagent/tree/HEAD/.agents/skills/senpi-qa", "install": ["npx skills add code-yeongyu/oh-my-openagent --skill senpi-qa"], "stars": 70897, "pushed": "2026-11-14T05:45:50Z", "license": "NOASSERTION", "plat": "senpi", "live": "Not checked (runs locally)"}, {"id": "skill:CherryHQ/cherry-studio/.agents/skills/cherry-regression-test", "name": "cherry-regression-test", "kind": "skill", "official": false, "desc": "Run Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for full regression, release acceptance, development-branch system validation, or a named cherry-regression-test task on GitHub-hosted macOS and Windows runners.", "repo": "https://github.com/CherryHQ/cherry-studio/tree/HEAD/.agents/skills/cherry-regression-test", "install": ["npx skills add CherryHQ/cherry-studio --skill cherry-regression-test"], "stars": 53498, "pushed": "2026-11-14T04:54:41Z", "license": "AGPL-3.0", "plat": "cherry studio", "live": "Not checked (runs locally)"}, {"id": "skill:alibaba/open-code-review/plugins/open-code-review/skills/open-code-review", "name": "open-code-review", "kind": "skill", "official": false, "desc": "Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply fixes when requested. With appropriate review rules, can detect various types of issues including bugs, security vulnerabilities, performance problems, and code quality concerns.", "repo": "https://github.com/alibaba/open-code-review/tree/HEAD/plugins/open-code-review/skills/open-code-review", "install": ["npx skills add alibaba/open-code-review --skill open-code-review"], "stars": 50807, "pushed": "2026-11-14T05:39:05Z", "license": "Apache-2.0", "plat": "git", "live": "Not checked (runs locally)"}, {"id": "skill:alibaba/open-code-review/plugins/open-code-review/skills/open-code-review-delegate", "name": "open-code-review-delegate", "kind": "skill", "official": false, "desc": "Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.", "repo": "https://github.com/alibaba/open-code-review/tree/HEAD/plugins/open-code-review/skills/open-code-review-delegate", "install": ["npx skills add alibaba/open-code-review --skill open-code-review-delegate"], "stars": 50807, "pushed": "2026-11-14T05:39:05Z", "license": "Apache-2.0", "plat": "git", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-ai-product-evaluation-ops/skills/ab-test-setup", "name": "ab-test-setup", "kind": "skill", "official": false, "desc": "Use when designing an A/B or split test: define the hypothesis, control and variants, estimate sample size, verify tracking, and predeclare metrics and stopping rules.", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-ai-product-evaluation-ops/skills/ab-test-setup", "install": ["npx skills add sickn33/agentic-awesome-skills --skill ab-test-setup"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-api-platform-builder/skills/api-contract-testing", "name": "api-contract-testing", "kind": "skill", "official": false, "desc": "Design and review API contract tests across providers and consumers. Use for schema changes, compatibility regressions and client integration failures.", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-api-platform-builder/skills/api-contract-testing", "install": ["npx skills add sickn33/agentic-awesome-skills --skill api-contract-testing"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-qa-test-automation/skills/code-review-checklist", "name": "code-review-checklist", "kind": "skill", "official": false, "desc": "Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-qa-test-automation/skills/code-review-checklist", "install": ["npx skills add sickn33/agentic-awesome-skills --skill code-review-checklist"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "code review", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-api-platform-builder/skills/e2e-testing-patterns", "name": "e2e-testing-patterns", "kind": "skill", "official": false, "desc": "Build reliable, fast, and maintainable end-to-end test suites that provide confidence to ship code quickly and catch regressions before users do.", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-api-platform-builder/skills/e2e-testing-patterns", "install": ["npx skills add sickn33/agentic-awesome-skills --skill e2e-testing-patterns"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-api-platform-builder/skills/k6-load-testing", "name": "k6-load-testing", "kind": "skill", "official": false, "desc": "Comprehensive k6 load testing skill for API, browser, and scalability testing. Write realistic load scenarios, analyze results, and integrate with CI/CD.", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-api-platform-builder/skills/k6-load-testing", "install": ["npx skills add sickn33/agentic-awesome-skills --skill k6-load-testing"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "k6", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-python-api-builder/skills/python-testing-patterns", "name": "python-testing-patterns", "kind": "skill", "official": false, "desc": "Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-python-api-builder/skills/python-testing-patterns", "install": ["npx skills add sickn33/agentic-awesome-skills --skill python-testing-patterns"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "python", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-qa-test-automation/skills/systematic-debugging", "name": "systematic-debugging", "kind": "skill", "official": false, "desc": "Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-qa-test-automation/skills/systematic-debugging", "install": ["npx skills add sickn33/agentic-awesome-skills --skill systematic-debugging"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "debugging", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-qa-test-automation/skills/test-driven-development", "name": "test-driven-development", "kind": "skill", "official": false, "desc": "Use a failing behavioral test to guide a feature or bug fix, then implement and refactor with relevant regression checks.", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-qa-test-automation/skills/test-driven-development", "install": ["npx skills add sickn33/agentic-awesome-skills --skill test-driven-development"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "test-driven development", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-qa-test-automation/skills/test-fixing", "name": "test-fixing", "kind": "skill", "official": false, "desc": "Systematically identify and fix all failing tests using smart grouping strategies. Use when explicitly asks to fix tests (\"fix these tests\", \"make tests pass\"), reports test failures (\"tests are failing\", \"test suite is broken\"), or completes implementation and wants tests passing.", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-qa-test-automation/skills/test-fixing", "install": ["npx skills add sickn33/agentic-awesome-skills --skill test-fixing"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "testing", "live": "Not checked (runs locally)"}, {"id": "skill:sickn33/agentic-awesome-skills/plugins/aasb-aas-qa-test-automation/skills/testing-patterns", "name": "testing-patterns", "kind": "skill", "official": false, "desc": "Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-green-refactor cycle.", "repo": "https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/aasb-aas-qa-test-automation/skills/testing-patterns", "install": ["npx skills add sickn33/agentic-awesome-skills --skill testing-patterns"], "stars": 49672, "pushed": "2026-11-13T22:02:29Z", "license": "MIT", "plat": "testing", "live": "Not checked (runs locally)"}, {"id": "skill:wshobson/agents/plugins/shell-scripting/skills/bats-testing-patterns", "name": "bats-testing-patterns", "kind": "skill", "official": false, "desc": "Master Bash Automated Testing System (Bats) for comprehensive shell script testing. Use when writing tests for shell scripts, CI/CD pipelines, or requiring test-driven development of shell utilities.", "repo": "https://github.com/wshobson/agents/tree/HEAD/plugins/shell-scripting/skills/bats-testing-patterns", "install": ["npx skills add wshobson/agents --skill bats-testing-patterns"], "stars": 42495, "pushed": "2026-11-09T01:08:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:wshobson/agents/plugins/developer-essentials/skills/debugging-strategies", "name": "debugging-strategies", "kind": "skill", "official": false, "desc": "Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.", "repo": "https://github.com/wshobson/agents/tree/HEAD/plugins/developer-essentials/skills/debugging-strategies", "install": ["npx skills add wshobson/agents --skill debugging-strategies"], "stars": 42495, "pushed": "2026-11-09T01:08:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:wshobson/agents/plugins/developer-essentials/skills/e2e-testing-patterns", "name": "e2e-testing-patterns", "kind": "skill", "official": false, "desc": "Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.", "repo": "https://github.com/wshobson/agents/tree/HEAD/plugins/developer-essentials/skills/e2e-testing-patterns", "install": ["npx skills add wshobson/agents --skill e2e-testing-patterns"], "stars": 42495, "pushed": "2026-11-09T01:08:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:wshobson/agents/plugins/javascript-typescript/skills/javascript-testing-patterns", "name": "javascript-testing-patterns", "kind": "skill", "official": false, "desc": "Implement comprehensive testing strategies using Jest, Vitest, and Testing Library for unit tests, integration tests, and end-to-end testing with mocking, fixtures, and test-driven development. Use when writing JavaScript/TypeScript tests, setting up test infrastructure, or implementing TDD/BDD workflows.", "repo": "https://github.com/wshobson/agents/tree/HEAD/plugins/javascript-typescript/skills/javascript-testing-patterns", "install": ["npx skills add wshobson/agents --skill javascript-testing-patterns"], "stars": 42495, "pushed": "2026-11-09T01:08:33Z", "license": "MIT", "plat": "javascript", "live": "Not checked (runs locally)"}, {"id": "skill:wshobson/agents/plugins/agent-teams/skills/multi-reviewer-patterns", "name": "multi-reviewer-patterns", "kind": "skill", "official": false, "desc": "Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.", "repo": "https://github.com/wshobson/agents/tree/HEAD/plugins/agent-teams/skills/multi-reviewer-patterns", "install": ["npx skills add wshobson/agents --skill multi-reviewer-patterns"], "stars": 42495, "pushed": "2026-11-09T01:08:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:wshobson/agents/plugins/agent-teams/skills/parallel-debugging", "name": "parallel-debugging", "kind": "skill", "official": false, "desc": "Debug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use this skill when debugging bugs with multiple potential causes, performing root cause analysis, or organizing parallel investigation workflows.", "repo": "https://github.com/wshobson/agents/tree/HEAD/plugins/agent-teams/skills/parallel-debugging", "install": ["npx skills add wshobson/agents --skill parallel-debugging"], "stars": 42495, "pushed": "2026-11-09T01:08:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:wshobson/agents/plugins/backend-development/skills/temporal-python-testing", "name": "temporal-python-testing", "kind": "skill", "official": false, "desc": "Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.", "repo": "https://github.com/wshobson/agents/tree/HEAD/plugins/backend-development/skills/temporal-python-testing", "install": ["npx skills add wshobson/agents --skill temporal-python-testing"], "stars": 42495, "pushed": "2026-11-09T01:08:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:wshobson/agents/plugins/blockchain-web3/skills/web3-testing", "name": "web3-testing", "kind": "skill", "official": false, "desc": "Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.", "repo": "https://github.com/wshobson/agents/tree/HEAD/plugins/blockchain-web3/skills/web3-testing", "install": ["npx skills add wshobson/agents --skill web3-testing"], "stars": 42495, "pushed": "2026-11-09T01:08:33Z", "license": "MIT", "plat": "smart contracts", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/breakdown-test", "name": "breakdown-test", "kind": "skill", "official": false, "desc": "Test Planning and Quality Assurance prompt that generates comprehensive test strategies, task breakdowns, and quality validation plans for GitHub projects.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/breakdown-test", "install": ["npx skills add github/awesome-copilot --skill breakdown-test"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/bug-receipt", "name": "bug-receipt", "kind": "skill", "official": false, "desc": "Close defects and incidents with a BUG RECEIPT and VERIFIED, PARTIAL, or BLOCKED status after diagnosis, repair, or recovery.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/bug-receipt", "install": ["npx skills add github/awesome-copilot --skill bug-receipt"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/bug-reproduction-brief", "name": "bug-reproduction-brief", "kind": "skill", "official": false, "desc": "Turn a vague, intermittent, or environment-specific bug report into a minimal evidence-backed reproduction before proposing a fix.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/bug-reproduction-brief", "install": ["npx skills add github/awesome-copilot --skill bug-reproduction-brief"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/codeql", "name": "codeql", "kind": "skill", "official": false, "desc": "Comprehensive guide for setting up and configuring CodeQL code scanning via GitHub Actions workflows and the CodeQL CLI. This skill should be used when users need help with code scanning configuration, CodeQL workflow files, CodeQL CLI commands, SARIF output, security analysis setup, or troubleshooting CodeQL analysis.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/codeql", "install": ["npx skills add github/awesome-copilot --skill codeql"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/csharp-mstest", "name": "csharp-mstest", "kind": "skill", "official": false, "desc": "Get best practices for MSTest 3.x/4.x unit testing, including modern assertion APIs and data-driven tests", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/csharp-mstest", "install": ["npx skills add github/awesome-copilot --skill csharp-mstest"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/csharp-nunit", "name": "csharp-nunit", "kind": "skill", "official": false, "desc": "Get best practices for NUnit unit testing, including data-driven tests", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/csharp-nunit", "install": ["npx skills add github/awesome-copilot --skill csharp-nunit"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/csharp-tunit", "name": "csharp-tunit", "kind": "skill", "official": false, "desc": "Get best practices for TUnit unit testing, including data-driven tests", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/csharp-tunit", "install": ["npx skills add github/awesome-copilot --skill csharp-tunit"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/csharp-xunit", "name": "csharp-xunit", "kind": "skill", "official": false, "desc": "Get best practices for XUnit unit testing, including data-driven tests", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/csharp-xunit", "install": ["npx skills add github/awesome-copilot --skill csharp-xunit"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/cypress-flake-fixer", "name": "cypress-flake-fixer", "kind": "skill", "official": false, "desc": "Find and fix flake-prone anti-patterns in an existing Cypress suite, and APIs removed in Cypress 12 to 16. Bundles a zero-dependency scanner for fixed cy.wait() delays, assigned command return values, async/await, force: true, chaining after actions, one-shot expect() inside .then(), conditional testing, and removed APIs such as Cypress.env(), cy.exec(), cy.server()/cy.route(). Use when asked to fix flaky Cypress tests, remove cy.wait, stabilize or harden a Cypress suite, audit Cypress specs, de", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/cypress-flake-fixer", "install": ["npx skills add github/awesome-copilot --skill cypress-flake-fixer"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/diagnose-ci-gate", "name": "diagnose-ci-gate", "kind": "skill", "official": false, "desc": "Determine whether a failing CI check was caused by the current change, then recommend exactly one action. Use when a required check fails on a pull request, when asked \"is this failure mine?\", when a job passes locally but fails in CI, or before retrying a red build. Covers fetching the real log, reading the first error instead of the tail, classifying bug / flaky / environment / pipeline, comparing against the base branch and recent runs, reproducing with CI versions, and fixing a flaky test ra", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/diagnose-ci-gate", "install": ["npx skills add github/awesome-copilot --skill diagnose-ci-gate"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/java-debugging", "name": "java-debugging", "kind": "skill", "official": false, "desc": "Debug Java applications systematically: JDWP remote debugging, jdb, VS Code and IntelliJ attach, debugging Maven/Gradle tests, Spring Boot and Quarkus dev mode, containers, breakpoints/logpoints, and reading stack traces. Use when the user needs to find the cause of a Java bug, exception, wrong behavior, or failing test, or asks how to attach a debugger.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/java-debugging", "install": ["npx skills add github/awesome-copilot --skill java-debugging"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "java", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/java-diagnostics", "name": "java-diagnostics", "kind": "skill", "official": false, "desc": "Symptom-first runtime diagnostics for JVM applications using JDK tools: jcmd, jstack, jmap, jstat, JFR, GC logs, async-profiler, Native Memory Tracking, and Eclipse MAT. Use when a Java app has high CPU, memory leaks or OutOfMemoryError, slow startup, deadlocks or thread starvation, long GC pauses, native memory growth, or slow requests. Includes permission tiers for safe use.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/java-diagnostics", "install": ["npx skills add github/awesome-copilot --skill java-diagnostics"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "java", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/java-junit", "name": "java-junit", "kind": "skill", "official": false, "desc": "Write, review and fix Java unit tests with JUnit 5 and JUnit 6 (Jupiter), AssertJ and Mockito: assertions, parameterized and nested tests, mocking rules, deterministic time and randomness, Surefire vs Failsafe, JaCoCo coverage, optional PIT mutation testing, and guardrails for agents (never skip or delete failing tests). Use when adding, refactoring or debugging tests in Maven or Gradle projects. Framework-neutral.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/java-junit", "install": ["npx skills add github/awesome-copilot --skill java-junit"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "java", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/java-testcontainers", "name": "java-testcontainers", "kind": "skill", "official": false, "desc": "Write reliable integration tests in plain Java with Testcontainers 2.x: JUnit Jupiter lifecycle, singleton containers, reuse, generic containers, wait strategies, networks, init scripts, Docker Compose, CI and Docker/Podman setup. Use when adding or fixing Testcontainers tests, or migrating from 1.x. Framework-neutral.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/java-testcontainers", "install": ["npx skills add github/awesome-copilot --skill java-testcontainers"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "java", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/javascript-typescript-jest", "name": "javascript-typescript-jest", "kind": "skill", "official": false, "desc": "Best practices for writing JavaScript/TypeScript tests using Jest, including mocking strategies, test structure, and common patterns.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/javascript-typescript-jest", "install": ["npx skills add github/awesome-copilot --skill javascript-typescript-jest"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "javascript/typescript", "live": "Not checked (runs locally)"}, {"id": "skill:github/awesome-copilot/skills/mcp-release-qa", "name": "mcp-release-qa", "kind": "skill", "official": false, "desc": "Verify an MCP server before release by exercising a real protocol session, comparing runtime capabilities with source and documentation, testing failure paths, and recording reproducible evidence. Use when shipping or reviewing an MCP server, tool, resource, prompt, catalog, or install path.", "repo": "https://github.com/github/awesome-copilot/tree/HEAD/skills/mcp-release-qa", "install": ["npx skills add github/awesome-copilot --skill mcp-release-qa"], "stars": 41140, "pushed": "2026-11-13T21:37:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:davila7/claude-code-templates/cli-tool/components/skills/ai-research/qa-test-planner", "name": "qa-test-planner", "kind": "skill", "official": false, "desc": "Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.", "repo": "https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/qa-test-planner", "install": ["npx skills add davila7/claude-code-templates --skill qa-test-planner"], "stars": 33495, "pushed": "2026-11-14T03:16:32Z", "license": "MIT", "plat": "figma", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering/skills/api-test-suite-builder", "name": "api-test-suite-builder", "kind": "skill", "official": false, "desc": "Use when asked to write API, integration or contract tests for REST endpoints. Builds the suite from the routes: happy paths, auth, validation errors and edge cases per endpoint.", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering/skills/api-test-suite-builder", "install": ["npx skills add alirezarezvani/claude-skills --skill api-test-suite-builder"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/playwright-pro/skills/coverage", "name": "coverage", "kind": "skill", "official": false, "desc": "Find what is not tested: map untested pages and flows and coverage gaps. Use whenever the user asks what needs tests, about missing tests or test coverage.", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/playwright-pro/skills/coverage", "install": ["npx skills add alirezarezvani/claude-skills --skill coverage"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/playwright-pro/skills/fix", "name": "fix", "kind": "skill", "official": false, "desc": "Diagnose and fix a failing or flaky Playwright test. Use whenever a test fails, passes only sometimes, breaks intermittently or needs fixing.", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/playwright-pro/skills/fix", "install": ["npx skills add alirezarezvani/claude-skills --skill fix"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/playwright-pro/skills/generate", "name": "generate", "kind": "skill", "official": false, "desc": "Use when asked to write Playwright or e2e tests for a page, component or feature ('write tests', 'add tests for', 'e2e test').", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/playwright-pro/skills/generate", "install": ["npx skills add alirezarezvani/claude-skills --skill generate"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/playwright-pro/skills/migrate", "name": "migrate", "kind": "skill", "official": false, "desc": "Use when moving tests from Cypress or Selenium to Playwright ('migrate tests', 'convert tests', 'replace selenium').", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/playwright-pro/skills/migrate", "install": ["npx skills add alirezarezvani/claude-skills --skill migrate"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/playwright-pro/skills/pw", "name": "pw", "kind": "skill", "official": false, "desc": "Use for any Playwright or end-to-end browser testing work: writing tests, fixing flaky ones, migrating from Cypress or Selenium, CI setup, TestRail or BrowserStack. Routes to the matching /pw sub-skill and its 55 templates.", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/playwright-pro/skills/pw", "install": ["npx skills add alirezarezvani/claude-skills --skill pw"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/playwright-pro/skills/pw-init", "name": "pw-init", "kind": "skill", "official": false, "desc": "Use when setting up Playwright in a project ('set up playwright', 'add e2e tests', 'configure playwright', 'init playwright').", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/playwright-pro/skills/pw-init", "install": ["npx skills add alirezarezvani/claude-skills --skill pw-init"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/playwright-pro/skills/pw-review", "name": "pw-review", "kind": "skill", "official": false, "desc": "Use when reviewing Playwright tests for quality ('review tests', 'audit tests', 'playwright best practices check').", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/playwright-pro/skills/pw-review", "install": ["npx skills add alirezarezvani/claude-skills --skill pw-review"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/skills/red-green-proof", "name": "red-green-proof", "kind": "skill", "official": false, "desc": "Turns a suspected bug into a proven one. Verify the cause against reality before claiming it, write a test that FAILS on the current code, apply the fix, watch it pass — then revert the fix and confirm the test goes red again, because a test that passes both ways proves nothing. Invoked bare after a debugging conversation, it takes the target from context rather than asking. Use when fixing a bug, investigating an incident, hardening a flaky area, or when asked to \"add tests that reveal the bug\"", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/skills/red-green-proof", "install": ["npx skills add alirezarezvani/claude-skills --skill red-green-proof"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/playwright-pro/skills/report", "name": "report", "kind": "skill", "official": false, "desc": "Summarize Playwright results. Use whenever the user asks how tests went, for a test report or status.", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/playwright-pro/skills/report", "install": ["npx skills add alirezarezvani/claude-skills --skill report"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/skills/senior-qa", "name": "senior-qa", "kind": "skill", "official": false, "desc": "Write and improve tests for React or Next.js apps: Jest, React Testing Library, MSW mocks, Playwright E2E, coverage gaps. Use whenever the user asks to add tests to a component or page, mock an API, set up end-to-end tests or raise coverage.", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/skills/senior-qa", "install": ["npx skills add alirezarezvani/claude-skills --skill senior-qa"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "jest, react testing library, playwright", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/skills/tdd-guide", "name": "tdd-guide", "kind": "skill", "official": false, "desc": "Test-first development and test generation for Jest, Pytest, JUnit, Vitest or Mocha: red-green-refactor, fixtures and mocks, coverage gaps. Use whenever the user asks to write tests (before or after the code), mock a dependency or raise coverage.", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/skills/tdd-guide", "install": ["npx skills add alirezarezvani/claude-skills --skill tdd-guide"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "jest, pytest, junit, vitest, mocha", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-skills/engineering-team/playwright-pro/skills/testrail", "name": "testrail", "kind": "skill", "official": false, "desc": "Use when syncing Playwright tests with TestRail ('testrail', 'sync test cases', 'push results to testrail', 'import from testrail').", "repo": "https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering-team/playwright-pro/skills/testrail", "install": ["npx skills add alirezarezvani/claude-skills --skill testrail"], "stars": 29773, "pushed": "2026-11-12T10:35:06Z", "license": "MIT", "plat": "testrail", "live": "Not checked (runs locally)"}, {"id": "skill:openai/skills/skills/.curated/gh-fix-ci", "name": "gh-fix-ci", "kind": "skill", "official": false, "desc": "Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.", "repo": "https://github.com/openai/skills/tree/HEAD/skills/.curated/gh-fix-ci", "install": ["npx skills add openai/skills --skill gh-fix-ci"], "stars": 28730, "pushed": "2026-10-28T17:31:41Z", "license": null, "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:phuryn/pm-skills/pm-execution/skills/test-scenarios", "name": "test-scenarios", "kind": "skill", "official": false, "desc": "Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writing QA test cases, creating test plans, defining acceptance tests, or preparing for feature validation.", "repo": "https://github.com/phuryn/pm-skills/tree/HEAD/pm-execution/skills/test-scenarios", "install": ["npx skills add phuryn/pm-skills --skill test-scenarios"], "stars": 27974, "pushed": "2026-11-08T23:10:04Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:yikart/AiToEarn/project/aitoearn-backend/.agents/skills/diagnose", "name": "diagnose", "kind": "skill", "official": false, "desc": "Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says \"diagnose this\" / \"debug this\", reports a bug, says something is broken/throwing/failing, or describes a performance regression.", "repo": "https://github.com/yikart/AiToEarn/tree/HEAD/project/aitoearn-backend/.agents/skills/diagnose", "install": ["npx skills add yikart/AiToEarn --skill diagnose"], "stars": 27717, "pushed": "2026-11-12T07:35:19Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:yikart/AiToEarn/project/aitoearn-backend/.agents/skills/tdd", "name": "tdd", "kind": "skill", "official": false, "desc": "Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions \"red-green-refactor\", wants integration tests, or asks for test-first development.", "repo": "https://github.com/yikart/AiToEarn/tree/HEAD/project/aitoearn-backend/.agents/skills/tdd", "install": ["npx skills add yikart/AiToEarn --skill tdd"], "stars": 27717, "pushed": "2026-11-12T07:35:19Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:nocobase/nocobase/packages/plugins/app-plugin-concurrency/skills/nocobase-app-plugin-concurrency", "name": "nocobase-app-plugin-concurrency", "kind": "skill", "official": false, "desc": "Configure and consume NocoBase 3 process-local Mutex locks, strict named managers, original service Token, optional TTL, public implementation extensions and application-owned shutdown.", "repo": "https://github.com/nocobase/nocobase/tree/HEAD/packages/plugins/app-plugin-concurrency/skills/nocobase-app-plugin-concurrency", "install": ["npx skills add nocobase/nocobase --skill nocobase-app-plugin-concurrency"], "stars": 24921, "pushed": "2026-11-14T05:16:46Z", "license": "NOASSERTION", "plat": "nocobase", "live": "Not checked (runs locally)"}, {"id": "skill:nocobase/nocobase/packages/plugins/app-plugin-scheduler/skills/nocobase-app-plugin-scheduler", "name": "nocobase-app-plugin-scheduler", "kind": "skill", "official": false, "desc": "Develop scheduled tasks in NocoBase 3 that business administrators need to view and track through the application UI. Define schedules in code, register the target a schedule points at, integrate execution status, and report completion. Do not use Scheduler to manage tasks that do not need UI visibility.", "repo": "https://github.com/nocobase/nocobase/tree/HEAD/packages/plugins/app-plugin-scheduler/skills/nocobase-app-plugin-scheduler", "install": ["npx skills add nocobase/nocobase --skill nocobase-app-plugin-scheduler"], "stars": 24921, "pushed": "2026-11-14T05:16:46Z", "license": "NOASSERTION", "plat": "nocobase", "live": "Not checked (runs locally)"}, {"id": "skill:google/skills/skills/ads/google-mobile-ads-validate", "name": "google-mobile-ads-validate", "kind": "skill", "official": false, "desc": "Validates a project's Google Mobile Ads (GMA) SDK integration for iOS, Android, or Unity projects. Use when conducting a full pre-launch audit of an app that integrates GMA SDK or when validating any individual GMA SDK integration checks, such as when validating ad unit IDs and ad formats, SKAdNetwork IDs, mediation adapter SDK version compatibility, or ad preloading.", "repo": "https://github.com/google/skills/tree/HEAD/skills/ads/google-mobile-ads-validate", "install": ["npx skills add google/skills --skill google-mobile-ads-validate"], "stars": 24146, "pushed": "2026-11-13T17:51:35Z", "license": "Apache-2.0", "plat": "google mobile ads", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.keploy/mcp", "name": "Keploy", "kind": "mcp", "official": null, "desc": "End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic.", "repo": "https://github.com/keploy/keploy", "install": ["https://api.keploy.io/client/v1/mcp"], "stars": 19756, "pushed": "2026-11-13T08:43:12Z", "license": "Apache-2.0", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "skill:wanshuiyin/Auto-claude-code-research-in-sleep/skills/experiment-audit", "name": "experiment-audit", "kind": "skill", "official": false, "desc": "Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says \\\"审计实验\\\", \\\"check experiment integrity\\\", \\\"audit results\\\", \\\"实验诚实度\\\", or after experiments complete before writing claims.", "repo": "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/HEAD/skills/experiment-audit", "install": ["npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill experiment-audit"], "stars": 19162, "pushed": "2026-11-11T07:39:57Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.tester-army/e2e", "name": "e2e", "kind": "mcp", "official": null, "desc": "Open live web and mobile app sessions from an e2e project to inspect the app and try locators.", "repo": "https://github.com/tester-army/e2e", "install": ["npm:e2e"], "stars": 13802, "pushed": "2026-11-13T11:23:57Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:Jeffallan/claude-skills/skills/playwright-expert", "name": "playwright-expert", "kind": "skill", "official": false, "desc": "Use when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke to write test scripts, create page objects, configure test fixtures, set up reporters, add CI integration, implement API mocking, or perform visual regression testing. Trigger terms: Playwright, E2E test, end-to-end, browser testing, automation, UI testing, visual testing, Page Object Model, test flakiness.", "repo": "https://github.com/Jeffallan/claude-skills/tree/HEAD/skills/playwright-expert", "install": ["npx skills add Jeffallan/claude-skills --skill playwright-expert"], "stars": 12355, "pushed": "2026-11-11T08:34:48Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:Jeffallan/claude-skills/skills/test-master", "name": "test-master", "kind": "skill", "official": false, "desc": "Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation frameworks; analyzing coverage gaps; performance testing with k6 or Artillery; security testing with OWASP methods; debugging flaky tests; or working on QA, regression, test automation, qu", "repo": "https://github.com/Jeffallan/claude-skills/tree/HEAD/skills/test-master", "install": ["npx skills add Jeffallan/claude-skills --skill test-master"], "stars": 12355, "pushed": "2026-11-11T08:34:48Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:modelcontextprotocol/inspector", "name": "inspector", "kind": "mcp", "official": null, "desc": "Deterministic testing tools for MCP servers", "repo": "https://github.com/modelcontextprotocol/inspector", "install": [], "stars": 11292, "pushed": null, "license": null, "plat": "mcp servers", "live": "Not checked (runs locally)"}, {"id": "skill:android/skills/profilers/android-profiler", "name": "android-profiler", "kind": "skill", "official": false, "desc": "Records and analyzes Android performance data and diagnoses performance bottlenecks across user apps, system apps, and system services, even if the user does not explicitly mention profiling or traces. Use when: recording system traces, CPU call stacks, Vulkan GPU/DRM memory, or Java/native heap profiles; analyzing Perfetto traces for UI jank, frame drops, ANRs, or app startup latency issues; investigating CPU bottlenecks, IPC/Binder storms, or thread scheduling stalls; diagnosing battery drain,", "repo": "https://github.com/android/skills/tree/HEAD/profilers/android-profiler", "install": ["npx skills add android/skills --skill android-profiler"], "stars": 10503, "pushed": "2026-11-11T06:04:32Z", "license": "Apache-2.0", "plat": "android", "live": "Not checked (runs locally)"}, {"id": "skill:android/skills/performance/anr-audit-and-fix", "name": "anr-audit-and-fix", "kind": "skill", "official": false, "desc": "Audits Android codebases for ANR risks and diagnoses ANR stack dumps. Use this skill when scanning Android code for ANR risks or triaging ANR stack dumps. Don't use for non-ANR crashes, dropped frames, general CPU profiling, or Perfetto system traces.", "repo": "https://github.com/android/skills/tree/HEAD/performance/anr-audit-and-fix", "install": ["npx skills add android/skills --skill anr-audit-and-fix"], "stars": 10503, "pushed": "2026-11-11T06:04:32Z", "license": "Apache-2.0", "plat": "android", "live": "Not checked (runs locally)"}, {"id": "skill:android/skills/testing/testing-setup", "name": "testing-setup", "kind": "skill", "official": false, "desc": "Analyze and create a testing strategy for Android apps - install testing libraries, set up test infrastructure, create harnesses for unit tests, UI tests, screenshot tests, and end-to-end tests.", "repo": "https://github.com/android/skills/tree/HEAD/testing/testing-setup", "install": ["npx skills add android/skills --skill testing-setup"], "stars": 10503, "pushed": "2026-11-11T06:04:32Z", "license": "Apache-2.0", "plat": "android", "live": "Not checked (runs locally)"}, {"id": "skill:Jakeschincariol/replica-skill/replica-test", "name": "replica-test", "kind": "skill", "official": false, "desc": "Clicks through every flow of an app clone and tests it for bugs: a test plan generated from the recon flows with happy paths and edge cases, Playwright end-to-end tests where possible, a browser click-through where not, and bug reports in a fixed format with severity, steps and evidence. Use when the user says \"test my clone\", \"find bugs\", \"QA this\", \"click through everything\", \"write e2e tests\", \"does it work\", or after /replica-build or /replica-backend.", "repo": "https://github.com/Jakeschincariol/replica-skill/tree/HEAD/replica-test", "install": ["npx skills add Jakeschincariol/replica-skill --skill replica-test"], "stars": 9270, "pushed": "2026-10-03T12:07:53Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:Gentleman-Programming/gentle-ai/internal/assets/skills/gentle-ai-bench", "name": "gentle-ai-bench", "kind": "skill", "official": false, "desc": "Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.", "repo": "https://github.com/Gentleman-Programming/gentle-ai/tree/HEAD/internal/assets/skills/gentle-ai-bench", "install": ["npx skills add Gentleman-Programming/gentle-ai --skill gentle-ai-bench"], "stars": 9147, "pushed": "2026-11-13T23:01:57Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:Gentleman-Programming/gentle-ai/internal/assets/skills/go-testing", "name": "go-testing", "kind": "skill", "official": false, "desc": "Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.", "repo": "https://github.com/Gentleman-Programming/gentle-ai/tree/HEAD/internal/assets/skills/go-testing", "install": ["npx skills add Gentleman-Programming/gentle-ai --skill go-testing"], "stars": 9147, "pushed": "2026-11-13T23:01:57Z", "license": "MIT", "plat": "go", "live": "Not checked (runs locally)"}, {"id": "skill:mvschwarz/openrig/packages/daemon/specs/agents/shared/skills/process/dogfood", "name": "dogfood", "kind": "skill", "official": false, "desc": "Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app/site/platform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.", "repo": "https://github.com/mvschwarz/openrig/tree/HEAD/packages/daemon/specs/agents/shared/skills/process/dogfood", "install": ["npx skills add mvschwarz/openrig --skill dogfood"], "stars": 8843, "pushed": "2026-11-14T05:50:58Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:mvschwarz/openrig/packages/daemon/specs/agents/shared/skills/process/test-driven-development", "name": "test-driven-development", "kind": "skill", "official": false, "desc": "Use when implementing any feature or bugfix, before writing implementation code", "repo": "https://github.com/mvschwarz/openrig/tree/HEAD/packages/daemon/specs/agents/shared/skills/process/test-driven-development", "install": ["npx skills add mvschwarz/openrig --skill test-driven-development"], "stars": 8843, "pushed": "2026-11-14T05:50:58Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:mvschwarz/openrig/packages/daemon/specs/agents/shared/skills/process/verification-before-completion", "name": "verification-before-completion", "kind": "skill", "official": false, "desc": "Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs", "repo": "https://github.com/mvschwarz/openrig/tree/HEAD/packages/daemon/specs/agents/shared/skills/process/verification-before-completion", "install": ["npx skills add mvschwarz/openrig --skill verification-before-completion"], "stars": 8843, "pushed": "2026-11-14T05:50:58Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/address-sanitizer", "name": "address-sanitizer", "kind": "skill", "official": false, "desc": "Builds and runs code under AddressSanitizer to catch buffer overflows, use-after-free, and other memory errors during fuzzing or tests. Covers -fsanitize=address builds, ASAN_OPTIONS, reading the crash report, LeakSanitizer, and the overhead and platform trade-offs. Use when fuzzing C/C++ or Rust that has unsafe blocks or FFI, when debugging a memory corruption crash, or when reading an ASan stack trace.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/address-sanitizer", "install": ["npx skills add trailofbits/skills --skill address-sanitizer"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/regression-hunt/skills/adjudicate-regression", "name": "adjudicate-regression", "kind": "skill", "official": false, "desc": "Use when deciding whether source and live reproduction evidence establish a new regression or an exclusion.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/regression-hunt/skills/adjudicate-regression", "install": ["npx skills add trailofbits/skills --skill adjudicate-regression"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/aflpp", "name": "aflpp", "kind": "skill", "official": false, "desc": "Sets up and runs AFL++ for multi-core fuzzing of C/C++ projects built with afl-clang-fast or afl-gcc-fast. Covers instrumentation modes, parallel main and secondary campaigns, persistent mode, corpus minimization, and crash triage. Use when scaling fuzzing across cores, fuzzing a mature C/C++ codebase, reading the afl-fuzz status screen, or moving on after libFuzzer has plateaued.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/aflpp", "install": ["npx skills add trailofbits/skills --skill aflpp"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/atheris", "name": "atheris", "kind": "skill", "official": false, "desc": "Sets up and runs Atheris, the coverage-guided Python fuzzer built on libFuzzer. Covers TestOneInput harnesses, FuzzedDataProvider, instrumenting both pure Python and native C extensions, and running under AddressSanitizer. Use when fuzzing a Python package, hunting memory corruption in a Python C extension, or choosing between Atheris and Hypothesis for a Python target.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/atheris", "install": ["npx skills add trailofbits/skills --skill atheris"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/cargo-fuzz", "name": "cargo-fuzz", "kind": "skill", "official": false, "desc": "Sets up and runs cargo-fuzz, the standard fuzzing tool for Cargo-based Rust projects. Covers cargo fuzz init, the nightly toolchain requirement, fuzz_target! harnesses, Arbitrary-derived structured inputs, sanitizer options, cargo fuzz coverage, and reproducing a crash artifact. Use when fuzzing a Rust crate, writing a fuzz_target!, exercising unsafe blocks or FFI in Rust, or triaging a cargo fuzz crash.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/cargo-fuzz", "install": ["npx skills add trailofbits/skills --skill cargo-fuzz"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/static-analysis/skills/codeql", "name": "codeql", "kind": "skill", "official": false, "desc": "Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis. Triggers on \"run codeql\", \"codeql scan\", \"build codeql database\", \"SAST scan\", \"taint analysis\", \"dataflow analysis\", or \"find vulnerabilities in this repo\". Covers Python, JavaScript/TypeScript, Go, Java/Kotlin, C/C++, C#, Ruby, and Swift. Supports \"run all\" (security-and-quality + security-experimental) and \"important only\" (high-precision) scan modes, and creates data extension ", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/static-analysis/skills/codeql", "install": ["npx skills add trailofbits/skills --skill codeql"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/constant-time-testing", "name": "constant-time-testing", "kind": "skill", "official": false, "desc": "Measures timing side channels in cryptographic implementations by running them, using dudect for statistical analysis and Timecop over Valgrind for dynamic tracing. Covers the formal, symbolic, dynamic, and statistical tool categories and how to read a result. Use when testing whether a running implementation is constant-time, measuring timing variance on a compiled binary, or investigating a suspected timing attack. Not for statically inspecting compiler output — the constant-time-analysis plug", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/constant-time-testing", "install": ["npx skills add trailofbits/skills --skill constant-time-testing"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/coverage-analysis", "name": "coverage-analysis", "kind": "skill", "official": false, "desc": "Measures and interprets what a fuzzing campaign actually reaches, using llvm-cov, lcov, or a fuzzer's own coverage output. Covers baselining a new campaign, reading coverage reports, and turning uncovered regions into harness, seed, or dictionary work. Use when a fuzzer plateaus, when judging whether a harness is effective, after changing a harness, or when asking why some code is never reached.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/coverage-analysis", "install": ["npx skills add trailofbits/skills --skill coverage-analysis"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/fuzzing-dictionary", "name": "fuzzing-dictionary", "kind": "skill", "official": false, "desc": "Builds and applies fuzzing dictionaries so a fuzzer can produce the keywords, magic bytes, and tokens a target expects. Covers extracting tokens from source, headers, binaries, and specifications, dictionary syntax, and wiring one into libFuzzer or AFL++. Use when fuzzing a parser, protocol, or file format, when coverage stalls at input validation, or when a target compares against fixed strings.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/fuzzing-dictionary", "install": ["npx skills add trailofbits/skills --skill fuzzing-dictionary"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/fuzzing-obstacles", "name": "fuzzing-obstacles", "kind": "skill", "official": false, "desc": "Patches past the barriers that stop a fuzzer making progress — checksum and hash verification, magic-value validation, time-based seeds, and other non-deterministic global state. Covers locating the blocking check, neutering it behind a fuzzing build flag, and avoiding the false positives a patch can introduce. Use when a fuzzer is stuck at validation, when coverage shows large regions behind a checksum, or when valid inputs are impractical to generate.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/fuzzing-obstacles", "install": ["npx skills add trailofbits/skills --skill fuzzing-obstacles"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/harness-writing", "name": "harness-writing", "kind": "skill", "official": false, "desc": "Designs and improves fuzzing harnesses for C/C++ and Rust. Covers mapping raw bytes onto a target API, generating structured inputs, avoiding non-determinism and false crashes, and deciding what to fuzz together. Use when writing a first LLVMFuzzerTestOneInput or fuzz_target! harness, when a campaign finds nothing or reports crashes that will not reproduce, or when the target API needs structured rather than raw input.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/harness-writing", "install": ["npx skills add trailofbits/skills --skill harness-writing"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/regression-hunt/skills/hunt-regressions", "name": "hunt-regressions", "kind": "skill", "official": false, "desc": "Use when discovering possible regressions from a pinned change and its callers before reproduction.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/regression-hunt/skills/hunt-regressions", "install": ["npx skills add trailofbits/skills --skill hunt-regressions"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/libafl", "name": "libafl", "kind": "skill", "official": false, "desc": "Builds custom fuzzers with LibAFL, the modular Rust fuzzing library. Covers composing observers, feedbacks, mutators, schedulers, and executors into a fuzzer for targets the standard tools do not fit. Use when writing a bespoke fuzzer or mutator, fuzzing a non-standard target or architecture, implementing a fuzzing research idea, or when libFuzzer and AFL++ lack the control you need.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/libafl", "install": ["npx skills add trailofbits/skills --skill libafl"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/libfuzzer", "name": "libfuzzer", "kind": "skill", "official": false, "desc": "Sets up and runs libFuzzer, the coverage-guided fuzzer built into LLVM, on C/C++ code that compiles with Clang. Covers harness structure, -fsanitize=fuzzer builds, corpus and dictionary management, sanitizer integration, and campaign triage. Use when writing or debugging an LLVMFuzzerTestOneInput harness, starting fuzzing on a C/C++ library, choosing between libFuzzer and AFL++, or working out why a libFuzzer run finds nothing.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/libfuzzer", "install": ["npx skills add trailofbits/skills --skill libfuzzer"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/mutation-testing/skills/mutation-testing", "name": "mutation-testing", "kind": "skill", "official": false, "desc": "Configures mewt or muton campaigns, analyzes surviving mutants, and investigates bugs exposed by testing gaps. Use when setting up mutation testing, reviewing campaign results, identifying equivalent mutants, or finding bugs from surviving mutations.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/mutation-testing/skills/mutation-testing", "install": ["npx skills add trailofbits/skills --skill mutation-testing"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/ossfuzz", "name": "ossfuzz", "kind": "skill", "official": false, "desc": "Enrolls a project in OSS-Fuzz, Google's free continuous fuzzing service for open source, and drives it locally. Covers project.yaml, Dockerfile and build.sh setup, the helper scripts, reproducing OSS-Fuzz crash reports, and the acceptance criteria. Use when setting up continuous fuzzing for an open-source project, reproducing an OSS-Fuzz bug report, or testing an OSS-Fuzz build before submitting it.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/ossfuzz", "install": ["npx skills add trailofbits/skills --skill ossfuzz"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/post-patch-validation/skills/post-patch-validation", "name": "post-patch-validation", "kind": "skill", "official": false, "desc": "Validates security patches with reproducible baseline-versus-patched evidence, including original exploits, root-cause variants, behavior preservation, regressions, and newly introduced security failures. Use after a patch exists and before accepting, merging, or reporting it as fixed; also use when an AI-generated patch, remediation commit, pull request, or proposed upstream fix needs adversarial post-patch validation across any language.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/post-patch-validation/skills/post-patch-validation", "install": ["npx skills add trailofbits/skills --skill post-patch-validation"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/regression-hunt/skills/prepare-regression", "name": "prepare-regression", "kind": "skill", "official": false, "desc": "Use when pinning before/after sources and collecting PR or commit context for a regression investigation.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/regression-hunt/skills/prepare-regression", "install": ["npx skills add trailofbits/skills --skill prepare-regression"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/property-based-testing/skills/property-based-testing", "name": "property-based-testing", "kind": "skill", "official": false, "desc": "Writes, reviews, and debugs property-based tests — Hypothesis, fast-check, proptest, jqwik, rapid, and Echidna or Medusa for Solidity invariants. Use whenever tests should cover a whole input domain instead of a hand-picked list of examples: encode/decode and serialize/deserialize pairs, parsers, canonicalizers and normalizers, validators, numeric and Decimal types, comparators and sort order, data structures, and smart-contract state invariants. Also use when adding cases to an existing @given,", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/property-based-testing/skills/property-based-testing", "install": ["npx skills add trailofbits/skills --skill property-based-testing"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/regression-hunt/skills/regression-hunt", "name": "regression-hunt", "kind": "skill", "official": false, "desc": "Use when investigating regressions in PRs or commits, coordinating a regression campaign, or resuming saved progress.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/regression-hunt/skills/regression-hunt", "install": ["npx skills add trailofbits/skills --skill regression-hunt"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/regression-hunt/skills/replay-regression", "name": "replay-regression", "kind": "skill", "official": false, "desc": "Use when independently verifying a supplied PoC against fresh live before/after deployments.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/regression-hunt/skills/replay-regression", "install": ["npx skills add trailofbits/skills --skill replay-regression"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/regression-hunt/skills/report-regressions", "name": "report-regressions", "kind": "skill", "official": false, "desc": "Use when assembling or refreshing an evidence-linked regression report from saved campaign decisions.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/regression-hunt/skills/report-regressions", "install": ["npx skills add trailofbits/skills --skill report-regressions"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/regression-hunt/skills/reproduce-regression", "name": "reproduce-regression", "kind": "skill", "official": false, "desc": "Use when deploying before/after systems and building a live-system PoC for a regression candidate.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/regression-hunt/skills/reproduce-regression", "install": ["npx skills add trailofbits/skills --skill reproduce-regression"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/ruzzy", "name": "ruzzy", "kind": "skill", "official": false, "desc": "Sets up and runs Ruzzy, Trail of Bits' coverage-guided Ruby fuzzer and the only production-ready one for the language. Covers harness structure, fuzzing pure Ruby and the native C extensions in gems, and sanitizer builds. Use when fuzzing a Ruby library or gem, testing a Ruby C extension for memory safety, or asking how to fuzz Ruby at all.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/ruzzy", "install": ["npx skills add trailofbits/skills --skill ruzzy"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/static-analysis/skills/sarif-parsing", "name": "sarif-parsing", "kind": "skill", "official": false, "desc": "Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on \"parse sarif\", \"read scan results\", \"aggregate findings\", \"deduplicate alerts\", or \"process sarif output\". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does NOT run scans — use the Semgrep or CodeQL skills for that.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/static-analysis/skills/sarif-parsing", "install": ["npx skills add trailofbits/skills --skill sarif-parsing"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/static-analysis/skills/semgrep", "name": "semgrep", "kind": "skill", "official": false, "desc": "Runs a Semgrep security scan over a codebase: detects languages, selects rulesets, presents the plan for explicit approval, then runs every approved ruleset through scripts/run-scans.sh, which batches the semgrep processes and writes scans.json, and merges the output to SARIF. Supports two scan modes, \"run all\" for full ruleset coverage and \"important only\" for security findings at medium-to-high confidence and impact. Uses Semgrep Pro for cross-file taint analysis when it is available. Use when", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/static-analysis/skills/semgrep", "install": ["npx skills add trailofbits/skills --skill semgrep"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:trailofbits/skills/plugins/testing-handbook-skills/skills/testing-handbook-generator", "name": "testing-handbook-generator", "kind": "skill", "official": false, "desc": "Generates Claude Code skills from the Trail of Bits Testing Handbook (appsec.guide), analyzing handbook pages and emitting SKILL.md files with the structure each skill type requires. Use when creating or refreshing a skill from handbook content, or when the user names the testing handbook or appsec.guide. Not for answering security testing questions — the generated skills cover those.", "repo": "https://github.com/trailofbits/skills/tree/HEAD/plugins/testing-handbook-skills/skills/testing-handbook-generator", "install": ["npx skills add trailofbits/skills --skill testing-handbook-generator"], "stars": 8179, "pushed": "2026-11-12T17:48:51Z", "license": "CC-BY-SA-4.0", "plat": "trail of bits testing handbook", "live": "Not checked (runs locally)"}, {"id": "skill:deanpeters/Product-Manager-Skills/plugins/pm-develop/skills/release-readiness", "name": "release-readiness", "kind": "skill", "official": false, "desc": "Check a release is safe to ship: tests, rollout, monitoring, rollback, support. Use when a build is about to go out and you need to know what could hurt, and how you'd undo it.", "repo": "https://github.com/deanpeters/Product-Manager-Skills/tree/HEAD/plugins/pm-develop/skills/release-readiness", "install": ["npx skills add deanpeters/Product-Manager-Skills --skill release-readiness"], "stars": 8014, "pushed": "2026-11-13T15:19:58Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:tw93/Waza/plugins/waza/skills/check", "name": "check", "kind": "skill", "official": false, "desc": "Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.", "repo": "https://github.com/tw93/Waza/tree/HEAD/plugins/waza/skills/check", "install": ["npx skills add tw93/Waza --skill check"], "stars": 7585, "pushed": "2026-11-11T07:02:04Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:tw93/Waza/plugins/waza/skills/hunt", "name": "hunt", "kind": "skill", "official": false, "desc": "Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.", "repo": "https://github.com/tw93/Waza/tree/HEAD/plugins/waza/skills/hunt", "install": ["npx skills add tw93/Waza --skill hunt"], "stars": 7585, "pushed": "2026-11-11T07:02:04Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:MengTo/Skills/agent-skills/game-development/optimize-threejs-games", "name": "optimize-threejs-games", "kind": "skill", "official": false, "desc": "Profile, diagnose, and improve Three.js or WebGL game performance without regressing gameplay. Use for frame-time drops, CPU/GPU pressure, draw calls, texture and geometry budgets, animation loops, adaptive quality, mobile performance, and browser performance verification.", "repo": "https://github.com/MengTo/Skills/tree/HEAD/agent-skills/game-development/optimize-threejs-games", "install": ["npx skills add MengTo/Skills --skill optimize-threejs-games"], "stars": 7464, "pushed": "2026-11-12T10:26:48Z", "license": "MIT", "plat": "three.js", "live": "Not checked (runs locally)"}, {"id": "skill:MengTo/Skills/agent-skills/game-development/test-playable-web-games", "name": "test-playable-web-games", "kind": "skill", "official": false, "desc": "Test a playable browser game end to end with deterministic fixtures and real browser evidence. Use for gameplay QA, regression testing, controls, accessibility, responsive/mobile testing, save flows, console checks, performance smoke tests, and release verification.", "repo": "https://github.com/MengTo/Skills/tree/HEAD/agent-skills/game-development/test-playable-web-games", "install": ["npx skills add MengTo/Skills --skill test-playable-web-games"], "stars": 7464, "pushed": "2026-11-12T10:26:48Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:internet-court/internet-court-skill/vendored/genlayer/direct-tests", "name": "direct-tests", "kind": "skill", "official": false, "desc": "Write and run fast direct mode tests for GenLayer intelligent contracts.", "repo": "https://github.com/internet-court/internet-court-skill/tree/HEAD/vendored/genlayer/direct-tests", "install": ["npx skills add internet-court/internet-court-skill --skill direct-tests"], "stars": 7120, "pushed": "2026-10-26T12:55:11Z", "license": "NOASSERTION", "plat": "genlayer", "live": "Not checked (runs locally)"}, {"id": "skill:internet-court/internet-court-skill/vendored/genlayer/integration-tests", "name": "integration-tests", "kind": "skill", "official": false, "desc": "Write and run integration tests against a GenLayer environment.", "repo": "https://github.com/internet-court/internet-court-skill/tree/HEAD/vendored/genlayer/integration-tests", "install": ["npx skills add internet-court/internet-court-skill --skill integration-tests"], "stars": 7120, "pushed": "2026-10-26T12:55:11Z", "license": "NOASSERTION", "plat": "genlayer", "live": "Not checked (runs locally)"}, {"id": "skill:czlonkowski/n8n-skills/skills/n8n-error-handling", "name": "n8n-error-handling", "kind": "skill", "official": false, "desc": "Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error branches/outputs, retries, retryOnFail, Respond to Webhook status codes, 4xx/5xx, Error Trigger, or \"my workflow fails silently\". Covers per-node error outputs and wiring, retry/self-healing, erro", "repo": "https://github.com/czlonkowski/n8n-skills/tree/HEAD/skills/n8n-error-handling", "install": ["npx skills add czlonkowski/n8n-skills --skill n8n-error-handling"], "stars": 6642, "pushed": "2026-10-24T11:44:27Z", "license": "MIT", "plat": "n8n", "live": "Not checked (runs locally)"}, {"id": "skill:czlonkowski/n8n-skills/skills/n8n-validation-expert", "name": "n8n-validation-expert", "kind": "skill", "official": false, "desc": "Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities. Consult this skill whenever a validate_node or validate_workflow call returns errors or warnings — it knows which warnings are false positives and which errors need real fixes.", "repo": "https://github.com/czlonkowski/n8n-skills/tree/HEAD/skills/n8n-validation-expert", "install": ["npx skills add czlonkowski/n8n-skills --skill n8n-validation-expert"], "stars": 6642, "pushed": "2026-10-24T11:44:27Z", "license": "MIT", "plat": "n8n", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Q00/ouroboros", "name": "Ouroboros", "kind": "mcp", "official": null, "desc": "Pins an acceptance spec; the verify command and expected output never enter the success contract.", "repo": "https://github.com/Q00/ouroboros", "install": ["pypi:ouroboros-ai"], "stars": 6358, "pushed": "2026-11-13T02:19:53Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/assertion-quality", "name": "assertion-quality", "kind": "skill", "official": false, "desc": "Analyze assertion quality, depth, variety, and false confidence in existing tests. ALWAYS USE when asked about weak, shallow, trivial, always-true, self-referential, assertion-free, presence/truthiness-only, or insufficiently diverse assertions, including MSTest, Jest, pytest, and Go. DO NOT USE for direct fixes: writing-mstest-tests owns supplied MSTest assertions; code-testing owns new cases. Use test-gap-analysis when asked whether tests would catch a production change, and test-anti-patterns", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/assertion-quality", "install": ["npx skills add dotnet/skills --skill assertion-quality"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/code-testing", "name": "code-testing", "kind": "skill", "official": false, "desc": "ALWAYS USE for test work that requires changes: write, add, generate, repair, or strengthen tests for existing code in xUnit, MSTest, NUnit, pytest, Vitest/Jest, Go, or another framework. Includes regression cases, failing or flaky tests, coverage-driven additions, and audit-then-fix requests. Focused work stays direct; broad or multi-stage work invokes test-engineer. DO NOT USE for only running tests, analysis-only audits, framework/platform migrations, a test blocked on a missing production se", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/code-testing", "install": ["npx skills add dotnet/skills --skill code-testing"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/code-testing-agent", "name": "code-testing-agent", "kind": "skill", "official": false, "desc": "Legacy compatibility alias for the code-testing skill. Do not self-activate for user requests and do not treat this name as a custom agent. When invoked explicitly by older instructions, load code-testing and follow it instead.", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/code-testing-agent", "install": ["npx skills add dotnet/skills --skill code-testing-agent"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/code-testing-extensions", "name": "code-testing-extensions", "kind": "skill", "official": false, "desc": "Provides file paths to language-specific extension files for the code-testing pipeline. Read this reference-only catalog for extension guidance files (e.g., dotnet.md for .NET, cpp.md for C++). Agents and skills read its bundled files directly; do not invoke this catalog through the model's skill tool.", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/code-testing-extensions", "install": ["npx skills add dotnet/skills --skill code-testing-extensions"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/coverage-analysis", "name": "coverage-analysis", "kind": "skill", "official": false, "desc": "Activation requires either supplied .NET coverage reports/percentages/line, branch, or condition metrics, or an explicit request to collect .NET coverage for analysis. USE FOR: interpreting that evidence, including Cobertura data, partial conditions, plateaus, target arithmetic, project-wide coverage-backed CRAP, and coverage-backed refactoring safety. Analyze supplied reports directly without rerunning tests or installing tools. DO NOT USE FOR: requests with neither coverage evidence nor explic", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/coverage-analysis", "install": ["npx skills add dotnet/skills --skill coverage-analysis"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/crap-score", "name": "crap-score", "kind": "skill", "official": false, "desc": "Calculates CRAP (Change Risk Anti-Patterns) for a named .NET method, class, or file. USE FOR: explicit CRAP calculation or coverage-and-complexity risk within that named target, including which tests to prioritize. DO NOT USE FOR: project-wide coverage/CRAP, plateaus, or project-wide blockers/priorities (coverage-analysis); behavioral/pseudo-mutation gaps (test-gap-analysis); writing tests; test runs without CRAP context.", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/crap-score", "install": ["npx skills add dotnet/skills --skill crap-score"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/.agents/skills/create-skill-test", "name": "create-skill-test", "kind": "skill", "official": false, "desc": "Scaffolds eval.yaml evaluation specs for skills, custom agents, and redistributable gh-aw workflow packages in the dotnet/skills repository. Use when creating skill or workflow-package tests, writing evaluation stimuli, defining graders and rubrics, sizing an eval for statistical power, or setting up test fixture files. Handles the Vally eval.yaml schema, fixture organization, and overfitting avoidance. Do not use for running or debugging existing evals (use improve-skill-quality) nor for skills", "repo": "https://github.com/dotnet/skills/tree/HEAD/.agents/skills/create-skill-test", "install": ["npx skills add dotnet/skills --skill create-skill-test"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/detect-static-dependencies", "name": "detect-static-dependencies", "kind": "skill", "official": false, "desc": "ACTIVATION PREREQUISITE: the request or discovered target must explicitly identify C#, .NET, `.cs`, or `.csproj`; otherwise stay dormant without invoking this skill. USE FOR: locating System.DateTime.Now/UtcNow, System.IO.File/Directory, System.Environment, HttpClient, Console, or Process usage in C#; auditing C# code for hard-to-test framework dependencies; or verifying those C# calls are already abstracted. DO NOT USE FOR: any target lacking the activation prerequisite; generating wrappers (us", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/detect-static-dependencies", "install": ["npx skills add dotnet/skills --skill detect-static-dependencies"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-upgrade/skills/dotnet-aot-compat", "name": "dotnet-aot-compat", "kind": "skill", "official": false, "desc": "Make .NET projects compatible with Native AOT and trimming by systematically resolving IL trim/AOT analyzer warnings. USE FOR: making projects AOT-compatible, fixing trimming warnings, resolving IL warnings (IL2026, IL2070, IL2067, IL2072, IL3050), adding DynamicallyAccessedMembers annotations, enabling IsAotCompatible. DO NOT USE FOR: publishing native AOT binaries, optimizing binary size, replacing reflection-heavy libraries with alternatives. INVOKES: no tools — pure knowledge skill.", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-upgrade/skills/dotnet-aot-compat", "install": ["npx skills add dotnet/skills --skill dotnet-aot-compat"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-experimental/skills/exp-mock-usage-analysis", "name": "exp-mock-usage-analysis", "kind": "skill", "official": false, "desc": "Audits .NET test mock usage by tracing each mock setup through the production code's execution path to find dead, unreachable, redundant, or replaceable mocks. Use when the user asks to audit mock usage, find unused or unnecessary mock setups, check if mocks are needed, reduce mock duplication or over-mocking, simplify test setup, or review whether mock configurations like ILogger/IOptions should use real implementations instead. Supports Moq, NSubstitute, and FakeItEasy.", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-experimental/skills/exp-mock-usage-analysis", "install": ["npx skills add dotnet/skills --skill exp-mock-usage-analysis"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-experimental/skills/exp-test-maintainability", "name": "exp-test-maintainability", "kind": "skill", "official": false, "desc": "Detects duplicate boilerplate, copy-paste tests, and structural maintainability issues across .NET test suites. Use when the user asks to reduce repetition, consolidate similar test methods, convert copy-paste tests to data-driven parameterized tests, suggest a better test structure, or identify refactoring opportunities. Identifies repeated construction, assertion patterns, copy-paste methods convertible to DataRow/Theory/TestCase, redundant setup/teardown, and shared infrastructure. Produces a", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-experimental/skills/exp-test-maintainability", "install": ["npx skills add dotnet/skills --skill exp-test-maintainability"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/filter-syntax", "name": "filter-syntax", "kind": "skill", "official": false, "desc": "Reference-only filter syntax for VSTest and MTP with MSTest, NUnit, xUnit v3, and TUnit. Load only after the platform/framework is known and a consumer needs to create or translate a filter. Do not load for unfiltered runs or platform detection. Used by run-tests and mtp-hot-reload; never invoke directly.", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/filter-syntax", "install": ["npx skills add dotnet/skills --skill filter-syntax"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/find-untested-sources", "name": "find-untested-sources", "kind": "skill", "official": false, "desc": "MANDATORY for static source-to-test pairing: find or list source files/modules without corresponding tests, or suggest test locations from repository structure. Invoke even for a tiny package; do not substitute manual globbing. Uses Roslyn for C#/.NET and tree-sitter for Python, TS/JS, Go, Java, Rust, Ruby, Kotlin, Swift, PowerShell, and C++. DO NOT USE FOR: real line/branch/Cobertura data, coverage-backed test priorities, CRAP risk, or grading existing tests.", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/find-untested-sources", "install": ["npx skills add dotnet/skills --skill find-untested-sources"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/generate-testability-wrappers", "name": "generate-testability-wrappers", "kind": "skill", "official": false, "desc": "DO NOT USE when the target already consumes an injected interface or built-in abstraction such as IFileSystem or TimeProvider, even if the request says \"generate a wrapper\"; no new wrapper is needed. Use only when C# source calls an ambient/static dependency and no injectable seam exists: first-time TimeProvider, IHttpClientFactory, or System.IO.Abstractions adoption; minimal Environment/Console/Process wrappers; IProcessRunner; DI registration; or an ambient seam that preserves a static API. Ex", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/generate-testability-wrappers", "install": ["npx skills add dotnet/skills --skill generate-testability-wrappers"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/grade-tests", "name": "grade-tests", "kind": "skill", "official": false, "desc": "Grade curated individual tests for readiness, A-F quality and improvements. ALWAYS USE FOR: grade tests, review only a named test, per-test readiness or quality bands for supplied methods, bodies, file spans or bounded PR diffs, including existing tests. Return Pass/Failed/Uncertain/Not applicable; unresolved/empty scopes omit grades. Compose read-only per-test evidence. Polyglot. DO NOT USE FOR: suite audits (test-engineer/test-anti-patterns), concrete fix/feature detection proof (test-value-ev", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/grade-tests", "install": ["npx skills add dotnet/skills --skill grade-tests"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-diag/skills/microbenchmarking", "name": "microbenchmarking", "kind": "skill", "official": false, "desc": "Activate this skill when BenchmarkDotNet (BDN) is involved in the task — creating, running, configuring, or reviewing BDN benchmarks. Also activate when microbenchmarking .NET code would be useful and BenchmarkDotNet is the likely tool. Consider activating when answering a .NET performance question requires measurement and BenchmarkDotNet may be needed. Covers microbenchmark design, BDN configuration and project setup, how to run BDN microbenchmarks efficiently and effectively, and using BDN for", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-diag/skills/microbenchmarking", "install": ["npx skills add dotnet/skills --skill microbenchmarking"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-upgrade/skills/migrate-dotnet10-to-dotnet11", "name": "migrate-dotnet10-to-dotnet11", "kind": "skill", "official": false, "desc": "Migrate a .NET 10 project or solution to .NET 11 and resolve all breaking changes. This is a MIGRATION skill — use it when upgrading from .NET 10 to .NET 11, NOT for writing new programs. USE FOR: upgrading TargetFramework from net10.0 to net11.0, fixing build errors after updating the .NET 11 SDK, resolving source-breaking and behavioral changes in .NET 11 runtime, C# 15 compiler, and EF Core 11, adapting to updated minimum hardware requirements (x86-64-v2, Arm64 LSE), and updating CI/CD pipeli", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-upgrade/skills/migrate-dotnet10-to-dotnet11", "install": ["npx skills add dotnet/skills --skill migrate-dotnet10-to-dotnet11"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-upgrade/skills/migrate-dotnet8-to-dotnet9", "name": "migrate-dotnet8-to-dotnet9", "kind": "skill", "official": false, "desc": "Migrate a .NET 8 project to .NET 9 and resolve all breaking changes. USE FOR: upgrading TargetFramework from net8.0 to net9.0, fixing build errors after updating the .NET 9 SDK, resolving behavioral changes in .NET 9 / C# 13 / ASP.NET Core 9 / EF Core 9, replacing BinaryFormatter (now always throws), resolving SYSLIB0054-SYSLIB0057, adapting to params span overload resolution, fixing C# 13 compiler changes, updating HttpClientFactory for SocketsHttpHandler, and resolving EF Core 9 migration/Cosm", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-upgrade/skills/migrate-dotnet8-to-dotnet9", "install": ["npx skills add dotnet/skills --skill migrate-dotnet8-to-dotnet9"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-upgrade/skills/migrate-dotnet9-to-dotnet10", "name": "migrate-dotnet9-to-dotnet10", "kind": "skill", "official": false, "desc": "Migrate a .NET 9 project or solution to .NET 10 and resolve all breaking changes. USE FOR: upgrading TargetFramework from net9.0 to net10.0, fixing build errors after updating the .NET 10 SDK, resolving source and behavioral changes in .NET 10 / C# 14 / ASP.NET Core 10 / EF Core 10, updating Dockerfiles for Debian-to-Ubuntu base images, resolving obsoletion warnings (SYSLIB0058-SYSLIB0062), adapting to SDK/NuGet changes (NU1510, PrunePackageReference), migrating System.Linq.Async to built-in Asy", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-upgrade/skills/migrate-dotnet9-to-dotnet10", "install": ["npx skills add dotnet/skills --skill migrate-dotnet9-to-dotnet10"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test-migration/skills/migrate-mstest-v1v2-to-v3", "name": "migrate-mstest-v1v2-to-v3", "kind": "skill", "official": false, "desc": "Use this skill before answering or editing whenever an MSTest v1/v2 project is being upgraded or repaired for v3. Triggers include QualityTools assembly references; MSTest.TestFramework/TestAdapter 1.x-2.x; \"upgrade to MSTest v3\"; comparing v1 and v2 migration paths; choosing MSTest or MSTest.Sdk; CS0411/CS1503 after a v3 package bump; DataRow type mismatch, MSTEST0014, or \"Test data doesn't match method parameters\"; .testsettings/LegacySettings to .runsettings; timeout changes; and net5.0 or ot", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test-migration/skills/migrate-mstest-v1v2-to-v3", "install": ["npx skills add dotnet/skills --skill migrate-mstest-v1v2-to-v3"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "mstest", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test-migration/skills/migrate-mstest-v3-to-v4", "name": "migrate-mstest-v3-to-v4", "kind": "skill", "official": false, "desc": "Use this skill before answering, planning, or editing any MSTest 3.x-to-4.x upgrade or post-upgrade failure. Triggers include \"MSTest v4 breaking changes\"; CS0507/CS0103/CS1061/CS1615; ExecuteAsync, CallerInfo, DisplayName, or custom TestMethodAttribute; ClassCleanupBehavior; ContainsKey; ThrowsExactly or ExpectedException; IsInstanceOfType out parameters; TestTimeout.Infinite; ManagedType; net6/net7 compatibility; TestCase.Id history; TestName in ClassInitialize; TreatDiscoveryWarningsAsErrors;", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test-migration/skills/migrate-mstest-v3-to-v4", "install": ["npx skills add dotnet/skills --skill migrate-mstest-v3-to-v4"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "mstest", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-upgrade/skills/migrate-nullable-references", "name": "migrate-nullable-references", "kind": "skill", "official": false, "desc": "Enable nullable reference types in a C# project and systematically resolve all warnings. USE FOR: adopting NRTs in existing codebases, file-by-file or project-wide migration, fixing CS8602/CS8618/CS86xx warnings, annotating APIs for nullability, cleaning up null-forgiving operators, upgrading dependencies with new nullable annotations. DO NOT USE FOR: projects already fully migrated with zero warnings (unless auditing suppressions), fixing a handful of nullable warnings in code that already has ", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-upgrade/skills/migrate-nullable-references", "install": ["npx skills add dotnet/skills --skill migrate-nullable-references"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test-migration/skills/migrate-nunit-to-mstest", "name": "migrate-nunit-to-mstest", "kind": "skill", "official": false, "desc": "Convert .NET tests from NUnit 3/4 to MSTest v4 while preserving VSTest or MTP. Use for replacing NUnit/NUnit3TestAdapter packages, Test/TestCase/ TestCaseSource/Values attributes, constraint assertions, SetUp/TearDown, OneTimeSetUp, SetUpFixture, FixtureLifeCycle, TestContext, categories, retries, timeouts, and NUnit parallelization. Also use when a \"convert NUnit to MSTest\" request may already be migrated: inspect and report the no-op. Do not use for NUnit version upgrades, xUnit/TUnit conversi", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test-migration/skills/migrate-nunit-to-mstest", "install": ["npx skills add dotnet/skills --skill migrate-nunit-to-mstest"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/migrate-static-to-wrapper", "name": "migrate-static-to-wrapper", "kind": "skill", "official": false, "desc": "ALWAYS USE when asked to migrate, replace, or make testable existing C# static calls with a named wrapper or built-in abstraction: DateTime.UtcNow/Now or DateTimeOffset.UtcNow to TimeProvider/IClock, File.* to IFileSystem or an existing store such as ITextFileStore, and Environment.* to an existing reader such as IEnvironmentReader. Covers scoped files/projects, constructor injection, replacing temp-file or process-environment tests with fakes, \"already registered\" abstractions, and static class", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/migrate-static-to-wrapper", "install": ["npx skills add dotnet/skills --skill migrate-static-to-wrapper"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test-migration/skills/migrate-vstest-to-mtp", "name": "migrate-vstest-to-mtp", "kind": "skill", "official": false, "desc": "Use this skill before answering, planning, or editing whenever .NET tests or CI are switching from VSTest to Microsoft.Testing.Platform (MTP), or an MTP migration behaves differently. Triggers include \"switch from VSTest\"; MSTest/NUnit/xUnit MTP enablement; OutputType=Exe only for test projects in Directory.Build.props; EnableMSTestRunner, EnableNUnitRunner, UseMicrosoftTestingPlatformRunner, or YTest.MTP.XUnit2; .NET 10 global.json test.runner and TestingPlatformDotnetTestSupport; translating V", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test-migration/skills/migrate-vstest-to-mtp", "install": ["npx skills add dotnet/skills --skill migrate-vstest-to-mtp"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test-migration/skills/migrate-xunit-to-mstest", "name": "migrate-xunit-to-mstest", "kind": "skill", "official": false, "desc": "Convert .NET tests from xUnit.net v2/v3 to MSTest v4 while preserving VSTest or MTP. Use for replacing xunit packages, Fact/Theory/InlineData/MemberData, assertions, IClassFixture/ICollectionFixture, ITestOutputHelper, TestContext cancellation, traits/Owner, skips, timeouts, and xUnit parallelization. Also use when a \"convert xUnit to MSTest\" request may already be migrated: inspect and report the no-op. Do not use for xUnit v2-to-v3, MSTest upgrades, NUnit/TUnit conversion, or runner-only VSTes", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test-migration/skills/migrate-xunit-to-mstest", "install": ["npx skills add dotnet/skills --skill migrate-xunit-to-mstest"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test-migration/skills/migrate-xunit-to-xunit-v3", "name": "migrate-xunit-to-xunit-v3", "kind": "skill", "official": false, "desc": "Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest attributes, Xunit.SkippableFact, xunit.abstractions/extensibility consolidation, and Xunit.Combinatorial/StaFact compatibility. Do not use for framework conversion or a runner-only migra", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test-migration/skills/migrate-xunit-to-xunit-v3", "install": ["npx skills add dotnet/skills --skill migrate-xunit-to-xunit-v3"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/mtp-hot-reload", "name": "mtp-hot-reload", "kind": "skill", "official": false, "desc": "Set up or recover MTP hot reload for a long-lived console-host edit/re-run loop in a Microsoft Testing Platform project. Use for explicit MTP console requests such as \"enable hot reload\", \"dotnet run to rerun on edit\", or unsupported/rude edits. Covers setup, run/watch, restarts, filters, and the VSTest no-mutation fallback. For one-time runs, exact commands, filter errors, TRX/dumps, or merely a failing test, use run-tests. Do not use when Test Explorer or an IDE should rerun tests without an M", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/mtp-hot-reload", "install": ["npx skills add dotnet/skills --skill mtp-hot-reload"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/platform-detection", "name": "platform-detection", "kind": "skill", "official": false, "desc": "Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system. Use only for \"which test platform/framework?\", \"VSTest or MTP?\", or \"what runner does this project use?\", including bridge settings, UseVSTest opt-outs, and incompatible or conflicting VSTest/MTP configuration. Resolves global.json, project, packages.config, Directory.Build.props, and Directory.Packages.props precedence for MSTest/xUnit/NUnit/TUnit. DO NOT USE when the user asks to run/filt", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/platform-detection", "install": ["npx skills add dotnet/skills --skill platform-detection"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/run-tests", "name": "run-tests", "kind": "skill", "official": false, "desc": "ALWAYS USE before running .NET tests or answering with a test command or flags. Trigger on \"run the tests\", \"exact dotnet test command\", one test/class/category/trait/target framework, combined filters, `--filter-query`, `--no-build`, `--diag`, diagnostic logs, TRX, coverage collection, crash/hang dumps, filter errors, or unrecognized options. Chooses repository-compatible classic, VSTest, bridged MTP, or native MTP syntax for MSTest/xUnit/NUnit/TUnit. DO NOT USE for platform identification alon", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/run-tests", "install": ["npx skills add dotnet/skills --skill run-tests"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/scaffold-dotnet-test-project", "name": "scaffold-dotnet-test-project", "kind": "skill", "official": false, "desc": "MUST USE when an existing .NET test project was excluded from a .slnf/CI solution filter, disappeared from .sln/.slnx discovery, or lost its production ProjectReference; also for requests to set up, create, reuse, add, register, include, or repair a test project. Handles \"tests pass directly but CI discovers zero\", exact solution wiring, xUnit/NUnit/MSTest, and central packages. DO NOT USE to only author tests in an already-wired project (code-testing), run tests, migrate, or correct MSTest synt", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/scaffold-dotnet-test-project", "install": ["npx skills add dotnet/skills --skill scaffold-dotnet-test-project"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/test-analysis-extensions", "name": "test-analysis-extensions", "kind": "skill", "official": false, "desc": "Provides file paths to language-specific reference files for the test ANALYSIS skills (assertion-quality, test-anti-patterns, test-gap-analysis, test-smell-detection, test-tagging). Read this catalog to discover available extension files (e.g., dotnet.md for .NET/MSTest/xUnit/NUnit/TUnit, python.md for pytest/unittest, typescript.md for Jest/Vitest/Mocha, java.md for JUnit/TestNG, etc.). Do not invoke this reference-only skill — its bundled files are read by the quality agent and analysis skills", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/test-analysis-extensions", "install": ["npx skills add dotnet/skills --skill test-analysis-extensions"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/test-anti-patterns", "name": "test-anti-patterns", "kind": "skill", "official": false, "desc": "Audit a test file or suite; produce a severity-ranked diagnostic report. ALWAYS USE for tests that verify nothing, missing/tautological assertions, swallowed/broad exceptions, flaky/order-dependent tests, duplication, or magic values. Polyglot. DO NOT USE for direct edits: writing-mstest-tests owns supplied MSTest assertions/attributes/lifecycle; code-testing owns new tests. Exclude running tests, migration, assertion metrics (assertion-quality), raw .NET coverage collection (run-tests), non-.NE", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/test-anti-patterns", "install": ["npx skills add dotnet/skills --skill test-anti-patterns"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/test-gap-analysis", "name": "test-gap-analysis", "kind": "skill", "official": false, "desc": "Find caller-visible production changes existing tests would miss through pseudo-mutation analysis; verify candidates or close gaps only when requested. Includes read-only per-test composition for grading. Polyglot. USE FOR: would tests catch a bug, behavioral blind spots, surviving mutations. DO NOT USE FOR: concrete fix/feature revision proof (test-value-evidence); suite taxonomy (test-tagging); .NET coverage, Cobertura, plateaus or coverage-backed priorities (coverage-analysis); named CRAP (cr", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/test-gap-analysis", "install": ["npx skills add dotnet/skills --skill test-gap-analysis"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/test-smell-detection", "name": "test-smell-detection", "kind": "skill", "official": false, "desc": "Audits existing tests in any language using formal, research-backed test smell names and the testsmells.org 19-smell academic taxonomy. Use when the caller asks for an academic or citable test-smell review, named smell categories, or a formal severity-ranked smell assessment. Covers Assertion Roulette, Conditional Test Logic, Mystery Guest, Eager Test, Sleepy Test, Unknown Test, Sensitive Equality, and the rest of the catalog across .NET, Python, JavaScript/TypeScript, Java, Go, Ruby, Rust, Swif", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/test-smell-detection", "install": ["npx skills add dotnet/skills --skill test-smell-detection"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/test-tagging", "name": "test-tagging", "kind": "skill", "official": false, "desc": "Classifies existing tests by standard traits and reports their distribution. USE FOR: tagging all tests with category attributes, categorizing/tagging/ labeling each test, compare happy vs error paths, audit the test mix, describe coverage shape by test type, or tag then verify the project builds. Read bodies when names mislead. Apply canonical attributes; otherwise report only. DO NOT USE FOR: requests owned by test-anti-patterns, coverage-analysis, crap-score, test-gap-analysis, code-testing, ", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/test-tagging", "install": ["npx skills add dotnet/skills --skill test-tagging"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/test-value-evidence", "name": "test-value-evidence", "kind": "skill", "official": false, "desc": "Assess tests for an identified code or test change, feature, PR or commit. USE FOR: review changed behavior or regression tests, prove pre-fix/missing behavior is detected, revision-bound red-green evidence. Polyglot. DO NOT USE without an identified change: hypothetical mutations or general suite blind spots (test-gap-analysis). Also exclude per-test readiness/A-F grades (grade-tests), coverage (coverage-analysis), new suites (code-testing), or mutation engines.", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/test-value-evidence", "install": ["npx skills add dotnet/skills --skill test-value-evidence"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/testability-obstacle", "name": "testability-obstacle", "kind": "skill", "official": false, "desc": "MUST USE for C#/.NET deterministic tests that require the smallest production seam for DateTime/Task.Delay/File/Environment/Guid/Random, static API preservation, nested/parallel overrides, or no real I/O. USE ONLY when the target workspace contains C# source plus a .csproj or .sln. DO NOT USE for audits, bulk migration, code that already has an injectable seam, or an explicit migration to a user-named existing abstraction (migrate-static-to-wrapper). Use instead of general test generation when t", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/testability-obstacle", "install": ["npx skills add dotnet/skills --skill testability-obstacle"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-upgrade/skills/thread-abort-migration", "name": "thread-abort-migration", "kind": "skill", "official": false, "desc": "Guides migration of .NET Framework Thread.Abort usage to cooperative cancellation in modern .NET. USE FOR: modernizing code that calls Thread.Abort, catching ThreadAbortException, replacing Thread.ResetAbort, replacing Thread.Interrupt for thread termination, resolving PlatformNotSupportedException or SYSLIB0006 after retargeting to .NET 6+, migrating ASP.NET Response.End or Response.Redirect(url, true) which internally call Thread.Abort. DO NOT USE FOR: code that only uses Thread.Join, Thread.S", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-upgrade/skills/thread-abort-migration", "install": ["npx skills add dotnet/skills --skill thread-abort-migration"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:dotnet/skills/plugins/dotnet-test/skills/writing-mstest-tests", "name": "writing-mstest-tests", "kind": "skill", "official": false, "desc": "ALWAYS USE when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for \"review\" when corrected code or edits are wanted, even for one pasted assertion or passing tests with bad failure output. Covers expected/actual labels; generic Boolean, collection, string, numeric, null, identity, exception, hard-cast, and object[] checks; TestContext/lifecycle; timeout/cancellation; OS/CI conditions, retry, clean", "repo": "https://github.com/dotnet/skills/tree/HEAD/plugins/dotnet-test/skills/writing-mstest-tests", "install": ["npx skills add dotnet/skills --skill writing-mstest-tests"], "stars": 6155, "pushed": "2026-11-13T20:11:12Z", "license": "MIT", "plat": "c#/.net", "live": "Not checked (runs locally)"}, {"id": "skill:antfu/skills/skills/vitest", "name": "vitest", "kind": "skill", "official": false, "desc": "Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures.", "repo": "https://github.com/antfu/skills/tree/HEAD/skills/vitest", "install": ["npx skills add antfu/skills --skill vitest"], "stars": 6067, "pushed": "2026-11-11T08:13:27Z", "license": "MIT", "plat": "vite", "live": "Not checked (runs locally)"}, {"id": "skill:breaking-brake/cc-wf-studio/.claude/skills/next-qa", "name": "next-qa", "kind": "skill", "official": false, "desc": "Run one unattended iteration of the QUALITY-ASSURANCE loop — steward any in-flight QA PR, then build ONE queued `qa` issue (test infrastructure, unit tests, regression tests for known bugs) on a branch off auto-qa and open a PR that squash-merges on green CI. Adds tests and tooling only; never edits product source. Use when the user says \"QAタスク\", \"next qa\", \"テストを進めて\", or wants autonomous progress on the quality track.", "repo": "https://github.com/breaking-brake/cc-wf-studio/tree/HEAD/.claude/skills/next-qa", "install": ["npx skills add breaking-brake/cc-wf-studio --skill next-qa"], "stars": 5455, "pushed": "2026-10-07T00:11:01Z", "license": "NOASSERTION", "plat": "cc-wf-studio", "live": "Not checked (runs locally)"}, {"id": "skill:breaking-brake/cc-wf-studio/.claude/skills/next-task", "name": "next-task", "kind": "skill", "official": false, "desc": "Run one unattended IMPLEMENTATION iteration of the autonomous value-creation loop — steward any in-flight PR, fix interrupts (red CI / security / human bugs), or else build ONE queued `idea` issue on a branch off auto-dev and open a PR that squash-merges on green CI. Ideation lives in the next-idea skill; this skill consumes its queue. Use when the user says \"次のタスク\", \"next task\", \"続きをやって\", or wants autonomous progress without specifying what to do.", "repo": "https://github.com/breaking-brake/cc-wf-studio/tree/HEAD/.claude/skills/next-task", "install": ["npx skills add breaking-brake/cc-wf-studio --skill next-task"], "stars": 5455, "pushed": "2026-10-07T00:11:01Z", "license": "NOASSERTION", "plat": "cc-wf-studio", "live": "Not checked (runs locally)"}, {"id": "skill:metalbear-co/mirrord/mirrord/mcp/corpus/skills/mirrord-chaos", "name": "mirrord-chaos", "kind": "skill", "official": false, "desc": "Help users chaos test their app with mirrord: inject artificial latency or connection errors into a mirrord session's outgoing traffic via per-session chaos rules managed with the `mirrord chaos` CLI. Use when a user wants to add latency or delay to outgoing connections or a dependency (e.g. a slow database), simulate connection failures (reset, timed out, refused), test app behavior under degraded network conditions, or wire chaos rules into CI test runs. Always use this skill instead of the de", "repo": "https://github.com/metalbear-co/mirrord/tree/HEAD/mirrord/mcp/corpus/skills/mirrord-chaos", "install": ["npx skills add metalbear-co/mirrord --skill mirrord-chaos"], "stars": 5411, "pushed": "2026-11-14T04:04:31Z", "license": "MIT", "plat": "mirrord", "live": "Not checked (runs locally)"}, {"id": "skill:metalbear-co/mirrord/mirrord/mcp/corpus/skills/mirrord-ci", "name": "mirrord-ci", "kind": "skill", "official": false, "desc": "Help users set up mirrord in CI pipelines for testing against real Kubernetes environments. Use when users want to run end-to-end tests, integration tests, or automated tests in CI using mirrord to connect to staging/shared clusters.", "repo": "https://github.com/metalbear-co/mirrord/tree/HEAD/mirrord/mcp/corpus/skills/mirrord-ci", "install": ["npx skills add metalbear-co/mirrord --skill mirrord-ci"], "stars": 5411, "pushed": "2026-11-14T04:04:31Z", "license": "MIT", "plat": "mirrord", "live": "Not checked (runs locally)"}, {"id": "skill:brycewang-stanford/Auto-Empirical-Research-Skills/skills/15-Felpix-Studios-social-science-research/skills/review-r", "name": "review-r", "kind": "skill", "official": false, "desc": "Run the R code review protocol on R scripts. Checks code quality, reproducibility, domain correctness, and professional standards. Produces a report without editing files. Make sure to use this skill whenever the user wants their existing R code evaluated or audited — not when they want new analysis written. Triggers include: \"review my R script\", \"check my R code\", \"is my code replication-ready\", \"audit this R file\", \"does this code follow conventions\", \"will this reproduce\", \"check my analysis", "repo": "https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/HEAD/skills/15-Felpix-Studios-social-science-research/skills/review-r", "install": ["npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill review-r"], "stars": 5013, "pushed": "2026-11-09T13:27:49Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:brycewang-stanford/Auto-Empirical-Research-Skills/skills/26-Data-Wise-scholar/skills/implementation/statistical-software-qa", "name": "statistical-software-qa", "kind": "skill", "official": false, "desc": "Quality assurance and testing protocols for statistical software", "repo": "https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/HEAD/skills/26-Data-Wise-scholar/skills/implementation/statistical-software-qa", "install": ["npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill statistical-software-qa"], "stars": 5013, "pushed": "2026-11-09T13:27:49Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:com.mock-server/mockserver", "name": "com.mock-server/mockserver", "kind": "mcp", "official": null, "desc": "Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.", "repo": "https://github.com/mock-server/mockserver-monorepo", "install": ["oci:docker.io/mockserver/mockserver:9.2.0"], "stars": 5010, "pushed": "2026-11-13T02:28:04Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:zebbern/claude-code-guide/skills/playwright/core", "name": "playwright-core", "kind": "skill", "official": false, "desc": "Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, assertions, fixtures, network mocking, auth flows, debugging, and framework recipes for React, Next.js, Vue, and Angular. TypeScript and JavaScript.", "repo": "https://github.com/zebbern/claude-code-guide/tree/HEAD/skills/playwright/core", "install": ["npx skills add zebbern/claude-code-guide --skill playwright-core"], "stars": 4708, "pushed": "2026-11-14T00:35:12Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:zebbern/claude-code-guide/skills/playwright/migration", "name": "playwright-migration", "kind": "skill", "official": false, "desc": "Step-by-step migration guides for moving to Playwright from Cypress or Selenium/WebDriver — command mappings, architecture changes, and incremental adoption strategies.", "repo": "https://github.com/zebbern/claude-code-guide/tree/HEAD/skills/playwright/migration", "install": ["npx skills add zebbern/claude-code-guide --skill playwright-migration"], "stars": 4708, "pushed": "2026-11-14T00:35:12Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:zebbern/claude-code-guide/skills/playwright/pom", "name": "playwright-pom", "kind": "skill", "official": false, "desc": "Page Object Model patterns for Playwright — when to use POM, how to structure page objects, and when fixtures or helpers are a better fit.", "repo": "https://github.com/zebbern/claude-code-guide/tree/HEAD/skills/playwright/pom", "install": ["npx skills add zebbern/claude-code-guide --skill playwright-pom"], "stars": 4708, "pushed": "2026-11-14T00:35:12Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:zebbern/claude-code-guide/skills/playwright", "name": "playwright-skill", "kind": "skill", "official": false, "desc": "Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, fixtures, POM, network mocking, auth flows, debugging, CI/CD (GitHub Actions, GitLab, CircleCI, Azure, Jenkins), framework recipes (React, Next.js, Vue, Angular), and migration guides from Cypress/Selenium. TypeScript and JavaScript.", "repo": "https://github.com/zebbern/claude-code-guide/tree/HEAD/skills/playwright", "install": ["npx skills add zebbern/claude-code-guide --skill playwright-skill"], "stars": 4708, "pushed": "2026-11-14T00:35:12Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:zebbern/claude-code-guide/skills/test-driven-dev", "name": "test-driven-dev", "kind": "skill", "official": false, "desc": "Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions \"red-green-refactor\", wants integration tests, or asks for test-first development.", "repo": "https://github.com/zebbern/claude-code-guide/tree/HEAD/skills/test-driven-dev", "install": ["npx skills add zebbern/claude-code-guide --skill test-driven-dev"], "stars": 4708, "pushed": "2026-11-14T00:35:12Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:zebbern/claude-code-guide/skills/test-suite-architect", "name": "test-suite-architect", "kind": "skill", "official": false, "desc": "This skill should be used when establishing comprehensive QA testing processes for any software project. Use when creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports. Includes autonomous execution capability via master prompts and complete documentation templates for third-party QA team handoffs. Implements OWASP security testing and achieves 90%", "repo": "https://github.com/zebbern/claude-code-guide/tree/HEAD/skills/test-suite-architect", "install": ["npx skills add zebbern/claude-code-guide --skill test-suite-architect"], "stars": 4708, "pushed": "2026-11-14T00:35:12Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:zenbu-labs/terminal-browser/.claude/skills/verify", "name": "verify", "kind": "skill", "official": false, "desc": "Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.", "repo": "https://github.com/zenbu-labs/terminal-browser/tree/HEAD/.claude/skills/verify", "install": ["npx skills add zenbu-labs/terminal-browser --skill verify"], "stars": 4636, "pushed": "2026-11-14T02:24:42Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:zgsm-ai/costrict/.roo/skills/evals-context", "name": "evals-context", "kind": "skill", "official": false, "desc": "Provides context about the CoStrict evals system structure in this monorepo. Use when tasks mention \"evals\", \"evaluation\", \"eval runs\", \"eval exercises\", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals, apps/web-evals) and the public website evals display page (apps/web-roo-code/src/app/evals).", "repo": "https://github.com/zgsm-ai/costrict/tree/HEAD/.roo/skills/evals-context", "install": ["npx skills add zgsm-ai/costrict --skill evals-context"], "stars": 4463, "pushed": "2026-09-30T09:24:54Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:httprunner/httprunner", "name": "httprunner", "kind": "mcp", "official": null, "desc": "HttpRunner 是一款开源的 API/UI 测试框架，简单易用，功能强大，具有丰富的插件化机制和高度的可扩展能力。", "repo": "https://github.com/httprunner/httprunner", "install": [], "stars": 4307, "pushed": null, "license": null, "plat": "api/ui", "live": "Not checked (runs locally)"}, {"id": "skill:michael-denyer/pstack-claude/plugins/pstack/skills/benchmark-checklist", "name": "benchmark-checklist", "kind": "skill", "official": false, "desc": "Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.", "repo": "https://github.com/michael-denyer/pstack-claude/tree/HEAD/plugins/pstack/skills/benchmark-checklist", "install": ["npx skills add michael-denyer/pstack-claude --skill benchmark-checklist"], "stars": 4298, "pushed": "2026-11-13T15:53:05Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:michael-denyer/pstack-claude/plugins/pstack/skills/blast-radius", "name": "blast-radius", "kind": "skill", "official": false, "desc": "Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', reviewing a small diff you don't trust, or a brief that asserts something about existing code ('make X public', 'X already handles Y') before you design against that assertion.", "repo": "https://github.com/michael-denyer/pstack-claude/tree/HEAD/plugins/pstack/skills/blast-radius", "install": ["npx skills add michael-denyer/pstack-claude --skill blast-radius"], "stars": 4298, "pushed": "2026-11-13T15:53:05Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:michael-denyer/pstack-claude/plugins/pstack/skills/correct", "name": "correct", "kind": "skill", "official": false, "desc": "Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.", "repo": "https://github.com/michael-denyer/pstack-claude/tree/HEAD/plugins/pstack/skills/correct", "install": ["npx skills add michael-denyer/pstack-claude --skill correct"], "stars": 4298, "pushed": "2026-11-13T15:53:05Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:michael-denyer/pstack-claude/plugins/pstack/skills/maintain-formal-verification-skill", "name": "maintain-formal-verification-skill", "kind": "skill", "official": false, "desc": "Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \\\"is the model still true to the code\\\", or after merges and refactors that touched verified code without rechecking it.", "repo": "https://github.com/michael-denyer/pstack-claude/tree/HEAD/plugins/pstack/skills/maintain-formal-verification-skill", "install": ["npx skills add michael-denyer/pstack-claude --skill maintain-formal-verification-skill"], "stars": 4298, "pushed": "2026-11-13T15:53:05Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:michael-denyer/pstack-claude/plugins/pstack/skills/maintain-verification-skill", "name": "maintain-verification-skill", "kind": "skill", "official": false, "desc": "Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or \\\"audit the verify skill\\\".", "repo": "https://github.com/michael-denyer/pstack-claude/tree/HEAD/plugins/pstack/skills/maintain-verification-skill", "install": ["npx skills add michael-denyer/pstack-claude --skill maintain-verification-skill"], "stars": 4298, "pushed": "2026-11-13T15:53:05Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:expo/skills/.claude/skills/expo-skill-eval", "name": "expo-skill-eval", "kind": "skill", "official": false, "desc": "Evaluate Expo skills in this repo end-to-end - trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via Expo Go (web optional). Use when the user wants to eval an Expo skill, test that a skill produces working code, benchmark a skill with device screenshots, or verify a skill's output renders correctly.", "repo": "https://github.com/expo/skills/tree/HEAD/.claude/skills/expo-skill-eval", "install": ["npx skills add expo/skills --skill expo-skill-eval"], "stars": 4131, "pushed": "2026-11-13T12:55:41Z", "license": "MIT", "plat": "expo", "live": "Not checked (runs locally)"}, {"id": "skill:Dimillian/Skills/bug-hunt-swarm", "name": "bug-hunt-swarm", "kind": "skill", "official": false, "desc": "Parallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures. Use when the user asks to investigate a bug, find the root cause, trace a regression, understand why something broke, or wants a ranked diagnosis with the fastest proof path without making code edits.", "repo": "https://github.com/Dimillian/Skills/tree/HEAD/bug-hunt-swarm", "install": ["npx skills add Dimillian/Skills --skill bug-hunt-swarm"], "stars": 4028, "pushed": "2026-03-29T15:28:02Z", "license": "MIT", "plat": "bug-hunt-swarm", "live": "Not checked (runs locally)"}, {"id": "skill:Dimillian/Skills/review-swarm", "name": "review-swarm", "kind": "skill", "official": false, "desc": "Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files.", "repo": "https://github.com/Dimillian/Skills/tree/HEAD/review-swarm", "install": ["npx skills add Dimillian/Skills --skill review-swarm"], "stars": 4028, "pushed": "2026-03-29T15:28:02Z", "license": "MIT", "plat": "review-swarm", "live": "Not checked (runs locally)"}, {"id": "skill:NVIDIA/skills/skills/compute-sanitizer-diagnose-cuda-bugs", "name": "compute-sanitizer-diagnose-cuda-bugs", "kind": "skill", "official": false, "desc": "Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when debugging illegal memory access, out-of-bounds, misaligned access, leaks, WAW/WAR/RAW races, __shared__ hazards, uninitialized reads, garbage results, hangs, divergent __syncthreads/__sy", "repo": "https://github.com/NVIDIA/skills/tree/HEAD/skills/compute-sanitizer-diagnose-cuda-bugs", "install": ["npx skills add NVIDIA/skills --skill compute-sanitizer-diagnose-cuda-bugs"], "stars": 3954, "pushed": "2026-11-12T14:09:43Z", "license": "Apache-2.0", "plat": "cuda", "live": "Not checked (runs locally)"}, {"id": "skill:NVIDIA/skills/skills/deepstream-profile-pipeline", "name": "deepstream-profile-pipeline", "kind": "skill", "official": false, "desc": "Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to benchmark, tune, or measure FPS.", "repo": "https://github.com/NVIDIA/skills/tree/HEAD/skills/deepstream-profile-pipeline", "install": ["npx skills add NVIDIA/skills --skill deepstream-profile-pipeline"], "stars": 3954, "pushed": "2026-11-12T14:09:43Z", "license": "Apache-2.0", "plat": "deepstream", "live": "Not checked (runs locally)"}, {"id": "skill:NVIDIA/skills/skills/fastgen-validate", "name": "fastgen-validate", "kind": "skill", "official": false, "desc": "Validate NVIDIA FastGen integrations and training quality: numerical parity against reference implementations, seeded side-by-side media, gradient and trainability checks, checkpoint round trips and repository tests. Use it whenever a claim about correctness, parity or quality needs evidence.", "repo": "https://github.com/NVIDIA/skills/tree/HEAD/skills/fastgen-validate", "install": ["npx skills add NVIDIA/skills --skill fastgen-validate"], "stars": 3954, "pushed": "2026-11-12T14:09:43Z", "license": "Apache-2.0", "plat": "nvidia fastgen", "live": "Not checked (runs locally)"}, {"id": "skill:NVIDIA/skills/skills/holoscan-app-debug-build-run", "name": "holoscan-app-debug-build-run", "kind": "skill", "official": false, "desc": "Use when a concrete holoscan command in holoscan-applications or a standalone Module fails, hangs, regresses, or returns wrong output.", "repo": "https://github.com/NVIDIA/skills/tree/HEAD/skills/holoscan-app-debug-build-run", "install": ["npx skills add NVIDIA/skills --skill holoscan-app-debug-build-run"], "stars": 3954, "pushed": "2026-11-12T14:09:43Z", "license": "Apache-2.0", "plat": "holoscan", "live": "Not checked (runs locally)"}, {"id": "skill:NVIDIA/skills/skills/mcore-testing", "name": "mcore-testing", "kind": "skill", "official": false, "desc": "Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.", "repo": "https://github.com/NVIDIA/skills/tree/HEAD/skills/mcore-testing", "install": ["npx skills add NVIDIA/skills --skill mcore-testing"], "stars": 3954, "pushed": "2026-11-12T14:09:43Z", "license": "Apache-2.0", "plat": "megatron-lm", "live": "Not checked (runs locally)"}, {"id": "skill:parcadei/Continuous-Claude-v3/.claude/skills/debug", "name": "debug", "kind": "skill", "official": false, "desc": "Debug issues by investigating logs, database state, and git history", "repo": "https://github.com/parcadei/Continuous-Claude-v3/tree/HEAD/.claude/skills/debug", "install": ["npx skills add parcadei/Continuous-Claude-v3 --skill debug"], "stars": 3949, "pushed": "2026-01-26T15:27:49Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:parcadei/Continuous-Claude-v3/.claude/skills/debug-hooks", "name": "debug-hooks", "kind": "skill", "official": false, "desc": "Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.", "repo": "https://github.com/parcadei/Continuous-Claude-v3/tree/HEAD/.claude/skills/debug-hooks", "install": ["npx skills add parcadei/Continuous-Claude-v3 --skill debug-hooks"], "stars": 3949, "pushed": "2026-01-26T15:27:49Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:parcadei/Continuous-Claude-v3/.claude/skills/fix", "name": "fix", "kind": "skill", "official": false, "desc": "Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.", "repo": "https://github.com/parcadei/Continuous-Claude-v3/tree/HEAD/.claude/skills/fix", "install": ["npx skills add parcadei/Continuous-Claude-v3 --skill fix"], "stars": 3949, "pushed": "2026-01-26T15:27:49Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:samber/cc-skills-golang/skills/golang-stretchr-testify", "name": "golang-stretchr-testify", "kind": "skill", "official": false, "desc": "Comprehensive guide to stretchr/testify for Golang testing. Covers assert, require, mock, and suite packages in depth. Use when writing tests with testify, creating mocks, setting up test suites, or choosing between assert and require. Covers testify assertions, mock expectations, argument matchers, call verification, suite lifecycle, and advanced patterns like Eventually, JSONEq, and custom matchers. Apply when the codebase imports github.com/stretchr/testify.", "repo": "https://github.com/samber/cc-skills-golang/tree/HEAD/skills/golang-stretchr-testify", "install": ["npx skills add samber/cc-skills-golang --skill golang-stretchr-testify"], "stars": 3848, "pushed": "2026-11-08T21:55:32Z", "license": "MIT", "plat": "golang", "live": "Not checked (runs locally)"}, {"id": "skill:samber/cc-skills-golang/skills/golang-testing", "name": "golang-testing", "kind": "skill", "official": false, "desc": "Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI, or debugging flaky/slow tests. For testify-specific APIs see `samber/cc-skills-golang@golang-stretchr-testify`; for measurement methodology see `samber/cc-skills-golang@golang-benchm", "repo": "https://github.com/samber/cc-skills-golang/tree/HEAD/skills/golang-testing", "install": ["npx skills add samber/cc-skills-golang --skill golang-testing"], "stars": 3848, "pushed": "2026-11-08T21:55:32Z", "license": "MIT", "plat": "golang", "live": "Not checked (runs locally)"}, {"id": "skill:samber/cc-skills-golang/skills/golang-troubleshooting", "name": "golang-troubleshooting", "kind": "skill", "official": false, "desc": "Troubleshoot Golang programs systematically - find and fix the root cause. Use when encountering bugs, crashes, deadlocks, races, or unexpected behavior in Go code. Covers debugging methodology, common Go pitfalls, test-driven debugging, pprof setup and capture, Delve, race detection, GODEBUG tracing, and production debugging. Start here for any 'something is wrong' situation. Not for interpreting profiles or benchmarking (→ See `samber/cc-skills-golang@golang-benchmark` skill), applying optimiz", "repo": "https://github.com/samber/cc-skills-golang/tree/HEAD/skills/golang-troubleshooting", "install": ["npx skills add samber/cc-skills-golang --skill golang-troubleshooting"], "stars": 3848, "pushed": "2026-11-08T21:55:32Z", "license": "MIT", "plat": "golang", "live": "Not checked (runs locally)"}, {"id": "skill:foryourhealth111-pixel/Vibe-Skills/bundled/skills/generating-test-reports", "name": "generating-test-reports", "kind": "skill", "official": false, "desc": "Generate structured test reports with pass/fail rollups, coverage summaries, and test artifacts. Use when the user is asking for test-result packaging or delivery, not for root-cause debugging or feature implementation.", "repo": "https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/HEAD/bundled/skills/generating-test-reports", "install": ["npx skills add foryourhealth111-pixel/Vibe-Skills --skill generating-test-reports"], "stars": 3816, "pushed": "2026-11-09T07:33:42Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:foryourhealth111-pixel/Vibe-Skills/bundled/skills/hypothesis-testing", "name": "hypothesis-testing", "kind": "skill", "official": false, "desc": "Property-based testing with Hypothesis for discovering edge cases and validating invariants. Use when implementing comprehensive test coverage, testing complex logic with many inputs, or validating mathematical properties and invariants across input domains. Triggered by: hypothesis, property-based testing, @given, strategies, generative testing.", "repo": "https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/HEAD/bundled/skills/hypothesis-testing", "install": ["npx skills add foryourhealth111-pixel/Vibe-Skills --skill hypothesis-testing"], "stars": 3816, "pushed": "2026-11-09T07:33:42Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:foryourhealth111-pixel/Vibe-Skills/bundled/skills/performance-testing", "name": "performance-testing", "kind": "skill", "official": false, "desc": "Benchmark indicator performance with BenchmarkDotNet. Use for Series/Buffer/Stream benchmarks, regression detection, and optimization patterns. Target 1.5x Series for StreamHub, 1.2x for BufferList.", "repo": "https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/HEAD/bundled/skills/performance-testing", "install": ["npx skills add foryourhealth111-pixel/Vibe-Skills --skill performance-testing"], "stars": 3816, "pushed": "2026-11-09T07:33:42Z", "license": "Apache-2.0", "plat": "benchmarkdotnet", "live": "Not checked (runs locally)"}, {"id": "skill:foryourhealth111-pixel/Vibe-Skills/bundled/skills/property-based-testing", "name": "property-based-testing", "kind": "skill", "official": false, "desc": "Property-based testing with fast-check (TypeScript/JavaScript) and Hypothesis (Python). Generate test cases automatically, find edge cases, and test mathematical properties. Use when user mentions property-based testing, fast-check, Hypothesis, generating test data, QuickCheck-style testing, or finding edge cases automatically.", "repo": "https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/HEAD/bundled/skills/property-based-testing", "install": ["npx skills add foryourhealth111-pixel/Vibe-Skills --skill property-based-testing"], "stars": 3816, "pushed": "2026-11-09T07:33:42Z", "license": "Apache-2.0", "plat": "property-based testing", "live": "Not checked (runs locally)"}, {"id": "skill:foryourhealth111-pixel/Vibe-Skills/bundled/skills/receiving-code-review", "name": "receiving-code-review", "kind": "skill", "official": false, "desc": "Review-feedback handling route for CodeRabbit, GitHub, PR, or human reviewer comments. Use before implementing suggestions to verify each finding. Do not use for a fresh code review, security audit, TDD, or final completion evidence.", "repo": "https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/HEAD/bundled/skills/receiving-code-review", "install": ["npx skills add foryourhealth111-pixel/Vibe-Skills --skill receiving-code-review"], "stars": 3816, "pushed": "2026-11-09T07:33:42Z", "license": "Apache-2.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:foryourhealth111-pixel/Vibe-Skills/bundled/skills/requesting-code-review", "name": "requesting-code-review", "kind": "skill", "official": false, "desc": "Prepare and request a code review after implementation or before merge by assembling scope, requirements, git range, and reviewer instructions.", "repo": "https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/HEAD/bundled/skills/requesting-code-review", "install": ["npx skills add foryourhealth111-pixel/Vibe-Skills --skill requesting-code-review"], "stars": 3816, "pushed": "2026-11-09T07:33:42Z", "license": "Apache-2.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:foryourhealth111-pixel/Vibe-Skills/bundled/skills/systematic-debugging", "name": "systematic-debugging", "kind": "skill", "official": false, "desc": "Root-cause route for actual bugs, failing tests, build errors, crashes, stack traces, and unexpected behavior. Do not use for test-first/TDD feature work, test-report packaging, review-feedback handling, or final completion evidence.", "repo": "https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/HEAD/bundled/skills/systematic-debugging", "install": ["npx skills add foryourhealth111-pixel/Vibe-Skills --skill systematic-debugging"], "stars": 3816, "pushed": "2026-11-09T07:33:42Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:foryourhealth111-pixel/Vibe-Skills/bundled/skills/verification-quality-assurance", "name": "Verification & Quality Assurance", "kind": "skill", "official": false, "desc": "Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.", "repo": "https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/HEAD/bundled/skills/verification-quality-assurance", "install": ["npx skills add foryourhealth111-pixel/Vibe-Skills --skill Verification & Quality Assurance"], "stars": 3816, "pushed": "2026-11-09T07:33:42Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:gotalab/cc-sdd/tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-review", "name": "kiro-review", "kind": "skill", "official": false, "desc": "Review a task implementation against approved specs, task boundaries, and verification evidence. Use after an implementer finishes a task, after remediation, or before accepting a task as complete.", "repo": "https://github.com/gotalab/cc-sdd/tree/HEAD/tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-review", "install": ["npx skills add gotalab/cc-sdd --skill kiro-review"], "stars": 3764, "pushed": "2026-10-22T03:43:11Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:scenario-labs/skills/skills/game-engines/unreal/scenario-unreal-performance", "name": "scenario-unreal-performance", "kind": "skill", "official": false, "desc": "Use when an Unreal Engine 5.8 project misses its frame rate or stutters: \"optimize to 60 fps\", \"we run at 38 fps\", CPU or GPU bound, game or render thread too long, hitches, traversal or shader stutter (PSO), GC spikes, camera-cut spikes, Lumen, Nanite, VSM, ray tracing, foliage, crowds or Niagara too expensive, async compute, stat unit, ProfileGPU, Unreal Insights, TraceQuery, snapshothitches, scalability and device profiles, dynamic resolution and TSR, streaming budgets, or proving a fix with ", "repo": "https://github.com/scenario-labs/skills/tree/HEAD/skills/game-engines/unreal/scenario-unreal-performance", "install": ["npx skills add scenario-labs/skills --skill scenario-unreal-performance"], "stars": 3764, "pushed": "2026-11-13T14:09:04Z", "license": "MIT", "plat": "unreal engine", "live": "Not checked (runs locally)"}, {"id": "skill:scenario-labs/skills/.agents/skills/skills-validate", "name": "skills-validate", "kind": "skill", "official": false, "desc": "Use when explicitly asked to run a live or plan-only application test for a published Scenario skill.", "repo": "https://github.com/scenario-labs/skills/tree/HEAD/.agents/skills/skills-validate", "install": ["npx skills add scenario-labs/skills --skill skills-validate"], "stars": 3764, "pushed": "2026-11-13T14:09:04Z", "license": "MIT", "plat": "scenario", "live": "Not checked (runs locally)"}, {"id": "skill:browserbase/skills/skills/ui-test", "name": "ui-test", "kind": "skill", "official": false, "desc": "AI-powered adversarial UI testing via the browse CLI. Analyzes git diffs to test only what changed, or explores the full app to find bugs. Tests functional correctness, accessibility, responsive layout, and UX heuristics. Use when the user asks to test UI changes, QA a pull request, audit accessibility, or run exploratory testing. Supports local browser (localhost) and remote Browserbase (deployed sites).", "repo": "https://github.com/browserbase/skills/tree/HEAD/skills/ui-test", "install": ["npx skills add browserbase/skills --skill ui-test"], "stars": 3757, "pushed": "2026-10-27T15:09:18Z", "license": null, "plat": "browserbase", "live": "Not checked (runs locally)"}, {"id": "skill:davepoon/buildwithclaude/plugins/ciagent/skills/check", "name": "check", "kind": "skill", "official": false, "desc": "Run CIAgent regression checks after changing an AI agent's code, prompts, or knowledge base in a repo that has agentci_spec.yaml, and interpret the results. Use after editing agent logic, before committing agent changes, or when the user asks whether the agent still works.", "repo": "https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/ciagent/skills/check", "install": ["npx skills add davepoon/buildwithclaude --skill check"], "stars": 3743, "pushed": "2026-11-13T07:12:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:davepoon/buildwithclaude/plugins/agent-triforce/skills/code-health", "name": "code-health", "kind": "skill", "official": false, "desc": "Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Delegates to the Centinela (QA) agent.", "repo": "https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/agent-triforce/skills/code-health", "install": ["npx skills add davepoon/buildwithclaude --skill code-health"], "stars": 3743, "pushed": "2026-11-13T07:12:33Z", "license": "MIT", "plat": "centinela", "live": "Not checked (runs locally)"}, {"id": "skill:davepoon/buildwithclaude/plugins/gsd/skills/add-tests", "name": "gsd:add-tests", "kind": "skill", "official": false, "desc": "Generate tests for a completed phase based on UAT criteria and implementation", "repo": "https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/gsd/skills/add-tests", "install": ["npx skills add davepoon/buildwithclaude --skill gsd:add-tests"], "stars": 3743, "pushed": "2026-11-13T07:12:33Z", "license": "MIT", "plat": "uat", "live": "Not checked (runs locally)"}, {"id": "skill:davepoon/buildwithclaude/plugins/ciagent/skills/onboard", "name": "onboard", "kind": "skill", "official": false, "desc": "Set up CIAgent regression testing for the AI agent in this repo — write a runner, record golden baselines, generate a test spec, and verify it. Use when the user asks to add tests, evals, or regression testing for their AI agent, or to set up CIAgent.", "repo": "https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/ciagent/skills/onboard", "install": ["npx skills add davepoon/buildwithclaude --skill onboard"], "stars": 3743, "pushed": "2026-11-13T07:12:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:davepoon/buildwithclaude/plugins/claude-ops/skills/ops-triage", "name": "ops-triage", "kind": "skill", "official": false, "desc": "Cross-platform issue triage. Pulls from Sentry (MCP), Linear (MCP), GitHub Issues (gh). Cross-references against code to find already-fixed issues. Auto-resolves fixed ones. Dispatches agents for active issues.", "repo": "https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/claude-ops/skills/ops-triage", "install": ["npx skills add davepoon/buildwithclaude --skill ops-triage"], "stars": 3743, "pushed": "2026-11-13T07:12:33Z", "license": "MIT", "plat": "sentry, linear, github issues", "live": "Not checked (runs locally)"}, {"id": "skill:davepoon/buildwithclaude/plugins/all-skills/skills/red-handed-audit", "name": "red-handed-audit", "kind": "skill", "official": false, "desc": "Check whether the tests the agent said passed actually ran. Reads the Claude Code session transcript and git state locally, then reports each gap with a timestamp and the quoted line. No model calls, nothing leaves the machine.", "repo": "https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/all-skills/skills/red-handed-audit", "install": ["npx skills add davepoon/buildwithclaude --skill red-handed-audit"], "stars": 3743, "pushed": "2026-11-13T07:12:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:davepoon/buildwithclaude/plugins/agent-triforce/skills/release-check", "name": "release-check", "kind": "skill", "official": false, "desc": "Pre-release verification checklist. Validates features, tests, docs, security, and quality gates before shipping. Delegates to the Centinela (QA) agent.", "repo": "https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/agent-triforce/skills/release-check", "install": ["npx skills add davepoon/buildwithclaude --skill release-check"], "stars": 3743, "pushed": "2026-11-13T07:12:33Z", "license": "MIT", "plat": "centinela", "live": "Not checked (runs locally)"}, {"id": "skill:davepoon/buildwithclaude/plugins/cc-best/skills/testing", "name": "testing", "kind": "skill", "official": false, "desc": "Testing strategies and methodologies including TDD, E2E testing, and multi-framework support", "repo": "https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/cc-best/skills/testing", "install": ["npx skills add davepoon/buildwithclaude --skill testing"], "stars": 3743, "pushed": "2026-11-13T07:12:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:davepoon/buildwithclaude/plugins/claude-ops/skills/uninstall", "name": "uninstall", "kind": "skill", "official": false, "desc": "Completely remove claude-ops plugin, all stored credentials, cached files, shell exports, and MCP registrations. Confirms each step before deletion.", "repo": "https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/claude-ops/skills/uninstall", "install": ["npx skills add davepoon/buildwithclaude --skill uninstall"], "stars": 3743, "pushed": "2026-11-13T07:12:33Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:wesammustafa/Claude-Code-Quest/solutions/a-6/team-marketplace/plugins/team-kit/skills/review-checklist", "name": "review-checklist", "kind": "skill", "official": false, "desc": "The team's checklist for reviewing a change to linkcheck. Use before you commit or open a pull request.", "repo": "https://github.com/wesammustafa/Claude-Code-Quest/tree/HEAD/solutions/a-6/team-marketplace/plugins/team-kit/skills/review-checklist", "install": ["npx skills add wesammustafa/Claude-Code-Quest --skill review-checklist"], "stars": 3699, "pushed": "2026-11-13T16:08:26Z", "license": "NOASSERTION", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:wesammustafa/Claude-Code-Quest/solutions/i-1/dot-claude/skills/tdd", "name": "tdd", "kind": "skill", "official": false, "desc": "Builds a requested feature test-first, one behavior at a time, and stops at a diff for review. Use when the user asks for a new function or feature, or says test-first or TDD.", "repo": "https://github.com/wesammustafa/Claude-Code-Quest/tree/HEAD/solutions/i-1/dot-claude/skills/tdd", "install": ["npx skills add wesammustafa/Claude-Code-Quest --skill tdd"], "stars": 3699, "pushed": "2026-11-13T16:08:26Z", "license": "NOASSERTION", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:wesammustafa/Claude-Code-Quest/solutions/a-capstone/dot-claude/skills/team-review", "name": "team-review", "kind": "skill", "official": false, "desc": "The team's review of a change to linkcheck, run the same way on a laptop and in CI. Use on a staged diff or a pull request.", "repo": "https://github.com/wesammustafa/Claude-Code-Quest/tree/HEAD/solutions/a-capstone/dot-claude/skills/team-review", "install": ["npx skills add wesammustafa/Claude-Code-Quest --skill team-review"], "stars": 3699, "pushed": "2026-11-13T16:08:26Z", "license": "NOASSERTION", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:vuejs-ai/skills/skills/vue-debug-guides", "name": "vue-debug-guides", "kind": "skill", "official": false, "desc": "Vue 3 debugging and error handling for runtime errors, warnings, async failures, and SSR/hydration issues. Use when diagnosing or fixing Vue issues.", "repo": "https://github.com/vuejs-ai/skills/tree/HEAD/skills/vue-debug-guides", "install": ["npx skills add vuejs-ai/skills --skill vue-debug-guides"], "stars": 3338, "pushed": "2026-10-23T14:53:15Z", "license": "MIT", "plat": "vue.js", "live": "Not checked (runs locally)"}, {"id": "skill:vuejs-ai/skills/skills/vue-testing-best-practices", "name": "vue-testing-best-practices", "kind": "skill", "official": false, "desc": "Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright for E2E testing.", "repo": "https://github.com/vuejs-ai/skills/tree/HEAD/skills/vue-testing-best-practices", "install": ["npx skills add vuejs-ai/skills --skill vue-testing-best-practices"], "stars": 3338, "pushed": "2026-10-23T14:53:15Z", "license": "MIT", "plat": "vue.js", "live": "Not checked (runs locally)"}, {"id": "skill:nexu-io/nexu/skills/localdev/nexu-e2e-test", "name": "nexu-e2e-test", "kind": "skill", "official": false, "desc": "Use when verifying OpenClaw gateway fixes end-to-end, testing skill loading after restart, or running integration tests against the local Nexu+OpenClaw stack. Triggers on \"e2e test\", \"verify fix\", \"test gateway\", \"test skills loading\".", "repo": "https://github.com/nexu-io/nexu/tree/HEAD/skills/localdev/nexu-e2e-test", "install": ["npx skills add nexu-io/nexu --skill nexu-e2e-test"], "stars": 3296, "pushed": "2026-04-26T13:40:30Z", "license": "MIT", "plat": "nexu", "live": "Not checked (runs locally)"}, {"id": "skill:lackeyjb/playwright-skill/skills/playwright-skill", "name": "playwright-skill", "kind": "skill", "official": false, "desc": "Complete browser automation with Playwright. Auto-detects dev servers, writes reusable test scripts, and supports screenshots, responsive checks, UX validation, login flows, link checks, and arbitrary browser automation. Use when the user wants to test a website, automate browser interactions, validate web functionality, or perform browser-based testing.", "repo": "https://github.com/lackeyjb/playwright-skill/tree/HEAD/skills/playwright-skill", "install": ["npx skills add lackeyjb/playwright-skill --skill playwright-skill"], "stars": 3293, "pushed": "2026-11-01T07:36:27Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:thananon/9arm-skills/skills/engineering/debug-mantra", "name": "debug-mantra", "kind": "skill", "official": false, "desc": "Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively whenever debugging starts — user reports a bug, says something is broken/throwing/failing, asks to debug/diagnose/investigate an issue, or pastes a stack trace or error log.", "repo": "https://github.com/thananon/9arm-skills/tree/HEAD/skills/engineering/debug-mantra", "install": ["npx skills add thananon/9arm-skills --skill debug-mantra"], "stars": 3267, "pushed": "2026-06-14T17:31:47Z", "license": null, "plat": "debug mantra", "live": "Not checked (runs locally)"}, {"id": "skill:thananon/9arm-skills/skills/engineering/post-mortem", "name": "post-mortem", "kind": "skill", "official": false, "desc": "Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through. Engineer-audience, code identifiers welcome. Use after a debug session lands a fix, before closing the ticket. Trigger on /post-mortem, when the user says \"write the post-mortem / postmortem / RCA / root cause analysis\", \"document this fix\", \"write up the root cause\", \"close out this bug with a writeup\", or hands you a fixed-and-validated bug and asks for the writeup.", "repo": "https://github.com/thananon/9arm-skills/tree/HEAD/skills/engineering/post-mortem", "install": ["npx skills add thananon/9arm-skills --skill post-mortem"], "stars": 3267, "pushed": "2026-06-14T17:31:47Z", "license": null, "plat": "post-mortem", "live": "Not checked (runs locally)"}, {"id": "skill:microsoft/skills/.github/plugins/azure-sdk-typescript/skills/azure-microsoft-playwright-testing-ts", "name": "azure-microsoft-playwright-testing-ts", "kind": "skill", "official": false, "desc": "Run Playwright tests at scale using Azure Playwright Workspaces (formerly Microsoft Playwright Testing). Use when scaling browser tests across cloud-hosted browsers, integrating with CI/CD pipelines, or publishing test results to the Azure portal.", "repo": "https://github.com/microsoft/skills/tree/HEAD/.github/plugins/azure-sdk-typescript/skills/azure-microsoft-playwright-testing-ts", "install": ["npx skills add microsoft/skills --skill azure-microsoft-playwright-testing-ts"], "stars": 3203, "pushed": "2026-11-13T22:48:25Z", "license": "MIT", "plat": "azure", "live": "Not checked (runs locally)"}, {"id": "skill:microsoft/skills/.github/plugins/azure-sdk-dotnet/skills/azure-resource-manager-playwright-dotnet", "name": "azure-resource-manager-playwright-dotnet", "kind": "skill", "official": false, "desc": "Azure Resource Manager SDK for Microsoft Playwright Testing in .NET. Use for MANAGEMENT PLANE operations: creating/managing Playwright Testing workspaces, checking name availability, and managing workspace quotas via Azure Resource Manager. NOT for running Playwright tests - use Azure.Developer.MicrosoftPlaywrightTesting.NUnit for that. Triggers: \"Playwright workspace\", \"create Playwright Testing workspace\", \"manage Playwright resources\", \"ARM Playwright\", \"PlaywrightWorkspaceResource\", \"provisi", "repo": "https://github.com/microsoft/skills/tree/HEAD/.github/plugins/azure-sdk-dotnet/skills/azure-resource-manager-playwright-dotnet", "install": ["npx skills add microsoft/skills --skill azure-resource-manager-playwright-dotnet"], "stars": 3203, "pushed": "2026-11-13T22:48:25Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:microsoft/skills/.github/plugins/azure-sdk-dotnet/skills/azure-servicebus-dotnet", "name": "azure-servicebus-dotnet", "kind": "skill", "official": false, "desc": "Azure Service Bus SDK for .NET. Enterprise messaging with queues, topics, subscriptions, and sessions. Use for reliable message delivery, pub/sub patterns, dead letter handling, and background processing. Triggers: \"Service Bus\", \"ServiceBusClient\", \"ServiceBusSender\", \"ServiceBusReceiver\", \"ServiceBusProcessor\", \"message queue\", \"pub/sub .NET\", \"dead letter queue\".", "repo": "https://github.com/microsoft/skills/tree/HEAD/.github/plugins/azure-sdk-dotnet/skills/azure-servicebus-dotnet", "install": ["npx skills add microsoft/skills --skill azure-servicebus-dotnet"], "stars": 3203, "pushed": "2026-11-13T22:48:25Z", "license": "MIT", "plat": "azure service bus", "live": "Not checked (runs locally)"}, {"id": "skill:runkids/skillshare/.skillshare/skills/skillshare-cli-e2e-test", "name": "skillshare-cli-e2e-test", "kind": "skill", "official": false, "desc": "Run isolated E2E tests in devcontainer from ai_docs/tests runbooks. Use this skill whenever the user asks to: run an E2E test, execute a test runbook, validate a feature end-to-end, create a new runbook, or test CLI behavior in isolation. If you need to run a multi-step CLI validation sequence (init → install → sync → verify), this is the skill — it handles ssenv isolation, flag verification, and structured reporting. Prefer this over ad-hoc docker exec sequences for any test that follows a runb", "repo": "https://github.com/runkids/skillshare/tree/HEAD/.skillshare/skills/skillshare-cli-e2e-test", "install": ["npx skills add runkids/skillshare --skill skillshare-cli-e2e-test"], "stars": 3112, "pushed": "2026-11-14T05:43:45Z", "license": "MIT", "plat": "skillshare", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/pro-workflow/skills/tdd", "name": "tdd", "kind": "skill", "official": false, "desc": "Drive a change through a red-green-refactor loop - failing test first, minimal code to pass, then clean up. Use when implementing a feature or fixing a bug where correctness matters and a test can pin the behavior. Says \"TDD\", \"test first\", \"red green refactor\", \"write the test first\".", "repo": "https://github.com/rohitg00/pro-workflow/tree/HEAD/skills/tdd", "install": ["npx skills add rohitg00/pro-workflow --skill tdd"], "stars": 2955, "pushed": "2026-09-29T10:12:13Z", "license": null, "plat": "testing", "live": "Not checked (runs locally)"}, {"id": "skill:jeremylongshore/tons-of-skills-marketplace/plugins/ai-agency/hyperflow/skills/audit", "name": "audit", "kind": "skill", "official": false, "desc": "Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a multi-level (L1-L5) review with a standalone Reviewer; on NEEDS_FIX, offers to apply findings via /hyperflow:plan. Trigger with /hyperflow:audit, \"review this change\", \"review my PR\", \"audit the diff\", \"code review\".", "repo": "https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/HEAD/plugins/ai-agency/hyperflow/skills/audit", "install": ["npx skills add jeremylongshore/tons-of-skills-marketplace --skill audit"], "stars": 2919, "pushed": "2026-11-14T05:32:50Z", "license": "MIT", "plat": "code", "live": "Not checked (runs locally)"}, {"id": "skill:jeremylongshore/tons-of-skills-marketplace/plugins/ai-agency/tonone/skills/proof", "name": "proof", "kind": "skill", "official": false, "desc": "QA and testing engineer — test strategy, E2E suites, API tests, flaky test triage, coverage.", "repo": "https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/HEAD/plugins/ai-agency/tonone/skills/proof", "install": ["npx skills add jeremylongshore/tons-of-skills-marketplace --skill proof"], "stars": 2919, "pushed": "2026-11-14T05:32:50Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:jeremylongshore/tons-of-skills-marketplace/plugins/ai-agency/tonone/skills/proof-api", "name": "proof-api", "kind": "skill", "official": false, "desc": "Build API test suites — endpoint testing, contract testing, load testing for REST/GraphQL/gRPC APIs. Use when asked to \"test this API\", \"API tests\", \"endpoint testing\", \"contract tests\", or \"load test\".", "repo": "https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/HEAD/plugins/ai-agency/tonone/skills/proof-api", "install": ["npx skills add jeremylongshore/tons-of-skills-marketplace --skill proof-api"], "stars": 2919, "pushed": "2026-11-14T05:32:50Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:jeremylongshore/tons-of-skills-marketplace/plugins/ai-agency/tonone/skills/proof-audit", "name": "proof-audit", "kind": "skill", "official": false, "desc": "Audit test suite health — find flaky tests, slow tests, coverage gaps, and testing anti-patterns. Use when asked to \"audit tests\", \"fix flaky tests\", \"why are tests slow\", \"test health\", or \"improve test suite\".", "repo": "https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/HEAD/plugins/ai-agency/tonone/skills/proof-audit", "install": ["npx skills add jeremylongshore/tons-of-skills-marketplace --skill proof-audit"], "stars": 2919, "pushed": "2026-11-14T05:32:50Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:jeremylongshore/tons-of-skills-marketplace/plugins/ai-agency/tonone/skills/proof-e2e", "name": "proof-e2e", "kind": "skill", "official": false, "desc": "Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to \"write E2E tests\", \"end-to-end testing\", \"browser tests\", \"UI tests\", or \"Playwright tests\".", "repo": "https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/HEAD/plugins/ai-agency/tonone/skills/proof-e2e", "install": ["npx skills add jeremylongshore/tons-of-skills-marketplace --skill proof-e2e"], "stars": 2919, "pushed": "2026-11-14T05:32:50Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:jeremylongshore/tons-of-skills-marketplace/plugins/ai-agency/tonone/skills/proof-recon", "name": "proof-recon", "kind": "skill", "official": false, "desc": "Testing reconnaissance — inventory all tests, frameworks, coverage, CI integration, and assess testing maturity for project takeover. Use when asked to \"understand the tests\", \"testing assessment\", \"what's tested\", or \"test inventory\".", "repo": "https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/HEAD/plugins/ai-agency/tonone/skills/proof-recon", "install": ["npx skills add jeremylongshore/tons-of-skills-marketplace --skill proof-recon"], "stars": 2919, "pushed": "2026-11-14T05:32:50Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:jeremylongshore/tons-of-skills-marketplace/plugins/ai-agency/tonone/skills/proof-strategy", "name": "proof-strategy", "kind": "skill", "official": false, "desc": "Produce a test strategy for a project or feature — risk map, test type decisions, coverage targets, CI config. Use when asked to \"create test strategy\", \"what should we test\", \"testing plan\", or \"improve test coverage\".", "repo": "https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/HEAD/plugins/ai-agency/tonone/skills/proof-strategy", "install": ["npx skills add jeremylongshore/tons-of-skills-marketplace --skill proof-strategy"], "stars": 2919, "pushed": "2026-11-14T05:32:50Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/awesome-claude-code-toolkit/skills/tdd-mastery", "name": "tdd-mastery", "kind": "skill", "official": false, "desc": "Test-driven development workflow with Red-Green-Refactor cycle across languages", "repo": "https://github.com/rohitg00/awesome-claude-code-toolkit/tree/HEAD/skills/tdd-mastery", "install": ["npx skills add rohitg00/awesome-claude-code-toolkit --skill tdd-mastery"], "stars": 2838, "pushed": "2026-05-12T07:18:34Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/awesome-claude-code-toolkit/skills/testing-strategies", "name": "testing-strategies", "kind": "skill", "official": false, "desc": "Testing strategies including contract testing, snapshot testing, mutation testing, property-based testing, and test organization", "repo": "https://github.com/rohitg00/awesome-claude-code-toolkit/tree/HEAD/skills/testing-strategies", "install": ["npx skills add rohitg00/awesome-claude-code-toolkit --skill testing-strategies"], "stars": 2838, "pushed": "2026-05-12T07:18:34Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:majidmanzarpour/threejs-game-skills/skills/threejs-debug-profiler", "name": "threejs-debug-profiler", "kind": "skill", "official": false, "desc": "Debug and profile Three.js browser games: blank canvases, render and runtime bugs, asset and audio loading, animation, resize, mobile input, plus performance profiling of draw calls, triangles, textures, memory, shader and post-processing cost, and bundle size.", "repo": "https://github.com/majidmanzarpour/threejs-game-skills/tree/HEAD/skills/threejs-debug-profiler", "install": ["npx skills add majidmanzarpour/threejs-game-skills --skill threejs-debug-profiler"], "stars": 2812, "pushed": "2026-09-28T03:23:18Z", "license": "MIT", "plat": "three.js", "live": "Not checked (runs locally)"}, {"id": "skill:majidmanzarpour/threejs-game-skills/skills/threejs-qa-release", "name": "threejs-qa-release", "kind": "skill", "official": false, "desc": "Verify and release Three.js browser games: playtest QA, automated bot playtests, mobile and responsive checks, production builds, static-hosting base paths, debug gating, bundle review, screenshots, visual regression baselines, canvas-pixel inspection with measured metrics, and release risk reports.", "repo": "https://github.com/majidmanzarpour/threejs-game-skills/tree/HEAD/skills/threejs-qa-release", "install": ["npx skills add majidmanzarpour/threejs-game-skills --skill threejs-qa-release"], "stars": 2812, "pushed": "2026-09-28T03:23:18Z", "license": "MIT", "plat": "three.js", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:mattzcarey/shippie", "name": "shippie", "kind": "mcp", "official": null, "desc": "extendable code review and QA agent 🚢", "repo": "https://github.com/mattzcarey/shippie", "install": [], "stars": 2525, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:maxrave-dev/kotlin-footguns/skills/engineering-method-footguns", "name": "engineering-method-footguns", "kind": "skill", "official": false, "desc": "Debugging-method traps: run the discriminating experiment first, read build logs bottom-up, treat an empty actual as unwritten, audit shared handles before removing a feature, read commit history critically. Use when a fix is not converging.", "repo": "https://github.com/maxrave-dev/kotlin-footguns/tree/HEAD/skills/engineering-method-footguns", "install": ["npx skills add maxrave-dev/kotlin-footguns --skill engineering-method-footguns"], "stars": 2306, "pushed": "2026-10-29T04:27:53Z", "license": "GPL-3.0", "plat": "engineering", "live": "Not checked (runs locally)"}, {"id": "skill:mrgoonie/claudekit-skills/.claude/skills/code-review", "name": "code-review", "kind": "skill", "official": false, "desc": "Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing f", "repo": "https://github.com/mrgoonie/claudekit-skills/tree/HEAD/.claude/skills/code-review", "install": ["npx skills add mrgoonie/claudekit-skills --skill code-review"], "stars": 2244, "pushed": "2026-04-03T06:19:25Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:mrgoonie/claudekit-skills/.claude/skills/debugging", "name": "debugging", "kind": "skill", "official": false, "desc": "Systematic debugging frameworks for finding and fixing bugs - includes root cause analysis, defense-in-depth validation, and verification protocols", "repo": "https://github.com/mrgoonie/claudekit-skills/tree/HEAD/.claude/skills/debugging", "install": ["npx skills add mrgoonie/claudekit-skills --skill debugging"], "stars": 2244, "pushed": "2026-04-03T06:19:25Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:mrgoonie/claudekit-skills/.claude/skills/debugging/defense-in-depth", "name": "Defense-in-Depth Validation", "kind": "skill", "official": false, "desc": "Validate at every layer data passes through to make bugs impossible", "repo": "https://github.com/mrgoonie/claudekit-skills/tree/HEAD/.claude/skills/debugging/defense-in-depth", "install": ["npx skills add mrgoonie/claudekit-skills --skill Defense-in-Depth Validation"], "stars": 2244, "pushed": "2026-04-03T06:19:25Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:mrgoonie/claudekit-skills/.claude/skills/debugging/root-cause-tracing", "name": "Root Cause Tracing", "kind": "skill", "official": false, "desc": "Systematically trace bugs backward through call stack to find original trigger", "repo": "https://github.com/mrgoonie/claudekit-skills/tree/HEAD/.claude/skills/debugging/root-cause-tracing", "install": ["npx skills add mrgoonie/claudekit-skills --skill Root Cause Tracing"], "stars": 2244, "pushed": "2026-04-03T06:19:25Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:mrgoonie/claudekit-skills/.claude/skills/debugging/systematic-debugging", "name": "Systematic Debugging", "kind": "skill", "official": false, "desc": "Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.", "repo": "https://github.com/mrgoonie/claudekit-skills/tree/HEAD/.claude/skills/debugging/systematic-debugging", "install": ["npx skills add mrgoonie/claudekit-skills --skill Systematic Debugging"], "stars": 2244, "pushed": "2026-04-03T06:19:25Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:mrgoonie/claudekit-skills/.claude/skills/web-testing", "name": "web-testing", "kind": "skill", "official": false, "desc": "Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.", "repo": "https://github.com/mrgoonie/claudekit-skills/tree/HEAD/.claude/skills/web-testing", "install": ["npx skills add mrgoonie/claudekit-skills --skill web-testing"], "stars": 2244, "pushed": "2026-04-03T06:19:25Z", "license": null, "plat": "playwright, vitest", "live": "Not checked (runs locally)"}, {"id": "skill:maxritter/qualitylayer/qualitylayer/src/skills/ql-quality", "name": "ql-quality", "kind": "skill", "official": false, "desc": "Review code health (complexity, duplication, maintainability) and run security scans (secrets, vulnerable or malicious dependencies, unsafe GitHub workflows, risky code) with QualityLayer's local tools; inspect findings, diagnose missing checks or configure automatic feedback. This does not start a planning/build workflow.", "repo": "https://github.com/maxritter/qualitylayer/tree/HEAD/qualitylayer/src/skills/ql-quality", "install": ["npx skills add maxritter/qualitylayer --skill ql-quality"], "stars": 2147, "pushed": "2026-11-13T12:33:41Z", "license": "NOASSERTION", "plat": "qualitylayer", "live": "Not checked (runs locally)"}, {"id": "skill:Leanmcp/gateway-skills/skills/analyze-exports", "name": "analyze-exports", "kind": "skill", "official": false, "desc": "Analyze tau2-bench task export files to identify exactly where and why tasks failed. Map failures to specific conversation rounds, show root causes, check whether relevant documentation was available, and cite sources. Use this skill whenever you need to debug a tau2-bench evaluation, understand why an agent made wrong decisions, identify missing knowledge, or review task performance—especially when context length, eligibility criteria, or policy compliance might be at fault.", "repo": "https://github.com/Leanmcp/gateway-skills/tree/HEAD/skills/analyze-exports", "install": ["npx skills add Leanmcp/gateway-skills --skill analyze-exports"], "stars": 2125, "pushed": "2026-10-07T16:04:10Z", "license": "MIT", "plat": "tau2-bench", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/api-testing-observability-api-mock", "name": "api-testing-observability-api-mock", "kind": "skill", "official": false, "desc": "Design realistic API mock services that simulate real API behavior for development, testing, and demos, enabling parallel development. Use when a team needs mocks for an API that is unavailable, unstable, or still being built.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/api-testing-observability-api-mock", "install": ["npx skills add rmyndharis/antigravity-skills --skill api-testing-observability-api-mock"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/debugger", "name": "debugger", "kind": "skill", "official": false, "desc": "Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/debugger", "install": ["npx skills add rmyndharis/antigravity-skills --skill debugger"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/debugging-toolkit-smart-debug", "name": "debugging-toolkit-smart-debug", "kind": "skill", "official": false, "desc": "Diagnose software failures using observability data, ranked hypotheses, and targeted instrumentation. Use when the cause is unclear or an issue requires systematic investigation.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/debugging-toolkit-smart-debug", "install": ["npx skills add rmyndharis/antigravity-skills --skill debugging-toolkit-smart-debug"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/performance-testing-review-ai-review", "name": "performance-testing-review-ai-review", "kind": "skill", "official": false, "desc": "Combine static analysis with model-assisted code review to assess security, performance, correctness, and architecture. Use when designing review automation or reviewing complex changes.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/performance-testing-review-ai-review", "install": ["npx skills add rmyndharis/antigravity-skills --skill performance-testing-review-ai-review"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/performance-testing-review-multi-agent-review", "name": "performance-testing-review-multi-agent-review", "kind": "skill", "official": false, "desc": "Coordinate specialized code, security, architecture, and performance reviewers and consolidate their results. Use when a codebase needs parallel review across multiple disciplines.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/performance-testing-review-multi-agent-review", "install": ["npx skills add rmyndharis/antigravity-skills --skill performance-testing-review-multi-agent-review"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/tdd-orchestrator", "name": "tdd-orchestrator", "kind": "skill", "official": false, "desc": "Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use for TDD implementation and governance.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/tdd-orchestrator", "install": ["npx skills add rmyndharis/antigravity-skills --skill tdd-orchestrator"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/tdd-workflows-tdd-cycle", "name": "tdd-workflows-tdd-cycle", "kind": "skill", "official": false, "desc": "Coordinate the test-driven development cycle from requirements and failing tests through implementation, refactoring, and validation. Use when building a feature with a structured TDD workflow.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/tdd-workflows-tdd-cycle", "install": ["npx skills add rmyndharis/antigravity-skills --skill tdd-workflows-tdd-cycle"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/tdd-workflows-tdd-green", "name": "tdd-workflows-tdd-green", "kind": "skill", "official": false, "desc": "Implement the minimal code needed to make failing tests pass in the TDD green phase.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/tdd-workflows-tdd-green", "install": ["npx skills add rmyndharis/antigravity-skills --skill tdd-workflows-tdd-green"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/tdd-workflows-tdd-red", "name": "tdd-workflows-tdd-red", "kind": "skill", "official": false, "desc": "Generate failing tests for the TDD red phase to define expected behavior and edge cases.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/tdd-workflows-tdd-red", "install": ["npx skills add rmyndharis/antigravity-skills --skill tdd-workflows-tdd-red"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/tdd-workflows-tdd-refactor", "name": "tdd-workflows-tdd-refactor", "kind": "skill", "official": false, "desc": "Refactor code while preserving passing tests and behavior. Use during the TDD refactor phase to remove duplication, improve design, and verify each structural change.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/tdd-workflows-tdd-refactor", "install": ["npx skills add rmyndharis/antigravity-skills --skill tdd-workflows-tdd-refactor"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/test-automator", "name": "test-automator", "kind": "skill", "official": false, "desc": "Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use for testing automation or quality assurance.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/test-automator", "install": ["npx skills add rmyndharis/antigravity-skills --skill test-automator"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/ui-visual-validator", "name": "ui-visual-validator", "kind": "skill", "official": false, "desc": "Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use when verifying that UI modifications achieved their intended goals through comprehensive visual analysis.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/ui-visual-validator", "install": ["npx skills add rmyndharis/antigravity-skills --skill ui-visual-validator"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rmyndharis/antigravity-skills/skills/unit-testing-test-generate", "name": "unit-testing-test-generate", "kind": "skill", "official": false, "desc": "Generate comprehensive, maintainable unit tests across languages with strong coverage and edge case focus.", "repo": "https://github.com/rmyndharis/antigravity-skills/tree/HEAD/skills/unit-testing-test-generate", "install": ["npx skills add rmyndharis/antigravity-skills --skill unit-testing-test-generate"], "stars": 2009, "pushed": "2026-11-07T15:24:20Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:rs.hotpath/hotpath-cloud", "name": "hotpath-cloud", "kind": "mcp", "official": null, "desc": "Read-only access to Rust profiling reports from CI: benchmark history, diffs and policies", "repo": "https://github.com/hotpath-rs/hotpath", "install": ["https://hotpath.rs/api/v1/mcp"], "stars": 1925, "pushed": "2026-11-12T23:56:48Z", "license": "MIT", "plat": "rust", "live": "Live · 977 ms · 8 tools · `get_diff` asked for an API key (checked 2026-11-13)"}, {"id": "skill:qufei1993/skills-hub/skills/dsh-ci-test-reliability", "name": "dsh-ci-test-reliability", "kind": "skill", "official": false, "desc": "设计或审查测试覆盖、选择单元/集成/真实入口/端到端测试及 mock 边界时使用；也用于诊断偶发失败、异步、并行及持有资源的测试。适用于测试计划、回归覆盖缺口和不可靠的 CI 证据。", "repo": "https://github.com/qufei1993/skills-hub/tree/HEAD/skills/dsh-ci-test-reliability", "install": ["npx skills add qufei1993/skills-hub --skill dsh-ci-test-reliability"], "stars": 1872, "pushed": "2026-11-13T20:01:15Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:qufei1993/skills-hub/skills/dsh-pre-push-checks", "name": "dsh-pre-push-checks", "kind": "skill", "official": false, "desc": "在交付或推送前验证改动时使用，核实项目必需检查、当前构建产物和真实用户行为，区分通过、失败、未运行与环境阻塞。", "repo": "https://github.com/qufei1993/skills-hub/tree/HEAD/skills/dsh-pre-push-checks", "install": ["npx skills add qufei1993/skills-hub --skill dsh-pre-push-checks"], "stars": 1872, "pushed": "2026-11-13T20:01:15Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:qufei1993/skills-hub/skills/dsh-speed-up-perf", "name": "dsh-speed-up-perf", "kind": "skill", "official": false, "desc": "调查性能问题或优化实际测量的用户路径时使用，建立优化前后对照，保留正确性、失败行为和真实运行证据。", "repo": "https://github.com/qufei1993/skills-hub/tree/HEAD/skills/dsh-speed-up-perf", "install": ["npx skills add qufei1993/skills-hub --skill dsh-speed-up-perf"], "stars": 1872, "pushed": "2026-11-13T20:01:15Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:daveebbelaar/bama/skills/ship/improve-loop", "name": "improve-loop", "kind": "skill", "official": false, "desc": "Autonomous loop that works through docs/STORIES.md one story at a time for a macOS app, building, snapshotting, comparing against reference screenshots, fixing, and committing, until a milestone is done. Use when the user says \"keep going\", \"work through the backlog\", \"make it match the reference\", or wants an unattended improvement loop.", "repo": "https://github.com/daveebbelaar/bama/tree/HEAD/skills/ship/improve-loop", "install": ["npx skills add daveebbelaar/bama --skill improve-loop"], "stars": 1811, "pushed": "2026-11-05T13:09:56Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:daveebbelaar/bama/skills/code/performance", "name": "performance", "kind": "skill", "official": false, "desc": "Make a macOS app fast by measuring hangs, stutter, CPU, memory, and energy, then moving work off the main thread and onto the GPU. Use when the app freezes, a shortcut feels slow, dragging stutters, the fan spins, memory grows, or the user asks to optimize or profile.", "repo": "https://github.com/daveebbelaar/bama/tree/HEAD/skills/code/performance", "install": ["npx skills add daveebbelaar/bama --skill performance"], "stars": 1811, "pushed": "2026-11-05T13:09:56Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:daveebbelaar/bama/skills/ship/test-mac-app", "name": "test-mac-app", "kind": "skill", "official": false, "desc": "Test a macOS app at three levels, from Swift Testing unit tests and an in-app self-test to a debug bridge that lets an agent drive the running app and read its state, plus computer use for real clicks. Use when adding logic, fixing a bug, before a release, or when the user asks for tests, end-to-end checks, or \"make sure it works\".", "repo": "https://github.com/daveebbelaar/bama/tree/HEAD/skills/ship/test-mac-app", "install": ["npx skills add daveebbelaar/bama --skill test-mac-app"], "stars": 1811, "pushed": "2026-11-05T13:09:56Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:callstackincubator/agent-skills/plugins/vendored/.agents/skills/dogfood", "name": "dogfood", "kind": "skill", "official": false, "desc": "Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", or \"test this app\" on mobile. Produces a structured report with reproducible evidence: screenshots, optional repro videos, and detailed steps for every issue.", "repo": "https://github.com/callstackincubator/agent-skills/tree/HEAD/plugins/vendored/.agents/skills/dogfood", "install": ["npx skills add callstackincubator/agent-skills --skill dogfood"], "stars": 1708, "pushed": "2026-10-08T19:06:40Z", "license": "MIT", "plat": "ios, android", "live": "Not checked (runs locally)"}, {"id": "skill:callstackincubator/agent-skills/plugins/vendored/.agents/skills/react-native-testing", "name": "react-native-testing", "kind": "skill", "official": false, "desc": "Write tests using React Native Testing Library (RNTL) v13 and v14 (`@testing-library/react-native`). Use when writing, reviewing, or fixing React Native component tests. Covers: render, screen, queries (getBy/getAllBy/queryBy/findBy), Jest matchers, userEvent, fireEvent, waitFor, and async patterns. Supports v13 (React 18, sync render) and v14 (React 19+, async render). Triggers on: test files for React Native components, RNTL imports, mentions of \"testing library\", \"write tests\", \"component tes", "repo": "https://github.com/callstackincubator/agent-skills/tree/HEAD/plugins/vendored/.agents/skills/react-native-testing", "install": ["npx skills add callstackincubator/agent-skills --skill react-native-testing"], "stars": 1708, "pushed": "2026-10-08T19:06:40Z", "license": "MIT", "plat": "react native", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.kubeshop/testkube-mcp", "name": "io.github.kubeshop/testkube-mcp", "kind": "mcp", "official": null, "desc": "MCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants", "repo": "https://github.com/kubeshop/testkube", "install": ["oci:docker.io/kubeshop/mcp-server:2.15.2", "https://api.testkube.io/organizations/{organization_id}/environments/{environment_id}/mcp"], "stars": 1679, "pushed": "2026-11-13T12:58:25Z", "license": "NOASSERTION", "plat": "testkube", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.svnscha/mcp-windbg", "name": "MCP Server for WinDbg Crash Analysis", "kind": "mcp", "official": null, "desc": "A Model Context Protocol server for Windows crash dump analysis using WinDbg/CDB", "repo": "https://github.com/svnscha/mcp-windbg", "install": ["pypi:mcp-windbg", "pypi:mcp-windbg"], "stars": 1669, "pushed": "2026-10-28T22:36:02Z", "license": "MIT", "plat": "windbg", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/skillkit/packages/core/src/methodology/packs/debugging/hypothesis-testing", "name": "hypothesis-testing", "kind": "skill", "official": false, "desc": "Applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes. Use when a user says their code isn't working, they're getting an error, something broke, they want to troubleshoot a bug, or they're trying to figure out what's causing an issue. Concrete actions include isolating failing components, forming and testing hypotheses, analyzing error messages, tracing executi", "repo": "https://github.com/rohitg00/skillkit/tree/HEAD/packages/core/src/methodology/packs/debugging/hypothesis-testing", "install": ["npx skills add rohitg00/skillkit --skill hypothesis-testing"], "stars": 1579, "pushed": "2026-06-02T09:43:09Z", "license": "Apache-2.0", "plat": "hypothesis-testing", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/skillkit/packages/core/src/methodology/packs/testing/red-green-refactor", "name": "red-green-refactor", "kind": "skill", "official": false, "desc": "Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like 'make the test pass', 'test coverage', or 'unit tests before implementation'.", "repo": "https://github.com/rohitg00/skillkit/tree/HEAD/packages/core/src/methodology/packs/testing/red-green-refactor", "install": ["npx skills add rohitg00/skillkit --skill red-green-refactor"], "stars": 1579, "pushed": "2026-06-02T09:43:09Z", "license": "Apache-2.0", "plat": "red-green-refactor", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/skillkit/packages/core/src/methodology/packs/debugging/root-cause-analysis", "name": "root-cause-analysis", "kind": "skill", "official": false, "desc": "Performs systematic root cause analysis to identify the true source of bugs, errors, and unexpected behavior through structured investigation phases — not just treating symptoms. Use when a user reports a bug, crash, error, or broken behavior and needs to debug, troubleshoot, or investigate why something is not working; especially for complex or intermittent issues across multiple components. Applies the Five Whys method, hypothesis-driven testing, stack trace analysis, git blame/log evidence ga", "repo": "https://github.com/rohitg00/skillkit/tree/HEAD/packages/core/src/methodology/packs/debugging/root-cause-analysis", "install": ["npx skills add rohitg00/skillkit --skill root-cause-analysis"], "stars": 1579, "pushed": "2026-06-02T09:43:09Z", "license": "Apache-2.0", "plat": "root-cause-analysis", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/skillkit/packages/core/src/methodology/packs/collaboration/structured-review", "name": "structured-code-review", "kind": "skill", "official": false, "desc": "Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. Use when the user asks for code review, PR feedback, pull request review, or wants their code checked for bugs, style issues, or vulnerabilities — triggered by phrases like \"review my code\", \"check this PR\", \"review my changes\", ", "repo": "https://github.com/rohitg00/skillkit/tree/HEAD/packages/core/src/methodology/packs/collaboration/structured-review", "install": ["npx skills add rohitg00/skillkit --skill structured-code-review"], "stars": 1579, "pushed": "2026-06-02T09:43:09Z", "license": "Apache-2.0", "plat": "structured-code-review", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/skillkit/packages/core/src/methodology/packs/testing/test-patterns", "name": "test-patterns", "kind": "skill", "official": false, "desc": "Applies proven testing patterns — Arrange-Act-Assert (AAA), Given-When-Then, Test Data Builders, Object Mother, parameterized tests, fixtures, spies, and test doubles — to help write maintainable, reliable, and readable test suites. Use when the user asks about writing unit tests, integration tests, or end-to-end tests; structuring test cases or test suites; applying TDD or BDD practices; working with mocks, stubs, spies, or fakes; improving test coverage or reducing flakiness; or needs guidance", "repo": "https://github.com/rohitg00/skillkit/tree/HEAD/packages/core/src/methodology/packs/testing/test-patterns", "install": ["npx skills add rohitg00/skillkit --skill test-patterns"], "stars": 1579, "pushed": "2026-06-02T09:43:09Z", "license": "Apache-2.0", "plat": "test-patterns", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/skillkit/packages/core/src/methodology/packs/testing/anti-patterns", "name": "testing-anti-patterns", "kind": "skill", "official": false, "desc": "Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or unreliable test failures, or when the user mentions flaky tests, test smells, brittle tests, test isolation issues, mock overuse, slow tests, or test maintenance problems.", "repo": "https://github.com/rohitg00/skillkit/tree/HEAD/packages/core/src/methodology/packs/testing/anti-patterns", "install": ["npx skills add rohitg00/skillkit --skill testing-anti-patterns"], "stars": 1579, "pushed": "2026-06-02T09:43:09Z", "license": "Apache-2.0", "plat": "testing-anti-patterns", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/skillkit/packages/core/src/methodology/packs/debugging/trace-and-isolate", "name": "trace-and-isolate", "kind": "skill", "official": false, "desc": "Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component, function, or line is faulty. Covers binary search debugging, git bisect for regressions, strategic logging with [TRACE] patterns, data and control flow tracing, component isolation, minim", "repo": "https://github.com/rohitg00/skillkit/tree/HEAD/packages/core/src/methodology/packs/debugging/trace-and-isolate", "install": ["npx skills add rohitg00/skillkit --skill trace-and-isolate"], "stars": 1579, "pushed": "2026-06-02T09:43:09Z", "license": "Apache-2.0", "plat": "trace-and-isolate", "live": "Not checked (runs locally)"}, {"id": "skill:rohitg00/skillkit/packages/core/src/methodology/packs/planning/verification-gates", "name": "verification-gates", "kind": "skill", "official": false, "desc": "Creates explicit validation checkpoints (verification gates) between project phases to catch errors early and ensure quality before proceeding. Use when the user asks about quality gates, milestone checks, phase transitions, approval steps, go/no-go decision points, or preventing cascading errors across a multi-step workflow. Produces acceptance criteria checklists, automated CI gate configurations, manual sign-off requirements, and conditional review rules for scenarios such as security changes", "repo": "https://github.com/rohitg00/skillkit/tree/HEAD/packages/core/src/methodology/packs/planning/verification-gates", "install": ["npx skills add rohitg00/skillkit --skill verification-gates"], "stars": 1579, "pushed": "2026-06-02T09:43:09Z", "license": "Apache-2.0", "plat": "verification-gates", "live": "Not checked (runs locally)"}, {"id": "skill:openclaw/crabbox/.agents/skills/autoreview", "name": "autoreview", "kind": "skill", "official": false, "desc": "Structured code review through the shared OpenClaw agent-skills installation.", "repo": "https://github.com/openclaw/crabbox/tree/HEAD/.agents/skills/autoreview", "install": ["npx skills add openclaw/crabbox --skill autoreview"], "stars": 1535, "pushed": "2026-11-14T05:49:52Z", "license": "MIT", "plat": "openclaw", "live": "Not checked (runs locally)"}, {"id": "skill:openclaw/crabbox/.agents/skills/crabbox", "name": "crabbox", "kind": "skill", "official": false, "desc": "Detect and use Crabbox for repository tests and validation on remote runners. Use when crabbox.yaml or .crabbox.yaml exists, the crabbox CLI is available, or work needs remote compute, a clean or reusable environment, target-platform coverage, or auditable execution evidence.", "repo": "https://github.com/openclaw/crabbox/tree/HEAD/.agents/skills/crabbox", "install": ["npx skills add openclaw/crabbox --skill crabbox"], "stars": 1535, "pushed": "2026-11-14T05:49:52Z", "license": "MIT", "plat": "crabbox", "live": "Not checked (runs locally)"}, {"id": "skill:openclaw/crabbox/.agents/skills/crabbox-quickstart", "name": "crabbox-quickstart", "kind": "skill", "official": false, "desc": "First contact with Crabbox: run your repository's tests inside a disposable Docker or Podman container on your own machine, no account and no cloud spend, then stop the box. Use when someone asks what Crabbox is or how to try it, wants a throwaway sandbox for a repo with no crabbox.yaml yet, or is about to run crabbox init here; hand off to the crabbox skill for config that already exists, leased remote machines, jobs, secrets, or artifacts.", "repo": "https://github.com/openclaw/crabbox/tree/HEAD/.agents/skills/crabbox-quickstart", "install": ["npx skills add openclaw/crabbox --skill crabbox-quickstart"], "stars": 1535, "pushed": "2026-11-14T05:49:52Z", "license": "MIT", "plat": "crabbox", "live": "Not checked (runs locally)"}, {"id": "skill:michaelshimeles/rstack/evidence-driven-testing", "name": "evidence-driven-testing", "kind": "skill", "official": false, "desc": "Records visual proof while testing UI behavior — the agent tests the app hands-on via computer use while a screen recording with structured test/assertion annotations captures the session — then posts the video and a results summary to the requested destination. Use when changed runtime behavior needs observable verification, including headless environments (scripted screenshots and probes) and non-UI changes (measured numbers, output pairs).", "repo": "https://github.com/michaelshimeles/rstack/tree/HEAD/evidence-driven-testing", "install": ["npx skills add michaelshimeles/rstack --skill evidence-driven-testing"], "stars": 1498, "pushed": "2026-11-05T15:04:32Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:amplifthq/openmeld/.agents/skills/debugging-ci-failures", "name": "debugging-ci-failures", "kind": "skill", "official": false, "desc": "Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions (\"is CI red?\", \"is master green today?\", \"what's broken right now?\"). Use when the user asks why CI is red, asks for the current CI or master status, or mentions a failing check, GitHub Actions run, Depot runner, workflow, job, shard, merge queue kick, flaky test, lint failure, typecheck failure, snapshot diff, migration check, generated types drift, or skills build failure. Start ", "repo": "https://github.com/amplifthq/openmeld/tree/HEAD/.agents/skills/debugging-ci-failures", "install": ["npx skills add amplifthq/openmeld --skill debugging-ci-failures"], "stars": 1424, "pushed": "2026-11-13T15:47:48Z", "license": "MIT", "plat": "github actions", "live": "Not checked (runs locally)"}, {"id": "skill:CloudAI-X/claude-workflow-v2/skills/designing-tests", "name": "designing-tests", "kind": "skill", "official": false, "desc": "Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.", "repo": "https://github.com/CloudAI-X/claude-workflow-v2/tree/HEAD/skills/designing-tests", "install": ["npx skills add CloudAI-X/claude-workflow-v2 --skill designing-tests"], "stars": 1424, "pushed": "2026-10-06T12:14:28Z", "license": "MIT", "plat": "testing", "live": "Not checked (runs locally)"}, {"id": "skill:amplifthq/openmeld/.agents/skills/fixing-flaky-tests", "name": "fixing-flaky-tests", "kind": "skill", "official": false, "desc": "Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but passes on rerun or locally, when `hogli ci:insights` or the debugging-ci-failures skill classifies a failure as a flaky test, when given a GitHub Actions URL for a flaky job, when asked to check Trunk Flaky Tests for a test, PR, or master, or when asked to deflake, stabilize, or fix a flaky Jest, pytest, or Playwright test. Core discipline:", "repo": "https://github.com/amplifthq/openmeld/tree/HEAD/.agents/skills/fixing-flaky-tests", "install": ["npx skills add amplifthq/openmeld --skill fixing-flaky-tests"], "stars": 1424, "pushed": "2026-11-13T15:47:48Z", "license": "MIT", "plat": "posthog monorepo", "live": "Not checked (runs locally)"}, {"id": "skill:CloudAI-X/claude-workflow-v2/skills/optimizing-performance", "name": "optimizing-performance", "kind": "skill", "official": false, "desc": "Analyzes and optimizes application performance across frontend, backend, and database layers. Use when diagnosing slowness, improving load times, optimizing queries, reducing bundle size, or when asked about performance issues.", "repo": "https://github.com/CloudAI-X/claude-workflow-v2/tree/HEAD/skills/optimizing-performance", "install": ["npx skills add CloudAI-X/claude-workflow-v2 --skill optimizing-performance"], "stars": 1424, "pushed": "2026-10-06T12:14:28Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:amplifthq/openmeld/.agents/skills/writing-tests", "name": "writing-tests", "kind": "skill", "official": false, "desc": "Gates whether a new test should exist and forces it to be efficient, protecting CI from low-value test bloat. Use before any change to what a pytest, Jest, or Playwright test asserts or sets up, down to one fixture or one assertion added to an existing block. Front-loads the value bar (every test must catch a realistic regression no existing test already catches; extend the nearest existing test before writing a new standalone one; test behavior through the public interface, not implementation d", "repo": "https://github.com/amplifthq/openmeld/tree/HEAD/.agents/skills/writing-tests", "install": ["npx skills add amplifthq/openmeld --skill writing-tests"], "stars": 1424, "pushed": "2026-11-13T15:47:48Z", "license": "MIT", "plat": "pytest, jest, playwright", "live": "Not checked (runs locally)"}, {"id": "skill:amElnagdy/guard-skills/skills/test-guard", "name": "test-guard", "kind": "skill", "official": false, "desc": "Review generated or changed test code against universal testing rules before it ships. Best used reactively after an agent writes, edits, generates, or refactors tests, before presenting, committing, or merging them. Use for pytest (test_*.py, *_test.py), PHPUnit/Pest (*Test.php), Jest/Vitest (*.test.ts, *.spec.js), Go (*_test.go), files under tests/, __tests__/, or spec/, and review requests like 'write tests for X', 'add tests', 'test this', 'review these tests', or PR diffs containing tests. ", "repo": "https://github.com/amElnagdy/guard-skills/tree/HEAD/skills/test-guard", "install": ["npx skills add amElnagdy/guard-skills --skill test-guard"], "stars": 1315, "pushed": "2026-07-04T15:26:29Z", "license": "MIT", "plat": "test code", "live": "Not checked (runs locally)"}, {"id": "skill:pashov/skills/fizz", "name": "fizz", "kind": "skill", "official": false, "desc": "Generate Echidna/Medusa-compatible Solidity fuzz suites from Foundry or Hardhat projects. Trigger on \"fizz\", \"generate fuzz suite\", \"build fuzz harness\", \"stateful fuzzing\", \"fuzzing harness\", \"property testing\", and \"invariant suite\".", "repo": "https://github.com/pashov/skills/tree/HEAD/fizz", "install": ["npx skills add pashov/skills --skill fizz"], "stars": 1311, "pushed": "2026-10-21T09:22:05Z", "license": "MIT", "plat": "solidity", "live": "Not checked (runs locally)"}, {"id": "skill:pashov/skills/solidity-auditor", "name": "solidity-auditor", "kind": "skill", "official": false, "desc": "Security audit of Solidity code while you develop. Trigger on \"audit\", \"check this contract\", \"review for security\", \"loop mode\", \"run the auditor in loop mode\", \"run 3 passes\". Modes - default (full repo) or a specific filename. Loop mode runs several passes in one scan, each pass told what the earlier ones found, and ends in one combined report; it remembers findings between scans in a ledger.", "repo": "https://github.com/pashov/skills/tree/HEAD/solidity-auditor", "install": ["npx skills add pashov/skills --skill solidity-auditor"], "stars": 1311, "pushed": "2026-10-21T09:22:05Z", "license": "MIT", "plat": "solidity", "live": "Not checked (runs locally)"}, {"id": "skill:AI-Builder-Club/skills/skills/e2e-setup", "name": "e2e-setup", "kind": "skill", "official": false, "desc": "Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable auth/session helper, video+trace evidence, and a compounding suite. Use when a repo has no e2e (or weak e2e) and you want system-level tests — \"set up e2e\", \"add end-to-end tests\", \"scaffold a test gate\".", "repo": "https://github.com/AI-Builder-Club/skills/tree/HEAD/skills/e2e-setup", "install": ["npx skills add AI-Builder-Club/skills --skill e2e-setup"], "stars": 1310, "pushed": "2026-09-15T21:40:31Z", "license": null, "plat": "e2e", "live": "Not checked (runs locally)"}, {"id": "skill:AI-Builder-Club/skills/skills/verifier-setup", "name": "verifier-setup", "kind": "skill", "official": false, "desc": "Set a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a one-command dev stack (`dev-local`) exists, asks whether verification runs locally or in a sandbox (crabbox), confirms/installs the driver (the `playwright-cli` skill for web by default). Outputs three artifacts: a committed `/verify` skill (per-task verification SOP — spawn a verifier sub-agent → drive the app → screenshot/video proof → open a PR with the proof embedded), the `/dev-loca", "repo": "https://github.com/AI-Builder-Club/skills/tree/HEAD/skills/verifier-setup", "install": ["npx skills add AI-Builder-Club/skills --skill verifier-setup"], "stars": 1310, "pushed": "2026-09-15T21:40:31Z", "license": null, "plat": "verifier", "live": "Not checked (runs locally)"}, {"id": "skill:AvdLee/Xcode-Build-Optimization-Agent-Skill/skills/xcode-build-benchmark", "name": "xcode-build-benchmark", "kind": "skill", "official": false, "desc": "Benchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped `.build-benchmark/` artifacts. Use when a developer wants a baseline, wants to compare before and after changes, asks to measure build performance, mentions build times, build duration, how long builds take, or wants to know if builds got faster or slower.", "repo": "https://github.com/AvdLee/Xcode-Build-Optimization-Agent-Skill/tree/HEAD/skills/xcode-build-benchmark", "install": ["npx skills add AvdLee/Xcode-Build-Optimization-Agent-Skill --skill xcode-build-benchmark"], "stars": 1273, "pushed": "2026-09-14T09:05:25Z", "license": "MIT", "plat": "xcode", "live": "Not checked (runs locally)"}, {"id": "skill:AvdLee/Xcode-Build-Optimization-Agent-Skill/skills/xcode-build-fixer", "name": "xcode-build-fixer", "kind": "skill", "official": false, "desc": "Apply approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement. Use when a developer has an approved optimization plan from xcode-build-orchestrator, wants to apply specific build fixes, needs help implementing build setting changes, script phase guards, source-level compilation fixes, or SPM restructuring that was recommended by an analysis skill.", "repo": "https://github.com/AvdLee/Xcode-Build-Optimization-Agent-Skill/tree/HEAD/skills/xcode-build-fixer", "install": ["npx skills add AvdLee/Xcode-Build-Optimization-Agent-Skill --skill xcode-build-fixer"], "stars": 1273, "pushed": "2026-09-14T09:05:25Z", "license": "MIT", "plat": "xcode", "live": "Not checked (runs locally)"}, {"id": "skill:AvdLee/Xcode-Build-Optimization-Agent-Skill/skills/xcode-build-orchestrator", "name": "xcode-build-orchestrator", "kind": "skill", "official": false, "desc": "Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval, delegating approved fixes to xcode-build-fixer, and re-benchmarking after changes. Use when a developer wants an end-to-end build optimization workflow, asks to speed up Xcode builds, wants a full build audit, or needs a recommend-first optimization pass covering compilation, project settings, and packages.", "repo": "https://github.com/AvdLee/Xcode-Build-Optimization-Agent-Skill/tree/HEAD/skills/xcode-build-orchestrator", "install": ["npx skills add AvdLee/Xcode-Build-Optimization-Agent-Skill --skill xcode-build-orchestrator"], "stars": 1273, "pushed": "2026-09-14T09:05:25Z", "license": "MIT", "plat": "xcode", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/agentic-tdd", "name": "agentic-tdd", "kind": "skill", "official": false, "desc": "Test-driven development for behaviour a unit test cannot reach, by writing the expectation against the running app before writing the code. Declare the consequence first, watch it fail, implement, watch it pass. Use when building a user-facing feature, when the user asks for TDD on UI or full-stack work, when a unit test cannot express the outcome that matters, or when you want a red-green loop that runs against the real app instead of mocks.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/agentic-tdd", "install": ["npx skills add reticlehq/reticle --skill agentic-tdd"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/debug-broken-ui", "name": "debug-broken-ui", "kind": "skill", "official": false, "desc": "Find out why something in a running web app does not work, when the console is empty and the code looks correct. Reads the click, the request, the store and the console together and returns the file:line to open. Use when a button does nothing, a form will not submit, data will not load, a page renders blank or stale, a modal will not close, or the user says \"it's broken\" and the code review says it is fine.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/debug-broken-ui", "install": ["npx skills add reticlehq/reticle --skill debug-broken-ui"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/drive-desktop-app", "name": "drive-desktop-app", "kind": "skill", "official": false, "desc": "Drive and verify an Electron or Tauri desktop app from the inside, including the main-process and Rust IPC calls a browser tool cannot see. Use when a desktop app needs testing, when a feature works in the browser but not in the packaged app, when an IPC or invoke call needs proving, when a desktop screenshot or visual diff is wanted, or when you need a headless run of a desktop UI in CI.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/drive-desktop-app", "install": ["npx skills add reticlehq/reticle --skill drive-desktop-app"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "desktop apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/false-green-tests", "name": "false-green-tests", "kind": "skill", "official": false, "desc": "Find out why the tests pass but the app is broken. Catches false greens: a green suite over a feature that does not work, a mocked API standing in for a real one, an assertion that holds no matter what the app does, a click handler wired to nothing. Use when the suite is green and the user says it is broken, when a test never fails, when coverage looks fine but bugs still ship, or before trusting a passing run you did not watch.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/false-green-tests", "install": ["npx skills add reticlehq/reticle --skill false-green-tests"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/fix-what-i-pointed-at", "name": "fix-what-i-pointed-at", "kind": "skill", "official": false, "desc": "Pick up the bugs a human flagged by pointing at them in the running app, each arriving with the element, the note they typed, and the source file and line. Use when the user says they marked or flagged something, when starting a session on an app someone has been clicking through, when a designer or PM has left feedback in the UI, or when the user describes a problem as \"that button there\" without saying which file.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/fix-what-i-pointed-at", "install": ["npx skills add reticlehq/reticle --skill fix-what-i-pointed-at"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/install-and-verify", "name": "install-and-verify", "kind": "skill", "official": false, "desc": "Verify that a web app change actually works by driving the running app from the inside (DOM, network, routing, console, framework state) instead of screenshots or guessing. Use after any user-facing change, when a fix is claimed but unproven, when a test passes but the UI is broken, or when you need a real verdict rather than \"looks right\". Also use to install and wire up Reticle in a project that does not have it yet.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/install-and-verify", "install": ["npx skills add reticlehq/reticle --skill install-and-verify"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/replay-user-flows", "name": "replay-user-flows", "kind": "skill", "official": false, "desc": "Turn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model in the loop and no test code to write. Use when you have driven the same flow twice, when the user wants regression coverage without a Playwright suite, when a refactor needs proving against every existing journey, or when re-verifying by hand is costing a full drive every time.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/replay-user-flows", "install": ["npx skills add reticlehq/reticle --skill replay-user-flows"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/test-error-states", "name": "test-error-states", "kind": "skill", "official": false, "desc": "Force the states a happy-path run never reaches (a failing API, an empty list, a slow request, a timeout, an expired session, a toast that auto-dismisses) and check the UI actually handles them. Use when error handling was written but never run, when a loading or empty state needs verifying, when a bug only happens on a slow connection, or when a timer, poll, debounce or retry needs testing without sleeping.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/test-error-states", "install": ["npx skills add reticlehq/reticle --skill test-error-states"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/verify-cli-run", "name": "verify-cli-run", "kind": "skill", "official": false, "desc": "Prove that a command-line tool actually did what it said, instead of trusting its exit code and its output. Snapshots the filesystem before and after, names the expected consequence in advance, and returns one of four verdicts with what could not be seen. Use after running a build, a migration, a scaffolder, a formatter, a codegen step, or an AI coding CLI; when a command printed success and you are about to report \"done\"; when you are about to write \"exit code 0, so it worked\"; or when a tool c", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/verify-cli-run", "install": ["npx skills add reticlehq/reticle --skill verify-cli-run"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "cli tools", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/verify-form-validation", "name": "verify-form-validation", "kind": "skill", "official": false, "desc": "Check that a form actually rejects bad input: the error message renders, the submit button stays disabled, and no request goes out. Use when validation logic was written but never driven, when a \"required\" or pattern check looks right on screen but was never proven, or when a bug report says the form submitted invalid data anyway.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/verify-form-validation", "install": ["npx skills add reticlehq/reticle --skill verify-form-validation"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/verify-keyboard-access", "name": "verify-keyboard-access", "kind": "skill", "official": false, "desc": "Verify that every interactive control on a page can take keyboard focus and that its primary action fires from the keyboard rather than only the mouse, and say plainly that Tab order cannot be verified today. Use when a component was hand-tested with a mouse, a custom dropdown/modal/combobox was added, or an accessibility report flags an unreachable control.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/verify-keyboard-access", "install": ["npx skills add reticlehq/reticle --skill verify-keyboard-access"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/verify-language-switch", "name": "verify-language-switch", "kind": "skill", "official": false, "desc": "Prove a language switch translates what the user sees, keeps what they had already typed, and is still in force after a reload. Use when i18n, a locale picker, a language menu or translation files were added or changed, when a string is suspected of staying in the old language or showing a raw translation key, or when a user reports losing their form or their language choice after switching or refreshing.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/verify-language-switch", "install": ["npx skills add reticlehq/reticle --skill verify-language-switch"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/verify-login-logout", "name": "verify-login-logout", "kind": "skill", "official": false, "desc": "Prove sign-in lands the user where they should be, sign-out really ends the session so a protected page sends them back to sign in, and an expired session asks to sign in again instead of breaking. Use when auth, a login form, a logout button, route guards or token refresh were added or changed, or when a user reports being logged out, or not logged out, unexpectedly.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/verify-login-logout", "install": ["npx skills add reticlehq/reticle --skill verify-login-logout"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/verify-optimistic-update", "name": "verify-optimistic-update", "kind": "skill", "official": false, "desc": "Prove a UI that updates before the server answers puts things back and says so when the request fails, and keeps the change when it succeeds. Use when a like, toggle, rename, reorder, delete or add-to-cart updates instantly, when an optimistic update was added or changed, or when a user reports a change that \"saved\" but was gone after a reload.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/verify-optimistic-update", "install": ["npx skills add reticlehq/reticle --skill verify-optimistic-update"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/verify-pagination", "name": "verify-pagination", "kind": "skill", "official": false, "desc": "Prove the next page of a list, or the next batch of an infinite scroll, loads NEW rows from the server, repeats none, and that the end of the list is handled. Use when pagination or infinite scroll was added or changed, when a list shows the same rows twice or skips some, or when the last page still offers a next control.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/verify-pagination", "install": ["npx skills add reticlehq/reticle --skill verify-pagination"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/verify-ui-change", "name": "verify-ui-change", "kind": "skill", "official": false, "desc": "Check that a change to a web app actually works in the running app before calling it done. Drives the real page and returns a pass/fail verdict with the request that fired, the state that moved, and the file:line to fix. Use after editing a component, a form, a route, or an API call; when you have said \"fixed\" but have not opened the app; when the user asks \"does it actually work?\"; or when a change looks right on screen and you cannot prove it.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/verify-ui-change", "install": ["npx skills add reticlehq/reticle --skill verify-ui-change"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:reticlehq/reticle/skills/verify-unattended", "name": "verify-unattended", "kind": "skill", "official": false, "desc": "Install, instrument and verify a web app end to end without pausing for a human. Use in an autonomous or goal-mode agent, in CI, or in any client that asks for approval on every command: it never says \"restart your client\" or \"open a browser\", because it takes a route that needs neither. Prefer the normal reticle skill when a human is present and can answer.", "repo": "https://github.com/reticlehq/reticle/tree/HEAD/skills/verify-unattended", "install": ["npx skills add reticlehq/reticle --skill verify-unattended"], "stars": 1272, "pushed": "2026-11-12T06:35:55Z", "license": "NOASSERTION", "plat": "web apps", "live": "Not checked (runs locally)"}, {"id": "skill:chrisbanes/skills/skills/compose-ui-testing-patterns", "name": "compose-ui-testing-patterns", "kind": "skill", "official": false, "desc": "Use when writing or reviewing Jetpack Compose UI tests, screenshot tests or baseline-recording evidence, previews, semantics assertions, fake image loading, keyboard input, focus assertions, interaction state (hover/pressed/focused), or tests for plain state-driven UI composables.", "repo": "https://github.com/chrisbanes/skills/tree/HEAD/skills/compose-ui-testing-patterns", "install": ["npx skills add chrisbanes/skills --skill compose-ui-testing-patterns"], "stars": 1154, "pushed": "2026-11-14T05:39:33Z", "license": "Apache-2.0", "plat": "jetpack compose", "live": "Not checked (runs locally)"}, {"id": "skill:openclaw/agent-skills/skills/behavior-validator", "name": "behavior-validator", "kind": "skill", "official": false, "desc": "Source-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts.", "repo": "https://github.com/openclaw/agent-skills/tree/HEAD/skills/behavior-validator", "install": ["npx skills add openclaw/agent-skills --skill behavior-validator"], "stars": 1119, "pushed": "2026-11-12T13:54:01Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:openclaw/agent-skills/skills/crabbox", "name": "crabbox", "kind": "skill", "official": false, "desc": "Crabbox/Testbox remote proof: portable provider routing, untrusted isolation, Linux/macOS/Windows/WSL2, live E2E, diagnostics, cleanup.", "repo": "https://github.com/openclaw/agent-skills/tree/HEAD/skills/crabbox", "install": ["npx skills add openclaw/agent-skills --skill crabbox"], "stars": 1119, "pushed": "2026-11-12T13:54:01Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:zenstory-ai/novel-to-game/skills/game-qa", "name": "game-qa", "kind": "skill", "official": false, "desc": "Blind-playtest and verify a game on its target runtime as a first-time player without reading source code. Run an isolated first-time playthrough first to uncover onboarding, guidance, interaction, pacing, and mobile viewport issues, then reconcile against design specs and write one complete-run verification record. Use for blind playtest a generated game, QA a game build as a new player, audit first-run playability, or verify a game build. 游戏实机盲玩与运行验收。先以未读源码与设计文档的新玩家身份在目标运行环境中从头盲玩，排查上手引导、操作流程、视", "repo": "https://github.com/zenstory-ai/novel-to-game/tree/HEAD/skills/game-qa", "install": ["npx skills add zenstory-ai/novel-to-game --skill game-qa"], "stars": 1081, "pushed": "2026-11-12T07:25:41Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:mariadb-operator/mariadb-operator/.agents/skills/mariadb-operator-test", "name": "mariadb-operator-test", "kind": "skill", "official": false, "desc": "Conduct in-depth, end-to-end testing of a mariadb-operator/mariadb-operator pull request in a local KIND environment, hunting for corner cases and failure modes to make the feature as robust and polished as possible before it is released. Builds a test plan from the PR, runs happy-path, reported-repro and failure-injection scenarios (process and container kills, retries, timeouts, concurrency, deletion mid-operation, operator restarts, manual interventions), fixes the gaps it finds, separates re", "repo": "https://github.com/mariadb-operator/mariadb-operator/tree/HEAD/.agents/skills/mariadb-operator-test", "install": ["npx skills add mariadb-operator/mariadb-operator --skill mariadb-operator-test"], "stars": 1038, "pushed": "2026-11-09T04:32:12Z", "license": "MIT", "plat": "kubernetes", "live": "Not checked (runs locally)"}, {"id": "skill:new-silvermoon/awesome-android-agent-skills/.github/skills/testing_and_automation/android-testing", "name": "android-testing", "kind": "skill", "official": false, "desc": "Comprehensive testing strategy involving Unit, Integration, Hilt, and Screenshot tests.", "repo": "https://github.com/new-silvermoon/awesome-android-agent-skills/tree/HEAD/.github/skills/testing_and_automation/android-testing", "install": ["npx skills add new-silvermoon/awesome-android-agent-skills --skill android-testing"], "stars": 1004, "pushed": "2026-07-27T21:51:10Z", "license": "Apache-2.0", "plat": "android", "live": "Not checked (runs locally)"}, {"id": "skill:laolaoshiren/claude-code-skills-zh/skills/api-tester", "name": "api-tester", "kind": "skill", "official": false, "desc": "依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时；区分“生成测试”和“执行请求”的授权，不猜测状态码、响应结构或 SLA，不在未确认环境中发送写请求。", "repo": "https://github.com/laolaoshiren/claude-code-skills-zh/tree/HEAD/skills/api-tester", "install": ["npx skills add laolaoshiren/claude-code-skills-zh --skill api-tester"], "stars": 909, "pushed": "2026-11-11T00:00:34Z", "license": "MIT", "plat": "openapi", "live": "Not checked (runs locally)"}, {"id": "skill:laolaoshiren/claude-code-skills-zh/skills/perf-profiler", "name": "perf-profiler", "kind": "skill", "official": false, "desc": "基于可复现基线和 profiler 证据分析性能问题。用于用户要求定位慢接口、慢任务、慢查询、内存或网络瓶颈，制定优化方案，或验证优化收益时；区分实测结论与静态推断，不虚构耗时和提升比例，生产环境操作需明确授权。", "repo": "https://github.com/laolaoshiren/claude-code-skills-zh/tree/HEAD/skills/perf-profiler", "install": ["npx skills add laolaoshiren/claude-code-skills-zh --skill perf-profiler"], "stars": 909, "pushed": "2026-11-11T00:00:34Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:laolaoshiren/claude-code-skills-zh/skills/test-generator", "name": "test-generator", "kind": "skill", "official": false, "desc": "依据真实代码契约生成并验证单元测试或集成测试。用于用户要求为函数、类、接口或缺陷补测试、提高覆盖率、生成回归用例或完善测试策略时；先读取现有测试与调用方，不猜测空值、异常或超时行为，不自动安装框架或访问生产依赖。", "repo": "https://github.com/laolaoshiren/claude-code-skills-zh/tree/HEAD/skills/test-generator", "install": ["npx skills add laolaoshiren/claude-code-skills-zh --skill test-generator"], "stars": 909, "pushed": "2026-11-11T00:00:34Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:alirezarezvani/claude-code-skill-factory/generated-skills/tdd-guide", "name": "tdd-guide", "kind": "skill", "official": false, "desc": "Comprehensive Test Driven Development guide for engineering subagents with multi-framework support, coverage analysis, and intelligent test generation", "repo": "https://github.com/alirezarezvani/claude-code-skill-factory/tree/HEAD/generated-skills/tdd-guide", "install": ["npx skills add alirezarezvani/claude-code-skill-factory --skill tdd-guide"], "stars": 900, "pushed": "2025-11-12T15:30:27Z", "license": "MIT", "plat": "testing", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:vostride/agent-qa", "name": "agent-qa", "kind": "mcp", "official": null, "desc": "Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.", "repo": "https://github.com/vostride/agent-qa", "install": [], "stars": 857, "pushed": null, "license": null, "plat": "software testing", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:dotnet/dev-proxy", "name": "dev-proxy", "kind": "mcp", "official": null, "desc": "Simulate API failures, throttling, and chaos — all from your command line.", "repo": "https://github.com/dotnet/dev-proxy", "install": [], "stars": 847, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:browser-use/vibetest-use", "name": "vibetest-use", "kind": "mcp", "official": null, "desc": "Vibetest MCP - automated QA testing using Browser-Use agents", "repo": "https://github.com/browser-use/vibetest-use", "install": [], "stars": 837, "pushed": null, "license": null, "plat": "browser-use", "live": "Not checked (runs locally)"}, {"id": "skill:yunshu0909/yunshu_skillshub/coding/issue-triage", "name": "issue-triage", "kind": "skill", "official": false, "desc": "GitHub Issue 处理协作流程。当用户收到 issue 需要分析和回复时使用。通过\"诊断 → 定性 → 决策 → 回复\"四步法，从一个 issue 产出准确的根因分析和得体的用户回复，避免误判问题类型或回复不专业。", "repo": "https://github.com/yunshu0909/yunshu_skillshub/tree/HEAD/coding/issue-triage", "install": ["npx skills add yunshu0909/yunshu_skillshub --skill issue-triage"], "stars": 790, "pushed": "2026-10-11T14:46:01Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:yunshu0909/yunshu_skillshub/coding/prd-test-writer", "name": "prd-test-writer", "kind": "skill", "official": false, "desc": "PRD + 可执行测试用例双文档一体化协作。与用户共同写并迭代。理解需求后自主读代码再写；故事驱动 + 分阶段单点确认；每个 PRD 产出 PRD-MD 与 测试用例-MD（给 AI 的事实源）+ 两份套模板的 review HTML（给人查阅，与 MD 严格 1:1）。触发：梳理/撰写/完善 PRD、需求文档、用户故事、验收标准、测试用例、测试基准、测试方案。", "repo": "https://github.com/yunshu0909/yunshu_skillshub/tree/HEAD/coding/prd-test-writer", "install": ["npx skills add yunshu0909/yunshu_skillshub --skill prd-test-writer"], "stars": 790, "pushed": "2026-10-11T14:46:01Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:lixiaolin94/skills/android-background-test", "name": "android-background-test", "kind": "skill", "official": false, "desc": "在 ADB 连接的 Android 真机上测试或操作 App：启动、截图、读控件树、按元素或坐标点击、滑动、按键、输入中文、 按步骤跑用例（Journeys）。全程在用户看不到的后台屏进行，用户可以照常用手机。用户提到“用手机/真机测一下” “adb 截图/点击”“dump UI 树/找到某个按钮点一下”“Android UI 自动化”“真机复现 bug”“看看 App 在手机上的效果” 时使用；优先于直接用 adb shell input/screencap/uiautomator 操作主屏。Use when testing or driving an Android app on a real device over ADB (screenshot, UI tree, tap by element, type text) without taking over the screen.", "repo": "https://github.com/lixiaolin94/skills/tree/HEAD/android-background-test", "install": ["npx skills add lixiaolin94/skills --skill android-background-test"], "stars": 774, "pushed": "2026-11-02T03:04:51Z", "license": null, "plat": "android", "live": "Not checked (runs locally)"}, {"id": "skill:decebals/claude-code-java/skills/test-quality", "name": "test-quality", "kind": "skill", "official": false, "desc": "Write high-quality JUnit 5 tests with AssertJ assertions. Use when user says \"add tests\", \"write tests\", \"improve test coverage\", or when reviewing/creating test classes for Java code.", "repo": "https://github.com/decebals/claude-code-java/tree/HEAD/skills/test-quality", "install": ["npx skills add decebals/claude-code-java --skill test-quality"], "stars": 773, "pushed": "2026-10-29T22:35:52Z", "license": "MIT", "plat": "junit 5", "live": "Not checked (runs locally)"}, {"id": "skill:laravel/agent-skills/laravel-nightwatch/skills/configure-nightwatch", "name": "configure-nightwatch", "kind": "skill", "official": false, "desc": "Configures Laravel Nightwatch data collection, sampling rates, filtering rules, and redaction policies. Use when setting up Nightwatch, managing data volume, protecting sensitive data (PII), or optimizing event collection for production workloads.", "repo": "https://github.com/laravel/agent-skills/tree/HEAD/laravel-nightwatch/skills/configure-nightwatch", "install": ["npx skills add laravel/agent-skills --skill configure-nightwatch"], "stars": 738, "pushed": "2026-11-14T00:18:41Z", "license": null, "plat": "laravel nightwatch", "live": "Not checked (runs locally)"}, {"id": "skill:marckohlbrugge/37signals-skills/skills/rails-testing", "name": "rails-testing", "kind": "skill", "official": false, "desc": "Apply Rails testing standards with Minitest, fixtures, and pragmatic coverage boundaries. Use when creating tests, reviewing test quality, or improving flaky and slow Rails test suites.", "repo": "https://github.com/marckohlbrugge/37signals-skills/tree/HEAD/skills/rails-testing", "install": ["npx skills add marckohlbrugge/37signals-skills --skill rails-testing"], "stars": 732, "pushed": "2026-06-09T20:50:05Z", "license": null, "plat": "ruby on rails", "live": "Not checked (runs locally)"}, {"id": "skill:spf13/go-skills/templates/skill", "name": "go-profiling", "kind": "skill", "official": false, "desc": "Use when a Go program is slow, allocation-heavy, or suspected of leaking — pprof CPU, heap, block, mutex and goroutine profiles, benchmark comparison with -benchmem, escape analysis via -gcflags=-m, and cutting allocation counts. Not for correctness bugs; use the go skill.", "repo": "https://github.com/spf13/go-skills/tree/HEAD/templates/skill", "install": ["npx skills add spf13/go-skills --skill go-profiling"], "stars": 708, "pushed": "2026-11-05T19:10:47Z", "license": "MIT", "plat": "go", "live": "Not checked (runs locally)"}, {"id": "skill:warpdotdev/common-skills/.agents/skills/diagnose-ci-failures", "name": "diagnose-ci-failures", "kind": "skill", "official": false, "desc": "Diagnose CI failures for a PR using the GitHub CLI, extract error logs, and generate a plan to fix them. Use when the user asks to check CI status, pull CI issues, triage test failures, or investigate PR build failures.", "repo": "https://github.com/warpdotdev/common-skills/tree/HEAD/.agents/skills/diagnose-ci-failures", "install": ["npx skills add warpdotdev/common-skills --skill diagnose-ci-failures"], "stars": 699, "pushed": "2026-11-11T01:12:11Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:warpdotdev/common-skills/.agents/skills/reproduce-bug-report", "name": "reproduce-bug-report", "kind": "skill", "official": false, "desc": "Launch Oz cloud agents with computer use to reproduce UI-focused bug reports, capture visual evidence (a screen recording by default), and report reproduction findings. Use when investigating a specific interactive or visual bug from an issue, ticket, support report, or prompt.", "repo": "https://github.com/warpdotdev/common-skills/tree/HEAD/.agents/skills/reproduce-bug-report", "install": ["npx skills add warpdotdev/common-skills --skill reproduce-bug-report"], "stars": 699, "pushed": "2026-11-11T01:12:11Z", "license": "MIT", "plat": "oz", "live": "Not checked (runs locally)"}, {"id": "skill:warpdotdev/common-skills/.agents/skills/validate-changes-match-specs", "name": "validate-changes-match-specs", "kind": "skill", "official": false, "desc": "Validate that a branch or pull request implementation matches introduced product, technical, security, and related specs. Use when reviewing or finishing a spec-driven change and resolving mismatches between checked-in specs and implementation.", "repo": "https://github.com/warpdotdev/common-skills/tree/HEAD/.agents/skills/validate-changes-match-specs", "install": ["npx skills add warpdotdev/common-skills --skill validate-changes-match-specs"], "stars": 699, "pushed": "2026-11-11T01:12:11Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:mhattingpete/claude-skills-marketplace/engineering-workflow-plugin/skills/test-fixing", "name": "test-fixing", "kind": "skill", "official": false, "desc": "Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.", "repo": "https://github.com/mhattingpete/claude-skills-marketplace/tree/HEAD/engineering-workflow-plugin/skills/test-fixing", "install": ["npx skills add mhattingpete/claude-skills-marketplace --skill test-fixing"], "stars": 695, "pushed": "2026-07-25T06:09:24Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.SonarSource/sonarqube-mcp-server", "name": "SonarQube MCP Server", "kind": "mcp", "official": null, "desc": "Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants.", "repo": "https://github.com/SonarSource/sonarqube-mcp-server", "install": ["oci:docker.io/sonarsource/sonarqube-mcp"], "stars": 686, "pushed": "2026-11-13T12:00:18Z", "license": "NOASSERTION", "plat": "sonarqube", "live": "Not checked (runs locally)"}, {"id": "skill:EricTechPro/super-board/skills/super-qa", "name": "super-qa", "kind": "skill", "official": false, "desc": "Super QA canonical workflow for functional bug-bash, evidence capture, and fix-ready issue filing. Crawls routes from `docs/super-qa/queue.md` with Playwright, records screenshots/logs/HARs, files product-readable issues with clear type/priority/area labels, and continues until traversal is complete or only human-gated blockers remain. Crawling is always browser-driven, but the regression test it leaves behind is written at whichever layer the defect actually lives — unit or integration in Vites", "repo": "https://github.com/EricTechPro/super-board/tree/HEAD/skills/super-qa", "install": ["npx skills add EricTechPro/super-board --skill super-qa"], "stars": 677, "pushed": "2026-10-29T20:57:37Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:EricTechPro/super-board/skills/super-qa/templates/project-verifier", "name": "verify-app", "kind": "skill", "official": false, "desc": "Run affected app feature checks, inspect evidence, or maintain this project's verifier when source or accepted behavior changes.", "repo": "https://github.com/EricTechPro/super-board/tree/HEAD/skills/super-qa/templates/project-verifier", "install": ["npx skills add EricTechPro/super-board --skill verify-app"], "stars": 677, "pushed": "2026-10-29T20:57:37Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:Gentleman-Programming/Gentleman-Skills/curated/playwright", "name": "playwright", "kind": "skill", "official": false, "desc": "Playwright E2E testing patterns. Trigger: When writing E2E tests - Page Objects, selectors, MCP workflow.", "repo": "https://github.com/Gentleman-Programming/Gentleman-Skills/tree/HEAD/curated/playwright", "install": ["npx skills add Gentleman-Programming/Gentleman-Skills --skill playwright"], "stars": 674, "pushed": "2026-03-28T09:24:56Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:Gentleman-Programming/Gentleman-Skills/curated/pytest", "name": "pytest", "kind": "skill", "official": false, "desc": "Pytest testing patterns for Python. Trigger: When writing Python tests - fixtures, mocking, markers.", "repo": "https://github.com/Gentleman-Programming/Gentleman-Skills/tree/HEAD/curated/pytest", "install": ["npx skills add Gentleman-Programming/Gentleman-Skills --skill pytest"], "stars": 674, "pushed": "2026-03-28T09:24:56Z", "license": "MIT", "plat": "pytest", "live": "Not checked (runs locally)"}, {"id": "skill:JackyST0/awesome-agent-skills/examples/unit-test-generator", "name": "unit-test-generator", "kind": "skill", "official": false, "desc": "Automatically generate unit tests based on source code, supporting multiple languages and testing frameworks.", "repo": "https://github.com/JackyST0/awesome-agent-skills/tree/HEAD/examples/unit-test-generator", "install": ["npx skills add JackyST0/awesome-agent-skills --skill unit-test-generator"], "stars": 669, "pushed": "2026-11-13T09:35:32Z", "license": "CC0-1.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:LeastBit/Claude_skills_zh-CN/skills/web-artifacts-builder", "name": "web-artifacts-builder", "kind": "skill", "official": false, "desc": "用于使用现代前端 Web 技术（React、Tailwind CSS、shadcn/ui）创建复杂的、多组件的 claude.ai HTML artifact 的工具套件。适用于需要状态管理、路由或 shadcn/ui 组件的复杂 artifact - 不适用于简单的单文件 HTML/JSX artifact。", "repo": "https://github.com/LeastBit/Claude_skills_zh-CN/tree/HEAD/skills/web-artifacts-builder", "install": ["npx skills add LeastBit/Claude_skills_zh-CN --skill web-artifacts-builder"], "stars": 612, "pushed": "2026-01-19T05:50:17Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:n8n-io/skills/skills/n8n-debugging-official", "name": "n8n-debugging-official", "kind": "skill", "official": false, "desc": "Use when an n8n workflow isn't working, errors appear, results don't match what was expected, or the user says \"this isn't working.\" Triggers on errors, unexpected output, \"it's not working\", \"why is this happening\", \"the workflow stopped\", failure investigation, or any debugging context.", "repo": "https://github.com/n8n-io/skills/tree/HEAD/skills/n8n-debugging-official", "install": ["npx skills add n8n-io/skills --skill n8n-debugging-official"], "stars": 606, "pushed": "2026-11-14T05:04:39Z", "license": "Apache-2.0", "plat": "n8n", "live": "Not checked (runs locally)"}, {"id": "skill:n8n-io/skills/skills/n8n-error-handling-official", "name": "n8n-error-handling-official", "kind": "skill", "official": false, "desc": "Use when building any webhook-triggered workflow, scheduled/production-bound workflow, wiring a per-node error output, or any workflow where silent failure would drop user-visible work. Triggers on \"webhook\", \"respond to webhook\", \"API\", \"production\", \"error\", \"failure\", \"5xx\", \"try/catch\", \"error workflow\", \"onError\", \"continueErrorOutput\", \"error branch\", \"node error output\", \"output(1)\", \"main[1]\", \"scheduled\", or any workflow that runs unattended.", "repo": "https://github.com/n8n-io/skills/tree/HEAD/skills/n8n-error-handling-official", "install": ["npx skills add n8n-io/skills --skill n8n-error-handling-official"], "stars": 606, "pushed": "2026-11-14T05:04:39Z", "license": "Apache-2.0", "plat": "n8n", "live": "Not checked (runs locally)"}, {"id": "skill:posit-dev/skills/posit-dev/review-testing", "name": "review-testing", "kind": "skill", "official": false, "desc": "Review test code for quality, design, and completeness after implementing a feature or fixing a bug. Use when the user asks to \"review my tests\", \"check my test quality\", \"are these tests good enough\", \"review testing\", or after completing a feature implementation that includes tests. Also use when tests feel brittle, flaky, or superficial. Cross-references production code to find coverage gaps.", "repo": "https://github.com/posit-dev/skills/tree/HEAD/posit-dev/review-testing", "install": ["npx skills add posit-dev/skills --skill review-testing"], "stars": 565, "pushed": "2026-11-12T21:12:35Z", "license": "MIT", "plat": "test code", "live": "Not checked (runs locally)"}, {"id": "skill:dart-lang/skills/skills/dart-add-unit-test", "name": "dart-add-unit-test", "kind": "skill", "official": false, "desc": "Write and organize unit tests for functions, methods, and classes using `package:test`. Use when creating new logic or fixing bugs to ensure code remains correct and regression-free.", "repo": "https://github.com/dart-lang/skills/tree/HEAD/skills/dart-add-unit-test", "install": ["npx skills add dart-lang/skills --skill dart-add-unit-test"], "stars": 552, "pushed": "2026-11-04T21:53:50Z", "license": "BSD-3-Clause", "plat": "dart", "live": "Not checked (runs locally)"}, {"id": "skill:dart-lang/skills/skills/dart-collect-coverage", "name": "dart-collect-coverage", "kind": "skill", "official": false, "desc": "Collect coverage using the coverage packge and create an LCOV report", "repo": "https://github.com/dart-lang/skills/tree/HEAD/skills/dart-collect-coverage", "install": ["npx skills add dart-lang/skills --skill dart-collect-coverage"], "stars": 552, "pushed": "2026-11-04T21:53:50Z", "license": "BSD-3-Clause", "plat": "dart", "live": "Not checked (runs locally)"}, {"id": "skill:dart-lang/skills/skills/dart-fix-runtime-errors", "name": "dart-fix-runtime-errors", "kind": "skill", "official": false, "desc": "Uses get_runtime_errors and lsp to fetch an active stack trace, locate the failing line, apply a fix, and verify resolution via hot_reload.", "repo": "https://github.com/dart-lang/skills/tree/HEAD/skills/dart-fix-runtime-errors", "install": ["npx skills add dart-lang/skills --skill dart-fix-runtime-errors"], "stars": 552, "pushed": "2026-11-04T21:53:50Z", "license": "BSD-3-Clause", "plat": "dart", "live": "Not checked (runs locally)"}, {"id": "skill:dart-lang/skills/skills/dart-generate-test-mocks", "name": "dart-generate-test-mocks", "kind": "skill", "official": false, "desc": "Define and generate mock objects for external dependencies using `package:mockito` and `build_runner`. Use when unit testing classes that depend on complex external services like APIs or databases.", "repo": "https://github.com/dart-lang/skills/tree/HEAD/skills/dart-generate-test-mocks", "install": ["npx skills add dart-lang/skills --skill dart-generate-test-mocks"], "stars": 552, "pushed": "2026-11-04T21:53:50Z", "license": "BSD-3-Clause", "plat": "dart", "live": "Not checked (runs locally)"}, {"id": "skill:UnrealXu/UnrealEngine5-Skills/skills/ue5-debug-validation", "name": "ue5-debug-validation", "kind": "skill", "official": false, "desc": "UE5.6-UE5.8 debugging and validation workflow for logs, asset checks, and regression triage. Use when requests involve troubleshooting why gameplay does not work, validating expected output, narrowing minimal repro, and producing concrete fix steps.", "repo": "https://github.com/UnrealXu/UnrealEngine5-Skills/tree/HEAD/skills/ue5-debug-validation", "install": ["npx skills add UnrealXu/UnrealEngine5-Skills --skill ue5-debug-validation"], "stars": 541, "pushed": "2026-08-26T11:00:11Z", "license": "MIT", "plat": "unreal engine", "live": "Not checked (runs locally)"}, {"id": "skill:TheQtCompanyRnD/agent-skills/skills/qt-qml-test", "name": "qt-qml-test", "kind": "skill", "official": false, "desc": "Generates Qt Quick Test cases (TestCase, SignalSpy, tryCompare) for QML components. Use for \"write QML tests\", \"qml test\", \"qt quick test\".", "repo": "https://github.com/TheQtCompanyRnD/agent-skills/tree/HEAD/skills/qt-qml-test", "install": ["npx skills add TheQtCompanyRnD/agent-skills --skill qt-qml-test"], "stars": 538, "pushed": "2026-11-09T13:35:44Z", "license": "NOASSERTION", "plat": "qt", "live": "Not checked (runs locally)"}, {"id": "skill:TheQtCompanyRnD/agent-skills/skills/qt-qml-test-run", "name": "qt-qml-test-run", "kind": "skill", "official": false, "desc": "Builds and runs Qt Quick Test (qmltestrunner / CTest) for a QML project, then writes a Markdown report. Use for \"run qml tests\", \"run qmltestrunner\".", "repo": "https://github.com/TheQtCompanyRnD/agent-skills/tree/HEAD/skills/qt-qml-test-run", "install": ["npx skills add TheQtCompanyRnD/agent-skills --skill qt-qml-test-run"], "stars": 538, "pushed": "2026-11-09T13:35:44Z", "license": "NOASSERTION", "plat": "qt", "live": "Not checked (runs locally)"}, {"id": "skill:zhuyansen/agent-skills-hub/ops/skillmgr-runs/in/input/library/perf-profiler-notes", "name": "perf-profiler-notes", "kind": "skill", "official": false, "desc": "Read a profiler output and point to the three functions where time is actually spent.", "repo": "https://github.com/zhuyansen/agent-skills-hub/tree/HEAD/ops/skillmgr-runs/in/input/library/perf-profiler-notes", "install": ["npx skills add zhuyansen/agent-skills-hub --skill perf-profiler-notes"], "stars": 502, "pushed": "2026-11-13T15:49:58Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:zhuyansen/agent-skills-hub/ops/skillmgr-runs/in/input/library/unit-test-scaffold", "name": "unit-test-scaffold", "kind": "skill", "official": false, "desc": "Create a unit test file for a module with one test per public function and the edge cases to cover.", "repo": "https://github.com/zhuyansen/agent-skills-hub/tree/HEAD/ops/skillmgr-runs/in/input/library/unit-test-scaffold", "install": ["npx skills add zhuyansen/agent-skills-hub --skill unit-test-scaffold"], "stars": 502, "pushed": "2026-11-13T15:49:58Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:AvdLee/Swift-Testing-Agent-Skill/swift-testing-expert", "name": "swift-testing-expert", "kind": "skill", "official": false, "desc": "Expert guidance for Swift Testing: test structure, #expect/#require macros, traits and tags, parameterized tests, test plans, parallel execution, async waiting patterns, and XCTest migration. Use when writing new Swift tests, modernizing XCTest suites, debugging flaky tests, or improving test quality and maintainability in Apple-platform or Swift server projects.", "repo": "https://github.com/AvdLee/Swift-Testing-Agent-Skill/tree/HEAD/swift-testing-expert", "install": ["npx skills add AvdLee/Swift-Testing-Agent-Skill --skill swift-testing-expert"], "stars": 480, "pushed": "2026-09-14T09:05:26Z", "license": "MIT", "plat": "swift-testing-expert", "live": "Not checked (runs locally)"}, {"id": "skill:udaysharmadev/Gravitas/plugins/gravitas-perf", "name": "gravitas-perf", "kind": "skill", "official": false, "desc": "Performance analysis mode for GRAVITAS. Adds profiling patterns, benchmark requirements, algorithmic complexity analysis, and before/after measurement protocol. Load for any performance optimization work.", "repo": "https://github.com/udaysharmadev/Gravitas/tree/HEAD/plugins/gravitas-perf", "install": ["npx skills add udaysharmadev/Gravitas --skill gravitas-perf"], "stars": 473, "pushed": "2026-11-03T14:09:22Z", "license": "MIT", "plat": "gravitas-perf", "live": "Not checked (runs locally)"}, {"id": "skill:VisionForge-OU/foreman/src/foreman/skills/foreman-debug", "name": "foreman-debug", "kind": "skill", "official": false, "desc": "Headless root-cause debugging loop for a Foreman worker whose tests, build, or acceptance check are failing — especially on a retry. Find the root cause before changing anything, fix at the source with a regression test, and never thrash on symptom patches. Used inside a foreman-tdd build session; emits no summary of its own.", "repo": "https://github.com/VisionForge-OU/foreman/tree/HEAD/src/foreman/skills/foreman-debug", "install": ["npx skills add VisionForge-OU/foreman --skill foreman-debug"], "stars": 439, "pushed": "2026-06-29T00:12:23Z", "license": "NOASSERTION", "plat": "foreman", "live": "Not checked (runs locally)"}, {"id": "skill:VisionForge-OU/foreman/src/foreman/skills/foreman-tdd", "name": "foreman-tdd", "kind": "skill", "official": false, "desc": "Stack-agnostic test-driven development loop for a single Foreman issue. Implements one vertical slice with strict red-green-refactor (one test at a time, never horizontal slicing) using the foreman-test wrapper, saves completion evidence, then emits a machine-readable FOREMAN-SUMMARY block Foreman parses.", "repo": "https://github.com/VisionForge-OU/foreman/tree/HEAD/src/foreman/skills/foreman-tdd", "install": ["npx skills add VisionForge-OU/foreman --skill foreman-tdd"], "stars": 439, "pushed": "2026-06-29T00:12:23Z", "license": "NOASSERTION", "plat": "foreman", "live": "Not checked (runs locally)"}, {"id": "skill:VisionForge-OU/foreman/src/foreman/skills/foreman-verify", "name": "foreman-verify", "kind": "skill", "official": false, "desc": "Headless self-verification gate a Foreman worker runs before it claims an issue is done. Re-run the real commands, read the actual output, and only then write the FOREMAN-SUMMARY — evidence before claims, always. Used inside a foreman-tdd build session; emits no summary of its own.", "repo": "https://github.com/VisionForge-OU/foreman/tree/HEAD/src/foreman/skills/foreman-verify", "install": ["npx skills add VisionForge-OU/foreman --skill foreman-verify"], "stars": 439, "pushed": "2026-06-29T00:12:23Z", "license": "NOASSERTION", "plat": "foreman", "live": "Not checked (runs locally)"}, {"id": "skill:VisionForge-OU/foreman/src/foreman/skills/foreman-web-testing", "name": "foreman-web-testing", "kind": "skill", "official": false, "desc": "Headless end-to-end / web-app testing for the Foreman e2e stage. Derive end-to-end tests from the PRD's User Flows, drive the real application the way a user would (browser flows, screenshots, accessibility checks for web apps), make them pass via the configured e2e command, and emit the FOREMAN-SUMMARY block Foreman parses.", "repo": "https://github.com/VisionForge-OU/foreman/tree/HEAD/src/foreman/skills/foreman-web-testing", "install": ["npx skills add VisionForge-OU/foreman --skill foreman-web-testing"], "stars": 439, "pushed": "2026-06-29T00:12:23Z", "license": "NOASSERTION", "plat": "web applications", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:shanselman/sandbox-mcp", "name": "sandbox-mcp", "kind": "mcp", "official": null, "desc": "Fresh, throwaway Windows machines for testing your apps: an MCP server and CLI that automate Windows Sandbox", "repo": "https://github.com/shanselman/sandbox-mcp", "install": [], "stars": 433, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:aws-solutions/distributed-load-testing-on-aws", "name": "distributed-load-testing-on-aws", "kind": "mcp", "official": null, "desc": "Distributed Load Testing on AWS automates performance testing at scale, demonstrating how systems behave under different load conditions and helping identify potential performance issues throughout their lifecycle.", "repo": "https://github.com/aws-solutions/distributed-load-testing-on-aws", "install": [], "stars": 425, "pushed": null, "license": null, "plat": "aws", "live": "Not checked (runs locally)"}, {"id": "skill:testdino-hq/playwright-skill/e2e-testdino", "name": "e2e-testdino", "kind": "skill", "official": false, "desc": "What to do after a run of e2e, the agentic test runner from e2e.com (`e2e.config.ts`, `*.e2e.ts` files, `agent.act` steps), leaves the machine it ran on. Not for Playwright runs. Use when an e2e test failed in CI and its trace page is not in the local `.e2e/` folder, when deciding from run history whether an e2e test is flaky or broken, when quarantining a failing e2e test or checking that a fix held, when sharded e2e jobs need to show as one run, when agent steps cost more than expected or stop", "repo": "https://github.com/testdino-hq/playwright-skill/tree/HEAD/e2e-testdino", "install": ["npx skills add testdino-hq/playwright-skill --skill e2e-testdino"], "stars": 417, "pushed": "2026-11-13T12:06:32Z", "license": "MIT", "plat": "e2e.com", "live": "Not checked (runs locally)"}, {"id": "skill:testdino-hq/playwright-skill/playwright-cli", "name": "playwright-cli", "kind": "skill", "official": false, "desc": "Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or have explicit authorization to test.", "repo": "https://github.com/testdino-hq/playwright-skill/tree/HEAD/playwright-cli", "install": ["npx skills add testdino-hq/playwright-skill --skill playwright-cli"], "stars": 417, "pushed": "2026-11-13T12:06:32Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:testdino-hq/playwright-skill/core", "name": "playwright-core", "kind": "skill", "official": false, "desc": "Battle-tested Playwright patterns for writing and debugging reliable E2E, API, component, visual, accessibility, and security tests. Use when you need locator strategy, assertions, fixtures, network mocking, auth flows, trace debugging, or framework recipes for React, Next.js, Vue, and Angular. TypeScript and JavaScript.", "repo": "https://github.com/testdino-hq/playwright-skill/tree/HEAD/core", "install": ["npx skills add testdino-hq/playwright-skill --skill playwright-core"], "stars": 417, "pushed": "2026-11-13T12:06:32Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:testdino-hq/playwright-skill/qa", "name": "playwright-qa", "kind": "skill", "official": false, "desc": "QA engineering workflows on top of Playwright. Use when a QA engineer asks to design test cases from a ticket, PRD or acceptance criteria, decide what to automate, write a bug report from a failing test or trace, convert manual test cases (TestRail, Xray, CSV) into Playwright specs with case-ID traceability, or review Playwright test code and pull requests.", "repo": "https://github.com/testdino-hq/playwright-skill/tree/HEAD/qa", "install": ["npx skills add testdino-hq/playwright-skill --skill playwright-qa"], "stars": 417, "pushed": "2026-11-13T12:06:32Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:testdino-hq/playwright-skill", "name": "playwright-skill", "kind": "skill", "official": false, "desc": "Current Playwright (1.64) patterns for writing, debugging, and scaling reliable test suites. Use for any Playwright task, even ones you think you know, because the guides cover APIs and CLI flags newer than most training data. Covers writing or fixing tests, locators, a failing or flaky test, a trace.zip or error message, playwright.config and projects, network mocking, auth, visual and accessibility testing, Docker and CI sharding, playwright-cli browser automation, Playwright Test Agents, page", "repo": "https://github.com/testdino-hq/playwright-skill", "install": ["npx skills add testdino-hq/playwright-skill --skill playwright-skill"], "stars": 417, "pushed": "2026-11-13T12:06:32Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:syahiidkamil/Software-Engineer-AI-Agent-Atlas/.claude/skills/adversarial-review", "name": "adversarial-review", "kind": "skill", "official": false, "desc": "Adversarially review something just built — presume it is broken and find where. Use after implementing a feature, finishing a build, or before shipping, or whenever ATLAS or Boss wants a hostile second opinion on a diff, a running app, or a whole codebase. Spawns clean-context reviewers with opposing lenses (correctness, security, empty-world) and reproduces every finding by running the target before believing it. Distinct from /code-review, which statically reads a diff and never runs the app.", "repo": "https://github.com/syahiidkamil/Software-Engineer-AI-Agent-Atlas/tree/HEAD/.claude/skills/adversarial-review", "install": ["npx skills add syahiidkamil/Software-Engineer-AI-Agent-Atlas --skill adversarial-review"], "stars": 406, "pushed": "2026-11-01T04:14:32Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:syahiidkamil/Software-Engineer-AI-Agent-Atlas/.claude/skills/playwright-cli", "name": "playwright-cli", "kind": "skill", "official": false, "desc": "Automate browser interactions, test web pages and work with Playwright tests.", "repo": "https://github.com/syahiidkamil/Software-Engineer-AI-Agent-Atlas/tree/HEAD/.claude/skills/playwright-cli", "install": ["npx skills add syahiidkamil/Software-Engineer-AI-Agent-Atlas --skill playwright-cli"], "stars": 406, "pushed": "2026-11-01T04:14:32Z", "license": null, "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ai-dashboad/flutter-skill", "name": "io.github.ai-dashboad/flutter-skill", "kind": "mcp", "official": null, "desc": "AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero test code needed.", "repo": "https://github.com/ai-dashboad/flutter-skill", "install": ["npm:flutter-skill"], "stars": 405, "pushed": "2026-09-01T11:56:02Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.telsav/flutter-skill", "name": "io.github.telsav/flutter-skill", "kind": "mcp", "official": null, "desc": "AI E2E testing bridge — give AI eyes and hands inside any app. 8 platforms, 40+ tools.", "repo": "https://github.com/ai-dashboad/flutter-skill", "install": ["npm:flutter-skill"], "stars": 405, "pushed": "2026-09-01T11:56:02Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:arpitg1304/robotics-agent-skills/skills/robotics-testing", "name": "robotics-testing", "kind": "skill", "official": false, "desc": "Testing strategies, patterns, and tools for robotics software. Use this skill when writing unit tests, integration tests, simulation tests, or hardware-in-the-loop tests for robot systems. Trigger whenever the user mentions testing ROS nodes, pytest with ROS, launch_testing, simulation testing, CI/CD for robotics, test fixtures for sensors, mock hardware, deterministic replay, regression testing for robot behaviors, or validating perception/planning/control pipelines. Also covers property-based ", "repo": "https://github.com/arpitg1304/robotics-agent-skills/tree/HEAD/skills/robotics-testing", "install": ["npx skills add arpitg1304/robotics-agent-skills --skill robotics-testing"], "stars": 401, "pushed": "2026-08-12T01:29:38Z", "license": "Apache-2.0", "plat": "ros2", "live": "Not checked (runs locally)"}, {"id": "plugin:anthropics/claude-plugins-official:codspeed", "name": "codspeed", "kind": "claude-plugin", "official": null, "desc": "CodSpeed is the all-in-one performance testing toolkit. Dive into benchmarking results, flamegraphs, and performance comparisons — give Claude granular profiling context to pinpoint bottlenecks and autonomously iterate on performance via the CodSpeed MCP server.", "repo": "https://github.com/CodSpeedHQ/codspeed.git", "install": ["claude plugin install codspeed@claude-plugins-official"], "stars": 394, "pushed": "2026-11-12T20:13:37Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:DougTrajano/pydantic-ai-skills/.claude/skills/sonarqube", "name": "sonarqube", "kind": "skill", "official": false, "desc": "Operate SonarQube-enabled repositories through the SonarQube CLI (`sonar`): verify authentication, discover project keys, inspect project metadata, issues, measures, and quality gates, analyze changed code, scan secrets and dependency risks, call authenticated APIs, trigger remediation, configure integrations, and troubleshoot the CLI. Use whenever the user mentions SonarQube, SonarQube Cloud/SonarCloud, Sonar project details, quality gates, Sonar issues, `sonar` commands, agentic analysis, depe", "repo": "https://github.com/DougTrajano/pydantic-ai-skills/tree/HEAD/.claude/skills/sonarqube", "install": ["npx skills add DougTrajano/pydantic-ai-skills --skill sonarqube"], "stars": 381, "pushed": "2026-11-07T11:26:31Z", "license": "MIT", "plat": "sonarqube", "live": "Not checked (runs locally)"}, {"id": "skill:superagents-lab/xcode27-skills/device-interaction", "name": "device-interaction", "kind": "skill", "official": false, "desc": "Verify iOS app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.", "repo": "https://github.com/superagents-lab/xcode27-skills/tree/HEAD/device-interaction", "install": ["npx skills add superagents-lab/xcode27-skills --skill device-interaction"], "stars": 366, "pushed": "2026-06-09T08:44:33Z", "license": null, "plat": "ios", "live": "Not checked (runs locally)"}, {"id": "skill:superagents-lab/xcode27-skills/test-modernizer", "name": "test-modernizer", "kind": "skill", "official": false, "desc": "Modernize test suites to use modern Swift Testing features or migrate from XCTest.", "repo": "https://github.com/superagents-lab/xcode27-skills/tree/HEAD/test-modernizer", "install": ["npx skills add superagents-lab/xcode27-skills --skill test-modernizer"], "stars": 366, "pushed": "2026-06-09T08:44:33Z", "license": null, "plat": "swift", "live": "Not checked (runs locally)"}, {"id": "skill:justxor/claude-code-pro-course/starter-kit/.claude/skills/write-tests", "name": "write-tests", "kind": "skill", "official": false, "desc": "Пишет unit-тесты для указанного файла или функции в стиле существующих тестов проекта. Используй, когда просят добавить тесты, покрыть код тестами или проверить граничные случаи.", "repo": "https://github.com/justxor/claude-code-pro-course/tree/HEAD/starter-kit/.claude/skills/write-tests", "install": ["npx skills add justxor/claude-code-pro-course --skill write-tests"], "stars": 352, "pushed": "2026-10-01T12:10:20Z", "license": "MIT", "plat": "write-tests", "live": "Not checked (runs locally)"}, {"id": "skill:todoist/todoist-cli/.agents/skills/fix-bug", "name": "fix-bug", "kind": "skill", "official": false, "desc": "Fixes a bug by reproducing it in a failing test first, then making the smallest change that turns it green. Use when something is \"broken\", \"wrong\", \"fails\", \"doesn't work\", throws an error, or a user or issue reports a bug.", "repo": "https://github.com/todoist/todoist-cli/tree/HEAD/.agents/skills/fix-bug", "install": ["npx skills add todoist/todoist-cli --skill fix-bug"], "stars": 332, "pushed": "2026-11-12T09:40:19Z", "license": "MIT", "plat": "todoist-cli", "live": "Not checked (runs locally)"}, {"id": "skill:todoist/todoist-cli/.agents/skills/learn", "name": "learn", "kind": "skill", "official": false, "desc": "Turns a correction or a repeated mistake into the strongest structure that prevents it, and proves it catches the mistake. Use when the owner says \"don't do that again\", \"remember this\", \"you keep doing X\", or a review finds the same problem twice.", "repo": "https://github.com/todoist/todoist-cli/tree/HEAD/.agents/skills/learn", "install": ["npx skills add todoist/todoist-cli --skill learn"], "stars": 332, "pushed": "2026-11-12T09:40:19Z", "license": "MIT", "plat": "todoist-cli", "live": "Not checked (runs locally)"}, {"id": "skill:todoist/todoist-cli/.agents/skills/review-changes", "name": "review-changes", "kind": "skill", "official": false, "desc": "Reviews a finished change with fresh reviewers (a task review, a blast-radius review for shared code, and Doistbot or per-check subagents), then confirms each finding before acting on it. Use when the owner says a change is \"ready for a PR\", \"ready to merge\" or ready for a release, or asks for \"a review\".", "repo": "https://github.com/todoist/todoist-cli/tree/HEAD/.agents/skills/review-changes", "install": ["npx skills add todoist/todoist-cli --skill review-changes"], "stars": 332, "pushed": "2026-11-12T09:40:19Z", "license": "MIT", "plat": "todoist-cli", "live": "Not checked (runs locally)"}, {"id": "skill:todoist/todoist-cli/.agents/skills/verify", "name": "verify", "kind": "skill", "official": false, "desc": "Proves a change works before it is called done, and reports the evidence on a ladder from \"said\" to \"ran\". Use when you are about to say \"done\", \"fixed\", \"works\" or \"ready\", when asked to check or test a change, or before opening a pull request.", "repo": "https://github.com/todoist/todoist-cli/tree/HEAD/.agents/skills/verify", "install": ["npx skills add todoist/todoist-cli --skill verify"], "stars": 332, "pushed": "2026-11-12T09:40:19Z", "license": "MIT", "plat": "todoist-cli", "live": "Not checked (runs locally)"}, {"id": "skill:todoist/todoist-cli/.agents/skills/write-tests", "name": "write-tests", "kind": "skill", "official": false, "desc": "Writes or changes tests in this repository to its quality bar, with the right helpers and layer. Use when adding, fixing or reviewing tests, when a change \"needs a test\", or when deciding whether a test may change.", "repo": "https://github.com/todoist/todoist-cli/tree/HEAD/.agents/skills/write-tests", "install": ["npx skills add todoist/todoist-cli --skill write-tests"], "stars": 332, "pushed": "2026-11-12T09:40:19Z", "license": "MIT", "plat": "todoist-cli", "live": "Not checked (runs locally)"}, {"id": "mcp:com.postman/postman-mcp-server", "name": "Postman MCP Server", "kind": "mcp", "official": null, "desc": "Give your AI agents trusted access to the full Postman platform.", "repo": "https://github.com/postmanlabs/postman-mcp-server", "install": ["npm:@postman/postman-mcp-server", "mcpb:https://github.com/postmanlabs/postman-mcp-server/releases/download/v2.15.0/postman-mcp-server-minimal.mcpb", "mcpb:https://github.com/postmanlabs/postman-mcp-server/releases/download/v2.15.0/postman-mcp-server-full.mcpb", "mcpb:https://github.com/postmanlabs/postman-mcp-server/releases/download/v2.15.0/postman-mcp-server-code.mcpb", "mcpb:https://github.com/postmanlabs/postman-mcp-server/releases/download/v2.15.0/postman-mcp-server-learn.mcpb", "https://mcp.postman.com/mcp", "https://mcp.postman.com/minimal", "https://mcp.eu.postman.com/mcp", "https://mcp.eu.postman.com/minimal"], "stars": 329, "pushed": "2026-11-12T16:28:37Z", "license": "Apache-2.0", "plat": "postman", "live": "Not checked (runs locally)"}, {"id": "skill:qshanx/docs-governance/skills/engineering/change-impact", "name": "change-impact", "kind": "skill", "official": false, "desc": "在改代码、数据、接口或治理文档前做有证据的影响分析，并在实施后把计划影响与实际 diff 对照；覆盖代码调用、数据/Schema、API 契约、测试、文档、ADR、部署、迁移和回滚。用于跨模块修改、高风险变更、数据库迁移、认证、公共接口、用户问“会影响哪里”“改之前检查一下”或实施后需要反思偏差时。English triggers: change impact analysis, blast radius, pre-change analysis, migration impact, rollback plan, post-implementation alignment.", "repo": "https://github.com/qshanx/docs-governance/tree/HEAD/skills/engineering/change-impact", "install": ["npx skills add qshanx/docs-governance --skill change-impact"], "stars": 326, "pushed": "2026-10-29T00:20:20Z", "license": "MIT", "plat": "变更影响分析", "live": "Not checked (runs locally)"}, {"id": "skill:qshanx/docs-governance/skills/engineering/loop-design-check", "name": "loop-design-check", "kind": "skill", "official": false, "desc": "把一个任务\"写成\"一个目标导向的 loop，并\"检查\"这个 loop 写得对不对、会不会跑飞——防止空转烧钱 / Goodhart 作弊 / 把错的干到底。两个动作：① 写 loop（先做减法判该不该建 → 定可判定目标 → 选回路类型 → 选骨架）② 体检 loop（过五个崩法 + 可判定性 + 边界 + 降级 + judge 独立 + 判断留人红线）。中文触发：写 loop、设计 loop、做一个 loop、把任务变 loop、agent 自动循环、检查 loop 对不对、loop 体检、loop 会不会跑飞、loop 空转烧钱、loop 作弊、目标导向循环、可判定目标、五个崩法、plan build judge、文档驱动派活、该不该建 loop。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent runaway loop, goal-oriented loop, decidable goal, plan build judge.", "repo": "https://github.com/qshanx/docs-governance/tree/HEAD/skills/engineering/loop-design-check", "install": ["npx skills add qshanx/docs-governance --skill loop-design-check"], "stars": 326, "pushed": "2026-10-29T00:20:20Z", "license": "MIT", "plat": "循环设计检查", "live": "Not checked (runs locally)"}, {"id": "skill:qshanx/docs-governance/skills/engineering/module-regression", "name": "module-regression", "kind": "skill", "official": false, "desc": "大项目模块间联动回归——一份 REGRESSION.md 回归台账登记\"每个模块的下游消费者 + 可执行的回归验收命令\"，跨模块行为或依赖变化后按受影响范围回归，防\"改一个模块悄悄弄坏其他模块\"。判决靠退出码，不靠 AI 看着没问题。中文触发：模块回归、回归台账、回归审计、改A坏B、模块联动检查、影响面检查、模块牵连、下游验证、大项目改动检查。English triggers: module regression, regression ledger, impact regression audit, downstream verification.", "repo": "https://github.com/qshanx/docs-governance/tree/HEAD/skills/engineering/module-regression", "install": ["npx skills add qshanx/docs-governance --skill module-regression"], "stars": 326, "pushed": "2026-10-29T00:20:20Z", "license": "MIT", "plat": "模块回归测试", "live": "Not checked (runs locally)"}, {"id": "skill:qshanx/docs-governance/skills/engineering/test-collaboration", "name": "test-collaboration", "kind": "skill", "official": false, "desc": "盘点并维护项目测试资产，按真实测试入口和重要覆盖变化维护 TESTS.md，必要时使用 TEST-ID 关联证据。用于测试资产盘点、测试缺口分析、单元/集成/契约/E2E/冒烟分类、Bug 回归保护、前后端或多服务基于同一契约的消费者/提供者测试、测试必要性判断、测试清单维护与交付前测试证据审查。中文触发：测试盘点、测试清单、测试资产、测试缺口、测试必要性、Bug 转测试、契约测试、前后端接口测试、测试治理。English triggers: test inventory, test catalog, test gap analysis, bug-to-test, contract testing, consumer contract, provider verification, test governance.", "repo": "https://github.com/qshanx/docs-governance/tree/HEAD/skills/engineering/test-collaboration", "install": ["npx skills add qshanx/docs-governance --skill test-collaboration"], "stars": 326, "pushed": "2026-10-29T00:20:20Z", "license": "MIT", "plat": "测试资产管理", "live": "Not checked (runs locally)"}, {"id": "skill:web-infra-dev/midscene-skills/skills/vitest-midscene-e2e", "name": "vitest-midscene-e2e", "kind": "skill", "official": false, "desc": "Enhances Vitest with Midscene for AI-powered UI testing across Web (Playwright), Android (ADB), and iOS (WDA). Scaffolds new projects, converts existing projects, and creates/updates/debugs/runs E2E tests using natural-language UI interactions. Triggers: write test, add test, create test, update test, fix test, debug test, run test, e2e test, midscene test, new project, convert project, init project, 写测试, 加测试, 创建测试, 更新测试, 修复测试, 调试测试, 运行测试, 新建工程, 转化工程.", "repo": "https://github.com/web-infra-dev/midscene-skills/tree/HEAD/skills/vitest-midscene-e2e", "install": ["npx skills add web-infra-dev/midscene-skills --skill vitest-midscene-e2e"], "stars": 323, "pushed": "2026-11-05T07:45:07Z", "license": "MIT", "plat": "vitest", "live": "Not checked (runs locally)"}, {"id": "skill:antithesishq/antithesis-skills/antithesis-feature-workload", "name": "antithesis-feature-workload", "kind": "skill", "official": false, "desc": "Design and build an Antithesis workload for a specific feature: analyze the feature, discover its testable properties, build a self-driving workload that runs locally and in Antithesis, and iterate until the feature's behaviors are exercised and its invariants are checked.", "repo": "https://github.com/antithesishq/antithesis-skills/tree/HEAD/antithesis-feature-workload", "install": ["npx skills add antithesishq/antithesis-skills --skill antithesis-feature-workload"], "stars": 312, "pushed": "2026-11-12T22:52:18Z", "license": "Apache-2.0", "plat": "antithesis", "live": "Not checked (runs locally)"}, {"id": "skill:antithesishq/antithesis-skills/antithesis-mutation-testing", "name": "antithesis-mutation-testing", "kind": "skill", "official": false, "desc": "Validate that an Antithesis property catalog can actually catch bugs. For each safety property, inject one realistic mutant into the SUT, run it, and confirm the targeted property fires. Diagnoses survivors as a bad mutant, bad oracle, bad workload, or bad property, and routes fixes back to the antithesis plugin's workload module or antithesis-research. Use once the harness is built and a baseline run is green.", "repo": "https://github.com/antithesishq/antithesis-skills/tree/HEAD/antithesis-mutation-testing", "install": ["npx skills add antithesishq/antithesis-skills --skill antithesis-mutation-testing"], "stars": 312, "pushed": "2026-11-12T22:52:18Z", "license": "Apache-2.0", "plat": "antithesis", "live": "Not checked (runs locally)"}, {"id": "skill:antithesishq/antithesis-skills/antithesis-research", "name": "antithesis-research", "kind": "skill", "official": false, "desc": "Analyze a codebase to figure out how it should be tested with Antithesis: map the system, identify failure-prone areas and testable properties, and produce the research artifacts needed for workload and environment planning.", "repo": "https://github.com/antithesishq/antithesis-skills/tree/HEAD/antithesis-research", "install": ["npx skills add antithesishq/antithesis-skills --skill antithesis-research"], "stars": 312, "pushed": "2026-11-12T22:52:18Z", "license": "Apache-2.0", "plat": "antithesis", "live": "Not checked (runs locally)"}, {"id": "skill:antithesishq/antithesis-skills/antithesis-review-inputs", "name": "antithesis-review-inputs", "kind": "skill", "official": false, "desc": "Review a workload's input generation for state space exploration: how well it uses randomness to drive the system under test into diverse regions of behavior.", "repo": "https://github.com/antithesishq/antithesis-skills/tree/HEAD/antithesis-review-inputs", "install": ["npx skills add antithesishq/antithesis-skills --skill antithesis-review-inputs"], "stars": 312, "pushed": "2026-11-12T22:52:18Z", "license": "Apache-2.0", "plat": "antithesis", "live": "Not checked (runs locally)"}, {"id": "skill:arcee-ai/nac/.agents/skills/qa", "name": "qa", "kind": "skill", "official": false, "desc": "Run scalable, isolated live QA for nac development. In NAC orchestrator mode the top-level local orchestrator must parse n (default 4), dispatch one setup worker with this skill, copy its n assignment contracts verbatim into exactly n parallel test workers with this skill, then dispatch one aggregate worker with this skill using all test episodes; setup selects or creates a clean worktree for the requested revision, every phase changes to that worktree, slots and paths stay immutable after setup", "repo": "https://github.com/arcee-ai/nac/tree/HEAD/.agents/skills/qa", "install": ["npx skills add arcee-ai/nac --skill qa"], "stars": 312, "pushed": "2026-11-12T23:54:31Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:nurettincoban/ai-prd-workflow/skills/review-rfc", "name": "review-rfc", "kind": "skill", "official": false, "desc": "Review an implemented RFC in a fresh context against its acceptance criteria, RULES.md and the test plan, and save the review to reviews/.", "repo": "https://github.com/nurettincoban/ai-prd-workflow/tree/HEAD/skills/review-rfc", "install": ["npx skills add nurettincoban/ai-prd-workflow --skill review-rfc"], "stars": 310, "pushed": "2026-10-08T15:19:40Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:nurettincoban/ai-prd-workflow/skills/test-strategy", "name": "test-strategy", "kind": "skill", "official": false, "desc": "Write TEST-STRATEGY.md, a test plan per RFC, before the tests are written.", "repo": "https://github.com/nurettincoban/ai-prd-workflow/tree/HEAD/skills/test-strategy", "install": ["npx skills add nurettincoban/ai-prd-workflow --skill test-strategy"], "stars": 310, "pushed": "2026-10-08T15:19:40Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:akitaonrails/my-skills/release-smoke-test", "name": "release-smoke-test", "kind": "skill", "official": false, "desc": "Test an oh-my-opencode-slim release candidate or bugfix before publishing. Use when validating a packed plugin artifact, release branch, crash fix, OpenCode runtime compatibility, or model-specific smoke test such as OpenCode 1.17.11 message transform regressions.", "repo": "https://github.com/akitaonrails/my-skills/tree/HEAD/release-smoke-test", "install": ["npx skills add akitaonrails/my-skills --skill release-smoke-test"], "stars": 304, "pushed": "2026-10-31T23:46:39Z", "license": null, "plat": "release-smoke-test", "live": "Not checked (runs locally)"}, {"id": "skill:akitaonrails/my-skills/verification-planning", "name": "verification-planning", "kind": "skill", "official": false, "desc": "Verification planning for non-trivial coding work. Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change that needs a credible project-specific evidence path.", "repo": "https://github.com/akitaonrails/my-skills/tree/HEAD/verification-planning", "install": ["npx skills add akitaonrails/my-skills --skill verification-planning"], "stars": 304, "pushed": "2026-10-31T23:46:39Z", "license": null, "plat": "verification-planning", "live": "Not checked (runs locally)"}, {"id": "skill:joshuadavidthomas/opencode-agent-skills/.opencode/skills/test-skill", "name": "test-skill", "kind": "skill", "official": false, "desc": "A test skill to verify all plugin tools work correctly - use_skill, read_skill_file, run_skill_script, find_skills", "repo": "https://github.com/joshuadavidthomas/opencode-agent-skills/tree/HEAD/.opencode/skills/test-skill", "install": ["npx skills add joshuadavidthomas/opencode-agent-skills --skill test-skill"], "stars": 287, "pushed": "2026-11-04T07:54:46Z", "license": "MIT", "plat": "plugin tools", "live": "Not checked (runs locally)"}, {"id": "skill:billy-enrizky/openbrowser-ai/plugin/skills/e2e-testing", "name": "e2e-testing", "kind": "skill", "official": false, "desc": "Test web applications end-to-end by simulating user interactions and verifying expected outcomes. Trigger when the user asks to: test a web app, verify a user flow, run end-to-end tests, QA a feature, check that a page works correctly, validate user journeys, or test a deployment.", "repo": "https://github.com/billy-enrizky/openbrowser-ai/tree/HEAD/plugin/skills/e2e-testing", "install": ["npx skills add billy-enrizky/openbrowser-ai --skill e2e-testing"], "stars": 280, "pushed": "2026-09-28T05:43:28Z", "license": "MIT", "plat": "web applications", "live": "Not checked (runs locally)"}, {"id": "skill:intercom/2x-skills/plugins/test-tools/skills/fix-flaky-tests", "name": "fix-flaky-tests", "kind": "skill", "official": false, "desc": "Investigate and fix flaky or intermittently-failing tests in any framework and CI system — detects the framework, CI provider, and app profile, then applies the matching classification and fix patterns. Triggers on a flaky-test issue or CI URL, a test that \"passes on retry\" or \"fails in CI but passes locally\", a bot that skipped a test, or a request to reopen or dispute the closure or diagnosis of a flaky-test issue (for that case open the issue first; its title or label confirms scope even when", "repo": "https://github.com/intercom/2x-skills/tree/HEAD/plugins/test-tools/skills/fix-flaky-tests", "install": ["npx skills add intercom/2x-skills --skill fix-flaky-tests"], "stars": 277, "pushed": "2026-11-11T13:07:30Z", "license": "MIT", "plat": "ci systems", "live": "Not checked (runs locally)"}, {"id": "skill:fugazi/test-automation-skills-agents/skills/api-testing", "name": "api-testing", "kind": "skill", "official": false, "desc": "Test REST and GraphQL endpoint contracts using Playwright request fixture (TypeScript) or REST Assured (Java). Use for standalone API tests covering schemas, auth, status/error handling, pagination, idempotency, rate limits, or contract checks; not for browser E2E specs. Keywords: REST, GraphQL, API contract, schema validation, REST Assured.", "repo": "https://github.com/fugazi/test-automation-skills-agents/tree/HEAD/skills/api-testing", "install": ["npx skills add fugazi/test-automation-skills-agents --skill api-testing"], "stars": 264, "pushed": "2026-11-09T22:42:23Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:fugazi/test-automation-skills-agents/skills/grill-me-qa", "name": "grill-me-qa", "kind": "skill", "official": false, "desc": "A guided interview to challenge and validate QA automation plans, test strategies, and framework designs before implementation. Use when the user wants to validate a test architecture, challenge a testing decision, prepare an AI-assisted testing rollout, or uses any \"grill\" trigger phrase (grill my test plan, audit my QA automation framework, challenge my QA strategy, review my test architecture).", "repo": "https://github.com/fugazi/test-automation-skills-agents/tree/HEAD/skills/grill-me-qa", "install": ["npx skills add fugazi/test-automation-skills-agents --skill grill-me-qa"], "stars": 264, "pushed": "2026-11-09T22:42:23Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:fugazi/test-automation-skills-agents/skills/playwright-e2e-testing", "name": "playwright-e2e-testing", "kind": "skill", "official": false, "desc": "Author and maintain versioned Playwright (@playwright/test) TypeScript UI specs for browser user flows. Use when asked to create, run, debug, or refactor E2E tests, form/navigation/auth flows, responsive checks, UI mocking, fixtures, Page Objects, or visual comparisons. Use api-testing for standalone REST/GraphQL contracts and playwright-cli for live browser sessions. Keywords: E2E spec, Playwright test, POM, fixtures, UI regression.", "repo": "https://github.com/fugazi/test-automation-skills-agents/tree/HEAD/skills/playwright-e2e-testing", "install": ["npx skills add fugazi/test-automation-skills-agents --skill playwright-e2e-testing"], "stars": 264, "pushed": "2026-11-09T22:42:23Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:fugazi/test-automation-skills-agents/skills/playwright-regression-testing", "name": "playwright-regression-testing", "kind": "skill", "official": false, "desc": "Govern Playwright TypeScript regression suites across many tests. Use when asked to plan, select, tier, execute, or optimize suites with risk/change analysis, tags, CI/CD, sharding, flaky-test management, or suite-health metrics; not for authoring one UI spec. Keywords: regression strategy, smoke tests, test selection, CI pipeline, flaky tests, test sharding, impact analysis, git diff.", "repo": "https://github.com/fugazi/test-automation-skills-agents/tree/HEAD/skills/playwright-regression-testing", "install": ["npx skills add fugazi/test-automation-skills-agents --skill playwright-regression-testing"], "stars": 264, "pushed": "2026-11-09T22:42:23Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:fugazi/test-automation-skills-agents/skills/qa-investigation", "name": "qa-investigation", "kind": "skill", "official": false, "desc": "Investigate a specific test failure to its root cause and document the why. Detects whether a failing test is flaky (intermittent) or a deterministic bug during reproduction. Use when a test fails and you need the real cause, not just to make it green. Execution layer, not strategy review. Keywords: flaky test, intermittent failure, debugging tests, root cause analysis, test failure triage, bug hunt, why does this test fail.", "repo": "https://github.com/fugazi/test-automation-skills-agents/tree/HEAD/skills/qa-investigation", "install": ["npx skills add fugazi/test-automation-skills-agents --skill qa-investigation"], "stars": 264, "pushed": "2026-11-09T22:42:23Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:fugazi/test-automation-skills-agents/skills/qa-manual-istqb", "name": "qa-manual-istqb", "kind": "skill", "official": false, "desc": "Create QA artifacts from requirements: test plans, test conditions/cases, bug reports, regression suites, traceability, and exploratory charters. Use for test planning, test design, defects, coverage, or QA deliverables. Applies ISTQB risk-based techniques and loads templates only when needed. Keywords: test plan, test case, bug report, traceability, regression suite, QA artifact.", "repo": "https://github.com/fugazi/test-automation-skills-agents/tree/HEAD/skills/qa-manual-istqb", "install": ["npx skills add fugazi/test-automation-skills-agents --skill qa-manual-istqb"], "stars": 264, "pushed": "2026-11-09T22:42:23Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:fugazi/test-automation-skills-agents/skills/webapp-selenium-testing", "name": "webapp-selenium-testing", "kind": "skill", "official": false, "desc": "Author and maintain versioned Selenium WebDriver tests with Java and JUnit 5. Use for creating, debugging, or running Selenium specs, implementing Page Objects, handling explicit waits, capturing screenshots, or setting up Maven test projects. Supports Chrome, Firefox, and Edge. Keywords: Selenium WebDriver, Java, JUnit 5, Page Object Model, explicit waits, Maven, screenshots.", "repo": "https://github.com/fugazi/test-automation-skills-agents/tree/HEAD/skills/webapp-selenium-testing", "install": ["npx skills add fugazi/test-automation-skills-agents --skill webapp-selenium-testing"], "stars": 264, "pushed": "2026-11-09T22:42:23Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:NiazMorshed2007/jev-review", "name": "jev-review", "kind": "mcp", "official": null, "desc": "Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.", "repo": "https://github.com/NiazMorshed2007/jev-review", "install": [], "stars": 253, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.PramodDutta/qaskills", "name": "io.github.PramodDutta/qaskills", "kind": "mcp", "official": null, "desc": "Search, inspect, and install 400+ QA testing skills from qaskills.sh into any MCP client.", "repo": "https://github.com/PramodDutta/qaskills", "install": ["npm:@qaskills/mcp"], "stars": 248, "pushed": "2026-11-03T05:21:20Z", "license": "MIT", "plat": "mcp client", "live": "Not checked (runs locally)"}, {"id": "skill:workersio/skills/plugins/wio/skills/wio", "name": "wio", "kind": "skill", "official": false, "desc": "Testing workflow skill for finding high-value test candidates, writing focused tests, generating realistic workloads, reviewing test value, and diagnosing test-suite health. Use for prompts about what to test next, adding or improving tests, reviewing whether a test is worth keeping, low-signal or flaky tests, workload scenarios, or test-suite trust. Do not use for general QA discussion unless the user wants a concrete testing workflow or artifact.", "repo": "https://github.com/workersio/skills/tree/HEAD/plugins/wio/skills/wio", "install": ["npx skills add workersio/skills --skill wio"], "stars": 244, "pushed": "2026-07-31T12:11:36Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:coralogix/cx-cli/.claude/skills/run-tests", "name": "run-tests", "kind": "skill", "official": false, "desc": "Use this skill when the user asks to \"run tests\", \"test this\", \"check if tests pass\", \"cargo test\", \"run clippy\", \"lint this\", \"check formatting\", \"cargo fmt\", \"CI checks\", \"verify changes\", \"does this pass tests\", \"run the full check\", \"pre-commit check\", or wants to verify that code changes are correct. Use this even when the user says something like \"make sure this works\" or \"check for issues\" in the context of code changes.", "repo": "https://github.com/coralogix/cx-cli/tree/HEAD/.claude/skills/run-tests", "install": ["npx skills add coralogix/cx-cli --skill run-tests"], "stars": 243, "pushed": "2026-11-13T08:06:44Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:Zhen-Bo/smell-check", "name": "smell-check", "kind": "skill", "official": false, "desc": "Runs a smell-first audit on a user-chosen path set: measures structure metrics, applies a named size profile, and reports code smells and test smells with evidence strength. Use for smell audit, code smell scan, whole-repo audit, tech debt scan, test smell check, maintainability audit, or duplication and nesting checks. Do not use for PR review, merge advice, implementing fixes, writing new features, or lint/format-only passes.", "repo": "https://github.com/Zhen-Bo/smell-check", "install": ["npx skills add Zhen-Bo/smell-check --skill smell-check"], "stars": 241, "pushed": "2026-08-29T22:40:42Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:johnku2011/boilerplates-with-ai-skills/shared/workflows/bwai-delivery/skills/bwai-delivery", "name": "bwai-delivery", "kind": "skill", "official": false, "desc": "Use when implementing approved work in a bwai-scaffolded project — follow TDD and stack skills from .bwai/skills/ after planning is complete.", "repo": "https://github.com/johnku2011/boilerplates-with-ai-skills/tree/HEAD/shared/workflows/bwai-delivery/skills/bwai-delivery", "install": ["npx skills add johnku2011/boilerplates-with-ai-skills --skill bwai-delivery"], "stars": 239, "pushed": "2026-08-24T15:57:37Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:johnku2011/boilerplates-with-ai-skills/shared/skills/test-driven-development", "name": "test-driven-development", "kind": "skill", "official": false, "desc": "Use when implementing a feature or fixing a bug — TDD, red-green-refactor, failing test first, then minimal code, then refactor. Run npm test before claiming done.", "repo": "https://github.com/johnku2011/boilerplates-with-ai-skills/tree/HEAD/shared/skills/test-driven-development", "install": ["npx skills add johnku2011/boilerplates-with-ai-skills --skill test-driven-development"], "stars": 239, "pushed": "2026-08-24T15:57:37Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:openqa-cn/codexqa/skills/codexqa-testdata-generator/references/case-data-material-planner", "name": "case-data-material-planner", "kind": "skill", "official": false, "desc": "Prepares executable case preconditions and case-executable.md from a requirement or written cases. Internal case-material engine; enter through codexqa-testdata-generator so SKILL_DIR and adapters resolve.", "repo": "https://github.com/openqa-cn/codexqa/tree/HEAD/skills/codexqa-testdata-generator/references/case-data-material-planner", "install": ["npx skills add openqa-cn/codexqa --skill case-data-material-planner"], "stars": 238, "pushed": "2026-11-06T11:55:53Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:openqa-cn/codexqa/skills/codexqa-change-analysis", "name": "codexqa-change-analysis", "kind": "skill", "official": false, "desc": "Change-impact analysis for one diff: use CodexQA diff indexing (`index --diff-base` tags nodes and files `add` / `change` / `delete`, then `change-groups` / `symbol-diff` / `file-base`) to write one HTML report (affected entries, changed methods, test plan, coverage verdict, sensitive paths) and add runnable test files in the analyzed repo for uncovered points (add only; do not edit existing test files). Use when the user mentions change impact, change analysis, blast radius, affected entries, a", "repo": "https://github.com/openqa-cn/codexqa/tree/HEAD/skills/codexqa-change-analysis", "install": ["npx skills add openqa-cn/codexqa --skill codexqa-change-analysis"], "stars": 238, "pushed": "2026-11-06T11:55:53Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:openqa-cn/codexqa/skills/codexqa-code-analyzer", "name": "codexqa-code-analyzer", "kind": "skill", "official": false, "desc": "Queries a local CodexQA symbol graph for change review, regression scope, test gaps, error location, and entry risk. Use when the user mentions codexqa-code-analyzer, code-analyzer, codexqa, 符号图, 代码知识图谱, 建索引, 查调用, 影响面, --diff-base, 变更审查, 回归范围, 测试缺口, or asks to install / run the codexqa CLI (index, query). Former skill name: code-analyzer. Not CodexQA evidence-pack HTML review (that is codexqa-code-reviewer), not SAST + Agent LLM Detection code-risk scan reports (that is codexqa-defect-analyzer),", "repo": "https://github.com/openqa-cn/codexqa/tree/HEAD/skills/codexqa-code-analyzer", "install": ["npx skills add openqa-cn/codexqa --skill codexqa-code-analyzer"], "stars": 238, "pushed": "2026-11-06T11:55:53Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:openqa-cn/codexqa/skills/codexqa-code-reviewer", "name": "codexqa-code-reviewer", "kind": "skill", "official": false, "desc": "Graph-evidence AI code review (codexqa-code-reviewer) for ANY language repo using ONLY the CodexQA CLI symbol graph (call chains, classes, methods, configs, blast radius, test edges), then an order-16 Agent LLM judgment pass by the host agent's embedded model with deterministic dedupe/merge against heuristic findings. Use when the user asks for codexqa-code-reviewer (former name ai-code-reviewer), code review, PR review, 代码评审, impact analysis, 影响面, regression scope, test gaps, full-repo health r", "repo": "https://github.com/openqa-cn/codexqa/tree/HEAD/skills/codexqa-code-reviewer", "install": ["npx skills add openqa-cn/codexqa --skill codexqa-code-reviewer"], "stars": 238, "pushed": "2026-11-06T11:55:53Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:openqa-cn/codexqa/skills/codexqa-rootcause-analyzer", "name": "codexqa-rootcause-analyzer", "kind": "skill", "official": false, "desc": "Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis. Use when the user mentions codexqa-rootcause-analyzer, exception RCA, crash analysis, AI code diagnosis, stack diagnosis, 异常根因, 堆栈诊断, 崩溃分析, 异常诊断, or asks to turn an exception into a root-cause report. Not structure/impact analysis (that is codexqa-code-analyzer), not SAST + Agent LLM Detection code-risk scan reports (that is codexqa-defect-analyzer), and", "repo": "https://github.com/openqa-cn/codexqa/tree/HEAD/skills/codexqa-rootcause-analyzer", "install": ["npx skills add openqa-cn/codexqa --skill codexqa-rootcause-analyzer"], "stars": 238, "pushed": "2026-11-06T11:55:53Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:openqa-cn/codexqa/skills/codexqa-testcase-generator", "name": "codexqa-testcase-generator", "kind": "skill", "official": false, "desc": "Generates test plans and test cases from local requirements for APP, Web, and server. Use when the user wants a test plan, test analysis, test design, write cases, both plan and cases, PRD-based testing, pre-submit case edits, post-submit incremental, PR/git regression, or says 测试方案、测试分析、测试设计、测试计划、只要方案、写用例、出用例、只要用例、方案和用例都要、按 PRD 出测试、提测前改用例、提测后增量、按 PR 或 git 补回归用例、帮我出测试、补测试、做一轮测试设计. Do not switch to other case-generation, knowledge-retrieval, or generic writing skills even if unnamed. Input is loc", "repo": "https://github.com/openqa-cn/codexqa/tree/HEAD/skills/codexqa-testcase-generator", "install": ["npx skills add openqa-cn/codexqa --skill codexqa-testcase-generator"], "stars": 238, "pushed": "2026-11-06T11:55:53Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:openqa-cn/codexqa/skills/codexqa-testdata-generator", "name": "codexqa-testdata-generator", "kind": "skill", "official": false, "desc": "Constructs test data against real backends and writes it back into test cases as executable preconditions. Use whenever the user wants test data built, case materials or preconditions prepared, a data-build skill or tool reused, an API discovered, a construction script written, or a proven method recorded — including Chinese phrasings such as 构造测试数据, 准备测试数据, 造数据, 用例数据, 用例物料, 用例数据准备, 用例前置数据, 测试数据回写, 测试物料清单, 数据需求分析. Also use it for concrete requests that never say \"test data\", like \"create this ac", "repo": "https://github.com/openqa-cn/codexqa/tree/HEAD/skills/codexqa-testdata-generator", "install": ["npx skills add openqa-cn/codexqa --skill codexqa-testdata-generator"], "stars": 238, "pushed": "2026-11-06T11:55:53Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:openqa-cn/codexqa/skills/codexqa-testdata-generator/slot-scaffolder", "name": "slot-scaffolder", "kind": "skill", "official": false, "desc": "Generate a domain data-build slot from OpenAPI files: new business-domain pack, scaffold a data-build skill, or add an enterprise custom domain. Internal helper of the parent pack; reach this through codexqa-testdata-generator.", "repo": "https://github.com/openqa-cn/codexqa/tree/HEAD/skills/codexqa-testdata-generator/slot-scaffolder", "install": ["npx skills add openqa-cn/codexqa --skill slot-scaffolder"], "stars": 238, "pushed": "2026-11-06T11:55:53Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:artwist-polyakov/polyakov-claude-skills/plugins/codex-review/skills/codex-review", "name": "codex-review", "kind": "skill", "official": false, "desc": "Workflow кросс-агентного ревью с Codex. Triggers (RU): \"кодекс ревью\". Triggers (EN): \"with codex review\", \"codex review workflow\", \"start codex review\". ВАЖНО: при срабатывании триггера прочитай SKILL.md до любых других шагов.", "repo": "https://github.com/artwist-polyakov/polyakov-claude-skills/tree/HEAD/plugins/codex-review/skills/codex-review", "install": ["npx skills add artwist-polyakov/polyakov-claude-skills --skill codex-review"], "stars": 234, "pushed": "2026-11-05T17:29:50Z", "license": "MIT", "plat": "codex", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:jumpstarter-dev/jumpstarter", "name": "jumpstarter", "kind": "mcp", "official": null, "desc": "Hardware testing for the software world. Real or virtual, local or remote, human, automated or agentic.", "repo": "https://github.com/jumpstarter-dev/jumpstarter", "install": [], "stars": 234, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:LichAmnesia/lich-skills/skills/build-until-pass", "name": "build-until-pass", "kind": "skill", "official": false, "desc": "Use when a build, typecheck, lint, or test command is failing and you want the agent to drive it to green on its own — run the check, read the errors, apply the smallest fix, re-run, repeat until exit code 0. Stops the human from being the while-loop (run → read error → fix one line → run again) and stops the agent from bulldozing huge speculative rewrites between checks.", "repo": "https://github.com/LichAmnesia/lich-skills/tree/HEAD/skills/build-until-pass", "install": ["npx skills add LichAmnesia/lich-skills --skill build-until-pass"], "stars": 232, "pushed": "2026-06-09T22:09:24Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:LichAmnesia/lich-skills/skills/debug-hypothesis", "name": "debug-hypothesis", "kind": "skill", "official": false, "desc": "Use when debugging any non-trivial bug — wrong output, crash, flaky test, performance regression, or \"it works locally but not in CI.\" Forces a scientific-method loop (Observe → Hypothesize → Experiment → Conclude) so the agent stops guessing and starts reasoning. Prevents the #1 AI debugging failure mode — bulldozing through a wrong idea instead of falsifying it.", "repo": "https://github.com/LichAmnesia/lich-skills/tree/HEAD/skills/debug-hypothesis", "install": ["npx skills add LichAmnesia/lich-skills --skill debug-hypothesis"], "stars": 232, "pushed": "2026-06-09T22:09:24Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:shenli/distributed-system-testing/skills/designing-distributed-system-tests", "name": "designing-distributed-system-tests", "kind": "skill", "official": false, "desc": "Design claim-driven test plans for distributed or stateful systems with persistence, replication, consensus, retries, idempotency, async messaging, multi-tenancy, or partial failure. Supports change-scoped and project-wide plans, including existing-test inventories and gap analysis. Use for stability, release-validation, durability, partition, crash-recovery, upgrade, linearizability, deterministic-simulation, SQL semantics or compatibility, tenant isolation, authz, namespace boundaries, fairnes", "repo": "https://github.com/shenli/distributed-system-testing/tree/HEAD/skills/designing-distributed-system-tests", "install": ["npx skills add shenli/distributed-system-testing --skill designing-distributed-system-tests"], "stars": 231, "pushed": "2026-11-10T17:48:26Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:shenli/distributed-system-testing/skills/executing-distributed-system-tests", "name": "executing-distributed-system-tests", "kind": "skill", "official": false, "desc": "Use when running a previously designed distributed-systems test plan against a real or simulated cluster — driving fault injection, workload, chaos scenarios, linearizability / consistency runs, durability, partition, crash-recovery, upgrade, performance/SLO runs, tenant isolation runs, boundary or authz runs, fairness / noisy-neighbor runs, or release validation. Also use when asked to \"execute the plan\", \"reproduce a distributed bug\", \"run stability tests\", \"drive chaos\", \"validate a release e", "repo": "https://github.com/shenli/distributed-system-testing/tree/HEAD/skills/executing-distributed-system-tests", "install": ["npx skills add shenli/distributed-system-testing --skill executing-distributed-system-tests"], "stars": 231, "pushed": "2026-11-10T17:48:26Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:antopolskiy/kanban-md/.agents/skills/test-kanban-md", "name": "test-kanban-md", "kind": "skill", "official": false, "desc": "Plan and run verification for kanban-md changes, including test-driven bug fixes, Go package tests, CLI end-to-end tests, TUI behavior and snapshots, lint, and precommit checks. Use when implementing or reviewing a change, fixing a bug, adding tests, updating snapshots, or deciding what evidence is required. Do not use as the source of release or schema-migration policy.", "repo": "https://github.com/antopolskiy/kanban-md/tree/HEAD/.agents/skills/test-kanban-md", "install": ["npx skills add antopolskiy/kanban-md --skill test-kanban-md"], "stars": 231, "pushed": "2026-10-05T20:52:24Z", "license": "MIT", "plat": "kanban-md", "live": "Not checked (runs locally)"}, {"id": "skill:tamdogood/builder-essential-skills/skills/build-scenario-tests", "name": "build-scenario-tests", "kind": "skill", "official": false, "desc": "Inspect an unfamiliar repository, turn a focused Markdown behavior scenario into a deterministic test in the repository's native test stack, run it, and preserve traceability between intent and code. Use when asked to add scenario tests, compile acceptance criteria or Given/When/Then Markdown into executable tests, reproduce a user-visible regression, or convert a narrow workflow specification into stable web, API, CLI, desktop, or mobile interaction coverage. Do not use for broad exploratory jo", "repo": "https://github.com/tamdogood/builder-essential-skills/tree/HEAD/skills/build-scenario-tests", "install": ["npx skills add tamdogood/builder-essential-skills --skill build-scenario-tests"], "stars": 228, "pushed": "2026-08-16T16:30:17Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:tamdogood/builder-essential-skills/skills/run-smoke-tests", "name": "run-smoke-tests", "kind": "skill", "official": false, "desc": "Inspect an unfamiliar repository, interpret a broad Markdown user journey at runtime, operate the real product through its supported web, API, CLI, desktop, or mobile surface, and produce an auditable pass, fail, or blocked judgment with screenshots, logs, recordings, and a step timeline when available. Use when asked to run smoke tests, validate an end-to-end user journey, dogfood a product, test a release candidate, or execute a non-deterministic workflow that may include authentication or hum", "repo": "https://github.com/tamdogood/builder-essential-skills/tree/HEAD/skills/run-smoke-tests", "install": ["npx skills add tamdogood/builder-essential-skills --skill run-smoke-tests"], "stars": 228, "pushed": "2026-08-16T16:30:17Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:dhruvjainin/absolute/skills/absolute-deflake", "name": "absolute-deflake", "kind": "skill", "official": false, "desc": "Flaky test fixes: detect nondeterministic tests empirically (repeat/shuffle/parallel runs), diagnose the root cause, fix it — never retry/skip/sleep — and verify across many randomized runs. Triggers on \"absolute deflake\", \"fix flaky tests\", \"CI is flaky\", \"this test fails randomly/intermittently\".", "repo": "https://github.com/dhruvjainin/absolute/tree/HEAD/skills/absolute-deflake", "install": ["npx skills add dhruvjainin/absolute --skill absolute-deflake"], "stars": 223, "pushed": "2026-10-26T12:48:58Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:wellwelwel/lagune/.claude/skills/calibrate", "name": "calibrate", "kind": "skill", "official": false, "desc": "Confronts every block, warning, and piece of noise a change raises with the false positives real projects trigger, measured on this tree's build, then gives a verdict and the calibration each case needs.", "repo": "https://github.com/wellwelwel/lagune/tree/HEAD/.claude/skills/calibrate", "install": ["npx skills add wellwelwel/lagune --skill calibrate"], "stars": 216, "pushed": "2026-11-12T20:03:45Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:ertugrul-dmr/clean-code-skills/skills/python/clean-tests", "name": "clean-tests", "kind": "skill", "official": false, "desc": "Use when writing, fixing, editing, or refactoring Python tests. Enforces Clean Code principles—fast tests, boundary coverage, one assert per test.", "repo": "https://github.com/ertugrul-dmr/clean-code-skills/tree/HEAD/skills/python/clean-tests", "install": ["npx skills add ertugrul-dmr/clean-code-skills --skill clean-tests"], "stars": 216, "pushed": "2026-04-21T08:49:42Z", "license": "MIT", "plat": "python", "live": "Not checked (runs locally)"}, {"id": "skill:ertugrul-dmr/clean-code-skills/skills/typescript/clean-tests", "name": "clean-tests", "kind": "skill", "official": false, "desc": "Use when writing, fixing, editing, or refactoring TypeScript tests. Enforces Clean Code principles—fast tests, boundary coverage, one assert per test.", "repo": "https://github.com/ertugrul-dmr/clean-code-skills/tree/HEAD/skills/typescript/clean-tests", "install": ["npx skills add ertugrul-dmr/clean-code-skills --skill clean-tests"], "stars": 216, "pushed": "2026-04-21T08:49:42Z", "license": "MIT", "plat": "typescript", "live": "Not checked (runs locally)"}, {"id": "skill:OutThisLife/brooklyn-skills/skills/perf", "name": "perf", "kind": "skill", "official": false, "desc": "The general profile-driven perf loop for any language or runtime: baseline, profile, fix the real hot path, re-measure. Use for /perf, \"this is slow\", or optimization work.", "repo": "https://github.com/OutThisLife/brooklyn-skills/tree/HEAD/skills/perf", "install": ["npx skills add OutThisLife/brooklyn-skills --skill perf"], "stars": 215, "pushed": "2026-11-11T05:43:45Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:ab604/claude-code-r-skills/.claude/skills/tdd-workflow", "name": "tdd-workflow", "kind": "skill", "official": false, "desc": "Test-driven development workflow for R using testthat. Use when writing new features, fixing bugs, or refactoring code. Enforces test-first development with 80%+ coverage.", "repo": "https://github.com/ab604/claude-code-r-skills/tree/HEAD/.claude/skills/tdd-workflow", "install": ["npx skills add ab604/claude-code-r-skills --skill tdd-workflow"], "stars": 213, "pushed": "2026-09-17T14:33:38Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:linxuan-sys/opencode-skills-chinese/playwright-cli", "name": "playwright-cli", "kind": "skill", "official": false, "desc": "自动化浏览器交互、测试网页以及处理Playwright测试用例", "repo": "https://github.com/linxuan-sys/opencode-skills-chinese/tree/HEAD/playwright-cli", "install": ["npx skills add linxuan-sys/opencode-skills-chinese --skill playwright-cli"], "stars": 207, "pushed": "2026-10-19T04:34:05Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:linxuan-sys/opencode-skills-chinese/systematic-debugging", "name": "systematic-debugging", "kind": "skill", "official": false, "desc": "在提出修复方案前，遇到任何bug、测试失败或意外行为时使用", "repo": "https://github.com/linxuan-sys/opencode-skills-chinese/tree/HEAD/systematic-debugging", "install": ["npx skills add linxuan-sys/opencode-skills-chinese --skill systematic-debugging"], "stars": 207, "pushed": "2026-10-19T04:34:05Z", "license": "MIT", "plat": "debugging", "live": "Not checked (runs locally)"}, {"id": "skill:tddworks/SkillsManager/.claude/skills/fix-bug", "name": "fix-bug", "kind": "skill", "official": false, "desc": "Guide for fixing bugs in ClaudeBar following Chicago School TDD and rich domain design. Use this skill when: (1) User reports a bug or unexpected behavior (2) Fixing a defect in existing functionality (3) User asks \"fix this bug\" or \"this doesn't work correctly\" (4) Correcting behavior that violates the user's mental model", "repo": "https://github.com/tddworks/SkillsManager/tree/HEAD/.claude/skills/fix-bug", "install": ["npx skills add tddworks/SkillsManager --skill fix-bug"], "stars": 206, "pushed": "2026-05-28T02:46:02Z", "license": null, "plat": "claudebar", "live": "Not checked (runs locally)"}, {"id": "skill:tddworks/SkillsManager/.claude/skills/improvement", "name": "improvement", "kind": "skill", "official": false, "desc": "Guide for making improvements to existing ClaudeBar functionality using TDD. Use this skill when: (1) Enhancing existing features (not adding new ones) (2) Improving UX, performance, or code quality (3) User asks \"improve X\", \"make Y better\", or \"enhance Z\" (4) Small enhancements that don't require full architecture design For NEW features, use implement-feature skill instead.", "repo": "https://github.com/tddworks/SkillsManager/tree/HEAD/.claude/skills/improvement", "install": ["npx skills add tddworks/SkillsManager --skill improvement"], "stars": 206, "pushed": "2026-05-28T02:46:02Z", "license": null, "plat": "claudebar", "live": "Not checked (runs locally)"}, {"id": "skill:mblode/agent-skills/skills/app-verification", "name": "app-verification", "kind": "skill", "official": false, "desc": "Builds and maintains a repo's own verification harness (verify CLI, doctor, worktree isolation, feature map, seed data) and a reproduce-first bug handoff. Use when asked to \"build a verification harness\", \"add a doctor command\", \"prove every feature still works\", or \"reproduce this bug report\".", "repo": "https://github.com/mblode/agent-skills/tree/HEAD/skills/app-verification", "install": ["npx skills add mblode/agent-skills --skill app-verification"], "stars": 201, "pushed": "2026-11-10T23:39:08Z", "license": "MIT", "plat": "verification harness", "live": "Not checked (runs locally)"}, {"id": "skill:mblode/agent-skills/skills/test-audit", "name": "test-audit", "kind": "skill", "official": false, "desc": "Prunes low-value tests across a whole suite to a measured target while holding coverage. Use when asked to \"remove useless tests\", \"prune the test suite\", \"we have too many tests\", \"agents keep writing pointless tests\", or \"cut 20% of tests without losing coverage\".", "repo": "https://github.com/mblode/agent-skills/tree/HEAD/skills/test-audit", "install": ["npx skills add mblode/agent-skills --skill test-audit"], "stars": 201, "pushed": "2026-11-10T23:39:08Z", "license": "MIT", "plat": "testing", "live": "Not checked (runs locally)"}, {"id": "skill:mblode/agent-skills/skills/ui-verification", "name": "ui-verification", "kind": "skill", "official": false, "desc": "Runs scoped browser probes for focus, hit targets, overflow, themes, request failures, and performance attribution, with evidence linked to UI rule IDs, plus an exploratory pass that uses a finished feature like a real user. Use when asked to \"verify this in the browser\", \"reproduce this UI finding\", \"re-measure after the UI fix\", \"review before and after screenshots\", or \"try to break this feature\".", "repo": "https://github.com/mblode/agent-skills/tree/HEAD/skills/ui-verification", "install": ["npx skills add mblode/agent-skills --skill ui-verification"], "stars": 201, "pushed": "2026-11-10T23:39:08Z", "license": "MIT", "plat": "ui", "live": "Not checked (runs locally)"}, {"id": "skill:rodrigohighermind/highermind-code-skills/hm-qa", "name": "hm-qa", "kind": "skill", "official": false, "desc": "Quality assurance que declara baseline-ready (Dev Team), não product-ready (Owner). Use antes do Dev Team entregar pro Owner avaliar. Valida 5 checks obrigatórios (typecheck, lint, smoke test, zero console.error em código novo, zero TODO crítico em código novo) + security quick scan + functional tests + edge cases (forms, streaming, erros, mobile, LLM, concorrência, dados sagrados). Para projetos que persistem dados, complementa com /hm-data-integrity.", "repo": "https://github.com/rodrigohighermind/highermind-code-skills/tree/HEAD/hm-qa", "install": ["npx skills add rodrigohighermind/highermind-code-skills --skill hm-qa"], "stars": 197, "pushed": "2026-06-14T22:39:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:cxuu/golang-skills/skills/go-linting", "name": "go-linting", "kind": "skill", "official": false, "desc": "Use when setting up linting for a Go project, configuring golangci-lint, or adding Go checks to a CI/CD pipeline. Also use when starting a new Go project and deciding which linters to enable, even if the user only asks about \"code quality\" or \"static analysis\" without mentioning specific linter names. Does not cover code review process (see go-code-review).", "repo": "https://github.com/cxuu/golang-skills/tree/HEAD/skills/go-linting", "install": ["npx skills add cxuu/golang-skills --skill go-linting"], "stars": 194, "pushed": "2026-06-20T04:12:05Z", "license": "Apache-2.0", "plat": "go", "live": "Not checked (runs locally)"}, {"id": "skill:cxuu/golang-skills/skills/go-testing", "name": "go-testing", "kind": "skill", "official": false, "desc": "Use when writing, reviewing, or improving Go test code — including table-driven tests, subtests, parallel tests, test helpers, test doubles, and assertions with cmp.Diff. Also use when a user asks to write a test for a Go function, even if they don't mention specific patterns like table-driven tests or subtests. Does not cover benchmark performance testing (see go-performance).", "repo": "https://github.com/cxuu/golang-skills/tree/HEAD/skills/go-testing", "install": ["npx skills add cxuu/golang-skills --skill go-testing"], "stars": 194, "pushed": "2026-06-20T04:12:05Z", "license": "Apache-2.0", "plat": "go", "live": "Not checked (runs locally)"}, {"id": "skill:jasonswett/llm-skills/tdd", "name": "tdd", "kind": "skill", "official": false, "desc": "Implement a change using test-driven development with RSpec. Guides the specify-encode-fulfill workflow.", "repo": "https://github.com/jasonswett/llm-skills/tree/HEAD/tdd", "install": ["npx skills add jasonswett/llm-skills --skill tdd"], "stars": 194, "pushed": "2026-10-20T13:36:40Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:jasonswett/llm-skills/test-design-review", "name": "test-design-review", "kind": "skill", "official": false, "desc": "Review tests for design quality using test design guidelines.", "repo": "https://github.com/jasonswett/llm-skills/tree/HEAD/test-design-review", "install": ["npx skills add jasonswett/llm-skills --skill test-design-review"], "stars": 194, "pushed": "2026-10-20T13:36:40Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:noqa-ai/noqa", "name": "noqa", "kind": "mcp", "official": null, "desc": "Automated mobile testing tool with device CLI for apps and games - real devices iOS & Android. Supports native (swift, kotlin), react native, flutter, KMP, unity and any mobile apps and games.", "repo": "https://github.com/noqa-ai/noqa", "install": [], "stars": 192, "pushed": null, "license": null, "plat": "ios & android", "live": "Not checked (runs locally)"}, {"id": "skill:TabooHarmony/roblox-brain/skills/core/roblox-performance", "name": "roblox-performance", "kind": "skill", "official": false, "desc": "Use when profiling or fixing Roblox performance: low FPS, lag, memory, network load, slow phones, hot paths.", "repo": "https://github.com/TabooHarmony/roblox-brain/tree/HEAD/skills/core/roblox-performance", "install": ["npx skills add TabooHarmony/roblox-brain --skill roblox-performance"], "stars": 186, "pushed": "2026-10-15T04:23:10Z", "license": "MIT", "plat": "roblox", "live": "Not checked (runs locally)"}, {"id": "skill:TabooHarmony/roblox-brain/skills/tools/roblox-publish-checklist", "name": "roblox-publish-checklist", "kind": "skill", "official": false, "desc": "Use before publishing or updating a Roblox experience to run evidence-backed release gates and a pre-release audit.", "repo": "https://github.com/TabooHarmony/roblox-brain/tree/HEAD/skills/tools/roblox-publish-checklist", "install": ["npx skills add TabooHarmony/roblox-brain --skill roblox-publish-checklist"], "stars": 186, "pushed": "2026-10-15T04:23:10Z", "license": "MIT", "plat": "roblox", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:terryso/claude-code-playwright-mcp-test", "name": "claude-code-playwright-mcp-test", "kind": "mcp", "official": null, "desc": "A YAML-based Playwright MCP automation testing framework designed for Claude Code", "repo": "https://github.com/terryso/claude-code-playwright-mcp-test", "install": [], "stars": 184, "pushed": null, "license": null, "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:mehrandvd/skunit", "name": "skunit", "kind": "mcp", "official": null, "desc": "skUnit is a testing tool for AI units, such as IChatClient, MCP Servers and agents.", "repo": "https://github.com/mehrandvd/skunit", "install": [], "stars": 181, "pushed": null, "license": null, "plat": "skunit", "live": "Not checked (runs locally)"}, {"id": "skill:kairyou/agent-tools/skills/workflow/at-review", "name": "at-review", "kind": "skill", "official": false, "desc": "Review code changes for bugs, regressions, convention violations, and high-value cleanup opportunities. Use for diffs, commit ranges, hosted PR/MR URLs, branches, paths, staged changes, or working-tree changes.", "repo": "https://github.com/kairyou/agent-tools/tree/HEAD/skills/workflow/at-review", "install": ["npx skills add kairyou/agent-tools --skill at-review"], "stars": 179, "pushed": "2026-11-13T15:24:08Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:atlanai/ai-registry/examples/acme-registry/artifacts/engineering/skill/pr-review/1.1.0", "name": "pr-review", "kind": "skill", "official": false, "desc": "Review a pull request for correctness, clarity, and test coverage, and leave findings ranked by severity.", "repo": "https://github.com/atlanai/ai-registry/tree/HEAD/examples/acme-registry/artifacts/engineering/skill/pr-review/1.1.0", "install": ["npx skills add atlanai/ai-registry --skill pr-review"], "stars": 179, "pushed": "2026-11-13T15:07:29Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:atlanai/ai-registry/examples/acme-registry/artifacts/engineering/skill/pr-review/1.2.0", "name": "pr-review", "kind": "skill", "official": false, "desc": "Review a pull request for correctness, clarity, and test coverage, and leave findings ranked by severity. Uses a checklist and a scoring rubric.", "repo": "https://github.com/atlanai/ai-registry/tree/HEAD/examples/acme-registry/artifacts/engineering/skill/pr-review/1.2.0", "install": ["npx skills add atlanai/ai-registry --skill pr-review"], "stars": 179, "pushed": "2026-11-13T15:07:29Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:rcosteira79/android-skills/plugins/android-skills/skills/android-debugging", "name": "android-debugging", "kind": "skill", "official": false, "desc": "Use when debugging Android or KMP issues — crashes, ANRs, performance regressions, obfuscated release stack traces, wrong on-screen UI state, or a bad value crossing several layers.", "repo": "https://github.com/rcosteira79/android-skills/tree/HEAD/plugins/android-skills/skills/android-debugging", "install": ["npx skills add rcosteira79/android-skills --skill android-debugging"], "stars": 173, "pushed": "2026-11-10T21:56:52Z", "license": "MIT", "plat": "android", "live": "Not checked (runs locally)"}, {"id": "skill:rcosteira79/android-skills/plugins/android-skills/skills/android-testing", "name": "android-testing", "kind": "skill", "official": false, "desc": "Use when writing, fixing, or refactoring Android/KMP code in Kotlin — a test-first (RED-GREEN-REFACTOR) foundation plus the Android/KMP test traps: Compose-test dispatching (v1 vs v2 test APIs, the two-schedulers trap), semantics-first selectors, choosing the smallest test shape, test-clock vs wall-clock, animation/screenshot determinism, and a `commonTest` name that fails the iOS compile while `jvmTest` stays green.", "repo": "https://github.com/rcosteira79/android-skills/tree/HEAD/plugins/android-skills/skills/android-testing", "install": ["npx skills add rcosteira79/android-skills --skill android-testing"], "stars": 173, "pushed": "2026-11-10T21:56:52Z", "license": "MIT", "plat": "android", "live": "Not checked (runs locally)"}, {"id": "skill:ravila4/claude-adhd-skills/skills/test-driven-development", "name": "test-driven-development", "kind": "skill", "official": false, "desc": "(TDD) Use when implementing any feature or bugfix. Apply the Logic Gate to identify what needs tests, then use the Iron Rule for strict test-first development on logic.", "repo": "https://github.com/ravila4/claude-adhd-skills/tree/HEAD/skills/test-driven-development", "install": ["npx skills add ravila4/claude-adhd-skills --skill test-driven-development"], "stars": 173, "pushed": "2026-03-01T01:39:04Z", "license": "MIT", "plat": "android", "live": "Not checked (runs locally)"}, {"id": "skill:tilework-tech/nori-skillsets/.claude/skills/e2e-testing-skillsets", "name": "E2E Testing Nori Skillsets Subcommands", "kind": "skill", "official": false, "desc": "Use when you need to interactively test a nori-skillsets CLI subcommand end-to-end via tmux, with full filesystem isolation", "repo": "https://github.com/tilework-tech/nori-skillsets/tree/HEAD/.claude/skills/e2e-testing-skillsets", "install": ["npx skills add tilework-tech/nori-skillsets --skill E2E Testing Nori Skillsets Subcommands"], "stars": 170, "pushed": "2026-11-03T23:32:20Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:tilework-tech/nori-skillsets/.claude/skills/tui-puppeteering-with-tmux", "name": "TUI Puppeteering with tmux", "kind": "skill", "official": false, "desc": "Use when automating or testing TUI/CLI applications - provides isolated tmux sessions with scripts for input, output capture, and state verification", "repo": "https://github.com/tilework-tech/nori-skillsets/tree/HEAD/.claude/skills/tui-puppeteering-with-tmux", "install": ["npx skills add tilework-tech/nori-skillsets --skill TUI Puppeteering with tmux"], "stars": 170, "pushed": "2026-11-03T23:32:20Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:frappe/skills/skills/fix-issue", "name": "fix-issue", "kind": "skill", "official": false, "desc": "Fix a bug reported in a GitHub issue or a markdown file, without letting the report's noise and guesses into the main context. Takes an issue number, an issue URL, or a file path as an argument. Use when asked to fix, investigate, or reproduce a reported bug.", "repo": "https://github.com/frappe/skills/tree/HEAD/skills/fix-issue", "install": ["npx skills add frappe/skills --skill fix-issue"], "stars": 168, "pushed": "2026-11-13T13:49:07Z", "license": null, "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:frappe/skills/skills/frappe-code-review", "name": "frappe-code-review", "kind": "skill", "official": false, "desc": "Review code for any Frappe application — a checklist distilled from years of engineering practice on correctness, security, performance, concurrency, readability, API design, and testing. Use this when reviewing a diff, a PR, or a piece of code for quality and security, or when you want a reviewer's checklist grounded in hard-won Frappe/ERPNext lessons.", "repo": "https://github.com/frappe/skills/tree/HEAD/skills/frappe-code-review", "install": ["npx skills add frappe/skills --skill frappe-code-review"], "stars": 168, "pushed": "2026-11-13T13:49:07Z", "license": null, "plat": "frappe", "live": "Not checked (runs locally)"}, {"id": "skill:frappe/skills/skills/guard-review", "name": "guard-review", "kind": "skill", "official": false, "desc": "Review a change with Guard, and do not push when the review has P0 findings. Run /guard-review to review the current change. Use it also on your own before `git push`, before `gh pr create` pushes a branch, and in the push step of other skills such as ship-it. Use it only when the Guard MCP server is connected (the `start_review` tool).", "repo": "https://github.com/frappe/skills/tree/HEAD/skills/guard-review", "install": ["npx skills add frappe/skills --skill guard-review"], "stars": 168, "pushed": "2026-11-13T13:49:07Z", "license": null, "plat": "guard", "live": "Not checked (runs locally)"}, {"id": "skill:supercorp-ai/supercov/plugins/supercov/skills/supercov", "name": "supercov", "kind": "skill", "official": false, "desc": "Measures test coverage and code quality in a repository with the supercov CLI, and turns what it finds into small, focused tests or fixes. Use when the user asks to add or improve tests, find untested code or raise coverage, or find what to refactor. Works with JavaScript, TypeScript, Python, Ruby, Rust, Go, Java and Kotlin projects.", "repo": "https://github.com/supercorp-ai/supercov/tree/HEAD/plugins/supercov/skills/supercov", "install": ["npx skills add supercorp-ai/supercov --skill supercov"], "stars": 167, "pushed": "2026-11-13T09:43:04Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:langchain-ai/langsmith-skills/config/skills/langsmith-evaluator", "name": "langsmith-evaluator", "kind": "skill", "official": false, "desc": "INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.", "repo": "https://github.com/langchain-ai/langsmith-skills/tree/HEAD/config/skills/langsmith-evaluator", "install": ["npx skills add langchain-ai/langsmith-skills --skill langsmith-evaluator"], "stars": 166, "pushed": "2026-11-14T01:59:09Z", "license": "MIT", "plat": "langsmith", "live": "Not checked (runs locally)"}, {"id": "mcp:com.make/mcp-server", "name": "Make", "kind": "mcp", "official": null, "desc": "Build, run and debug Make automation scenarios.", "repo": "https://github.com/integromat/make-skills", "install": ["https://mcp.make.com/v2"], "stars": 166, "pushed": "2026-11-09T12:30:02Z", "license": "MIT", "plat": "make", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "skill:UiPath/coder_eval/plugins/coder-eval/skills/analyze", "name": "analyze", "kind": "skill", "official": false, "desc": "Analyze a finished coder-eval run and write analysis.md — cluster failures into systemic patterns and recommend fixes. Use when the user wants to know why a run failed, what regressed or got worse since a previous run, what to fix, or what a run says about their tasks.", "repo": "https://github.com/UiPath/coder_eval/tree/HEAD/plugins/coder-eval/skills/analyze", "install": ["npx skills add UiPath/coder_eval --skill analyze"], "stars": 160, "pushed": "2026-11-14T00:47:28Z", "license": "Apache-2.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:UiPath/coder_eval/plugins/coder-eval/skills/check-skill", "name": "check-skill", "kind": "skill", "official": false, "desc": "Generate and run a coder-eval activation suite for a Claude Code skill. Use when the user asks whether a skill triggers, wants to test skill activation, or worries a skill has silently stopped firing.", "repo": "https://github.com/UiPath/coder_eval/tree/HEAD/plugins/coder-eval/skills/check-skill", "install": ["npx skills add UiPath/coder_eval --skill check-skill"], "stars": 160, "pushed": "2026-11-14T00:47:28Z", "license": "Apache-2.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:UiPath/coder_eval", "name": "coder_eval", "kind": "mcp", "official": null, "desc": "Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.", "repo": "https://github.com/UiPath/coder_eval", "install": [], "stars": 160, "pushed": "2026-11-14T00:47:28Z", "license": "Apache-2.0", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:UiPath/coder_eval/plugins/coder-eval/skills/init", "name": "init", "kind": "skill", "official": false, "desc": "Set up coder-eval in this repository — scan for what is worth evaluating (Claude Code skills, an MCP server, a CLI), then scaffold a task directory with one real task and the command to run it.", "repo": "https://github.com/UiPath/coder_eval/tree/HEAD/plugins/coder-eval/skills/init", "install": ["npx skills add UiPath/coder_eval --skill init"], "stars": 160, "pushed": "2026-11-14T00:47:28Z", "license": "Apache-2.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:UiPath/coder_eval/plugins/coder-eval/skills/lint-tasks", "name": "lint-tasks", "kind": "skill", "official": false, "desc": "Review existing coder-eval task YAML — find criteria that cannot fail, prompts that leak the answer, and near-duplicate tasks, each with a fix. Read-only. Use when the user wants existing tasks reviewed, linted, audited, or checked for gaps.", "repo": "https://github.com/UiPath/coder_eval/tree/HEAD/plugins/coder-eval/skills/lint-tasks", "install": ["npx skills add UiPath/coder_eval --skill lint-tasks"], "stars": 160, "pushed": "2026-11-14T00:47:28Z", "license": "Apache-2.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:UiPath/coder_eval/plugins/coder-eval/skills/task", "name": "task", "kind": "skill", "official": false, "desc": "Turn a natural-language description into coder-eval task YAML — minimal prompts, weighted criteria that check output content, validated with `coder-eval plan`. Use when the user wants to write, add, or generate an evaluation task.", "repo": "https://github.com/UiPath/coder_eval/tree/HEAD/plugins/coder-eval/skills/task", "install": ["npx skills add UiPath/coder_eval --skill task"], "stars": 160, "pushed": "2026-11-14T00:47:28Z", "license": "Apache-2.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:AlexZio00/sovereign-skills/code-autopsy", "name": "code-autopsy", "kind": "skill", "official": false, "desc": "Quantified code review: 12 questions (design, bugs, security, tests, error handling, observability), severity scoring, a four-axis composite score and a deployment verdict (SHIP IT / FIX FIRST / RISKY / BLOCK). Modes: full, --fast (runtime bugs only, max 8 findings), --quick (lint/type gate), diff. Use when: 'code autopsy', 'review this code', 'review my diff', 'is this safe to ship', 'security review of this change', 'deployment verdict'. Read-only: reports findings as diffs, never edits files.", "repo": "https://github.com/AlexZio00/sovereign-skills/tree/HEAD/code-autopsy", "install": ["npx skills add AlexZio00/sovereign-skills --skill code-autopsy"], "stars": 158, "pushed": "2026-11-07T04:21:53Z", "license": "MIT", "plat": "code", "live": "Not checked (runs locally)"}, {"id": "skill:AlexZio00/sovereign-skills/pre-push", "name": "pre-push", "kind": "skill", "official": false, "desc": "Pre-push security and quality pipeline: secrets scan, then tests, lint and review. TRIGGER automatically whenever the user requests a git push: 'push my changes', 'push to origin', 'push this', 'push the code', 'commit and push', 'ship it', 'deploy to remote', 'deploy to prod/staging/production', or any git push command. Blocks hardcoded credentials and prompt-injection/exfiltration markers (14 patterns: AWS/GCP/Azure/LLM keys, private keys, connection strings, platform tokens, merge conflicts, ", "repo": "https://github.com/AlexZio00/sovereign-skills/tree/HEAD/pre-push", "install": ["npx skills add AlexZio00/sovereign-skills --skill pre-push"], "stars": 158, "pushed": "2026-11-07T04:21:53Z", "license": "MIT", "plat": "git", "live": "Not checked (runs locally)"}, {"id": "skill:SnowBankSDK/foundationdb-dotnet-client/.claude/skills/snowbank-distributed-testing", "name": "snowbank-distributed-testing", "kind": "skill", "official": false, "desc": "How to write, run, and especially DIAGNOSE multi-node integration tests built on the SnowBank distributed-test framework (SnowBank.Testing.Framework / SnowBank.Testing.Common — a general-purpose harness, NOT FoundationDB-specific). Covers DistributedTest/MakeItSo + virtual hosts (AddSimpleLan/WithMinimalWebHost), the unified in-memory Timeline journal that every test prints (its column format and kind/level vocabulary), and the controls for cranking diagnostic detail when a test regresses — per-", "repo": "https://github.com/SnowBankSDK/foundationdb-dotnet-client/tree/HEAD/.claude/skills/snowbank-distributed-testing", "install": ["npx skills add SnowBankSDK/foundationdb-dotnet-client --skill snowbank-distributed-testing"], "stars": 158, "pushed": "2026-11-10T19:28:00Z", "license": "BSD-3-Clause", "plat": "snowbank", "live": "Not checked (runs locally)"}, {"id": "mcp:io.mockd/mockd", "name": "mockd", "kind": "mcp", "official": null, "desc": "Multi-protocol API mock server: HTTP, GraphQL, gRPC, WebSocket, MQTT, SSE, SOAP.", "repo": "https://github.com/getmockd/mockd", "install": ["oci:ghcr.io/getmockd/mockd"], "stars": 155, "pushed": "2026-09-17T23:27:22Z", "license": "Apache-2.0", "plat": "mockd", "live": "Not checked (runs locally)"}, {"id": "skill:mar-antaya/my-claude-skills/performance-profiler", "name": "performance-profiler", "kind": "skill", "official": false, "desc": "Performance Profiler", "repo": "https://github.com/mar-antaya/my-claude-skills/tree/HEAD/performance-profiler", "install": ["npx skills add mar-antaya/my-claude-skills --skill performance-profiler"], "stars": 151, "pushed": "2026-03-16T00:33:41Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:selmakcby/claude-agents-skills/skills/tdd", "name": "tdd", "kind": "skill", "official": false, "desc": "Test-Driven Development workflow. Use when writing new features, fixing bugs, or refactoring code. Enforces RED-GREEN-REFACTOR cycle with 80%+ coverage.", "repo": "https://github.com/selmakcby/claude-agents-skills/tree/HEAD/skills/tdd", "install": ["npx skills add selmakcby/claude-agents-skills --skill tdd"], "stars": 149, "pushed": "2026-04-21T16:50:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:kevmoo/dash_skills/skills/dart-test-coverage", "name": "dart-test-coverage", "kind": "skill", "official": false, "desc": "Understand and improve test coverage in a Dart package. Helps agents run coverage, interpret results, and identify missed lines.", "repo": "https://github.com/kevmoo/dash_skills/tree/HEAD/skills/dart-test-coverage", "install": ["npx skills add kevmoo/dash_skills --skill dart-test-coverage"], "stars": 148, "pushed": "2026-11-07T23:29:23Z", "license": "Apache-2.0", "plat": "dart", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.hidai25/evalview-mcp", "name": "io.github.hidai25/evalview-mcp", "kind": "mcp", "official": null, "desc": "Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.", "repo": "https://github.com/hidai25/eval-view", "install": ["pypi:evalview"], "stars": 142, "pushed": "2026-10-16T08:19:33Z", "license": "Apache-2.0", "plat": "mcp server", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Dave-London/build", "name": "io.github.Dave-London/build", "kind": "mcp", "official": null, "desc": "Structured build tool output (tsc, generic commands) as typed JSON diagnostics.", "repo": "https://github.com/Dave-London/Pare", "install": ["npm:@paretools/build"], "stars": 141, "pushed": "2026-11-10T03:44:41Z", "license": "MIT", "plat": "build tools", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Dave-London/cargo", "name": "io.github.Dave-London/cargo", "kind": "mcp", "official": null, "desc": "Structured Rust cargo operations (build, test, clippy) as typed JSON.", "repo": "https://github.com/Dave-London/Pare", "install": ["npm:@paretools/cargo"], "stars": 141, "pushed": "2026-11-10T03:44:41Z", "license": "MIT", "plat": "rust cargo", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Dave-London/docker", "name": "io.github.Dave-London/docker", "kind": "mcp", "official": null, "desc": "Structured Docker operations (ps, images, logs, build) as typed JSON.", "repo": "https://github.com/Dave-London/Pare", "install": ["npm:@paretools/docker"], "stars": 141, "pushed": "2026-11-10T03:44:41Z", "license": "MIT", "plat": "docker", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Dave-London/go", "name": "io.github.Dave-London/go", "kind": "mcp", "official": null, "desc": "Structured Go tool output (build, test, vet) as typed JSON diagnostics.", "repo": "https://github.com/Dave-London/Pare", "install": ["npm:@paretools/go"], "stars": 141, "pushed": "2026-11-10T03:44:41Z", "license": "MIT", "plat": "go tool", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Dave-London/http", "name": "io.github.Dave-London/http", "kind": "mcp", "official": null, "desc": "MCP server for HTTP requests (curl) with structured, token-efficient output", "repo": "https://github.com/Dave-London/Pare", "install": ["npm:@paretools/http"], "stars": 141, "pushed": "2026-11-10T03:44:41Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Dave-London/pare-test", "name": "io.github.Dave-London/pare-test", "kind": "mcp", "official": null, "desc": "Pare Test ג€” Auto-detects test framework (pytest, jest, vitest, mocha), returns typed JSON.", "repo": "https://github.com/Dave-London/Pare", "install": ["npm:@paretools/test"], "stars": 141, "pushed": "2026-11-10T03:44:41Z", "license": "MIT", "plat": "pytest", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Dave-London/test", "name": "io.github.Dave-London/test", "kind": "mcp", "official": null, "desc": "Auto-detects test framework (pytest, jest, vitest) and returns structured results.", "repo": "https://github.com/Dave-London/Pare", "install": ["npm:@paretools/test"], "stars": 141, "pushed": "2026-11-10T03:44:41Z", "license": "MIT", "plat": "pytest", "live": "Not checked (runs locally)"}, {"id": "skill:instructa/agent-skills/skills/engineering/code-quality", "name": "code-quality", "kind": "skill", "official": false, "desc": "Apply focused code-quality checks when implementing or reviewing behavioral changes. Use for maintainability, framework fit, data safety and meaningful verification; not visual design or a full security audit.", "repo": "https://github.com/instructa/agent-skills/tree/HEAD/skills/engineering/code-quality", "install": ["npx skills add instructa/agent-skills --skill code-quality"], "stars": 140, "pushed": "2026-11-06T17:20:07Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:instructa/agent-skills/skills/engineering/consolidate-test-suites", "name": "consolidate-test-suites", "kind": "skill", "official": false, "desc": "Decide where durable test coverage belongs and clean up temporary test probes. Use while testing a bug fix or architectural change, or before finishing work that added tests, fixtures, snapshots, diagnostics, or temporary assertions. Select one owning layer, reuse canonical suites, merge unique signal, and remove task-created probe residue without disturbing pre-existing work.", "repo": "https://github.com/instructa/agent-skills/tree/HEAD/skills/engineering/consolidate-test-suites", "install": ["npx skills add instructa/agent-skills --skill consolidate-test-suites"], "stars": 140, "pushed": "2026-11-06T17:20:07Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:instructa/agent-skills/skills/electron/electron-live-test", "name": "electron-live-test", "kind": "skill", "official": false, "desc": "Live-test any Electron desktop app with native-devtools-mcp, Chrome DevTools Protocol, screenshots, OCR, and accessibility tools. Use when the user asks for Electron UI verification, MCP-driven app control, renderer CDP interaction, native desktop automation, screenshots, or OCR-driven checks.", "repo": "https://github.com/instructa/agent-skills/tree/HEAD/skills/electron/electron-live-test", "install": ["npx skills add instructa/agent-skills --skill electron-live-test"], "stars": 140, "pushed": "2026-11-06T17:20:07Z", "license": null, "plat": "electron", "live": "Not checked (runs locally)"}, {"id": "skill:instructa/agent-skills/skills/go/go-local-health", "name": "go-local-health", "kind": "skill", "official": false, "desc": "Run local Go health checks (tests, coverage, lint) in Go repositories that contain go.mod/go.sum. Use when the user asks to run or interpret local Go test/coverage/lint workflows using tools like lazygotest, gocovsh, tparse, and golangci-lint. Do not use for Rust or non-Go projects.", "repo": "https://github.com/instructa/agent-skills/tree/HEAD/skills/go/go-local-health", "install": ["npx skills add instructa/agent-skills --skill go-local-health"], "stars": 140, "pushed": "2026-11-06T17:20:07Z", "license": null, "plat": "go", "live": "Not checked (runs locally)"}, {"id": "skill:instructa/agent-skills/skills/engineering/lean-ci", "name": "lean-ci", "kind": "skill", "official": false, "desc": "Right-size CI from measured run data instead of stacking pipeline mechanics. Use when CI is slow, expensive, flaky, or runs too often; when the user asks to clean up, speed up, split, or reduce GitHub Actions, GitLab CI, or other pipelines; when reviewing a CI proposal for over-engineering; and before you yourself add jobs, caches, matrices, path filters, concurrency rules, nightly runs, pre-push hooks, or test selection to a workflow.", "repo": "https://github.com/instructa/agent-skills/tree/HEAD/skills/engineering/lean-ci", "install": ["npx skills add instructa/agent-skills --skill lean-ci"], "stars": 140, "pushed": "2026-11-06T17:20:07Z", "license": null, "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:instructa/agent-skills/skills/engineering/lean-testing", "name": "lean-testing", "kind": "skill", "official": false, "desc": "Prevent unnecessary test generation in agentic coding. Use when implementing features, fixing bugs or deciding whether to add tests; select the smallest sufficient check and justify lasting test code.", "repo": "https://github.com/instructa/agent-skills/tree/HEAD/skills/engineering/lean-testing", "install": ["npx skills add instructa/agent-skills --skill lean-testing"], "stars": 140, "pushed": "2026-11-06T17:20:07Z", "license": null, "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:fallow-rs/fallow-skills/claude-directory/fallow/skills/fallow-mutation", "name": "fallow-mutation", "kind": "skill", "official": false, "desc": "Mutation testing for TypeScript and JavaScript with `fallow mutation`. Use when asked to improve, strengthen or check the tests of a change, a PR, a branch or a file, to check whether a test can fail at all, to find behavior that the tests do not protect, to find redundant tests, to check that a change of the tests did not weaken them, to gate a mutation score, or to run fallow mutation. Do not use to raise line coverage, to write one requested test, or to fix a failing test. Do not use for Rust", "repo": "https://github.com/fallow-rs/fallow-skills/tree/HEAD/claude-directory/fallow/skills/fallow-mutation", "install": ["npx skills add fallow-rs/fallow-skills --skill fallow-mutation"], "stars": 139, "pushed": "2026-11-13T16:17:56Z", "license": "MIT", "plat": "javascript", "live": "Not checked (runs locally)"}, {"id": "skill:Amplicode/spring-skills/skills/coverage", "name": "coverage", "kind": "skill", "official": false, "desc": "Measure a project's code coverage and report the coverage number. Use whenever coverage needs to be measured — a user asking to run the coverage report or check the current level, and also when the task itself calls for it: recording the starting coverage before development, confirming coverage didn't drop below the committed baseline after a change. Measures the whole project (unit + integration merged) or just one test group — a package/class glob or a subproject.", "repo": "https://github.com/Amplicode/spring-skills/tree/HEAD/skills/coverage", "install": ["npx skills add Amplicode/spring-skills --skill coverage"], "stars": 138, "pushed": "2026-09-06T10:25:50Z", "license": null, "plat": "java", "live": "Not checked (runs locally)"}, {"id": "skill:Amplicode/spring-skills/skills/java-debug", "name": "java-debug", "kind": "skill", "official": false, "desc": "Safety rules, workflows, and tool reference for debugging applications via IntelliJ debugger: breakpoints, debug sessions, stepping, evaluating expressions, inspecting runtime state. TRIGGER when: user wants to debug, investigate a bug, set breakpoints, inspect runtime behavior, step through code, or understand why code behaves unexpectedly at runtime. Trigger phrases (EN): \"debug\", \"breakpoint\", \"step through\", \"step into\", \"step over\", \"why does this crash\", \"why is this null\", \"launch in debu", "repo": "https://github.com/Amplicode/spring-skills/tree/HEAD/skills/java-debug", "install": ["npx skills add Amplicode/spring-skills --skill java-debug"], "stars": 138, "pushed": "2026-09-06T10:25:50Z", "license": null, "plat": "intellij idea", "live": "Not checked (runs locally)"}, {"id": "skill:Amplicode/spring-skills/skills/mutation-testing", "name": "mutation-testing", "kind": "skill", "official": false, "desc": "Set up and run mutation testing with PIT (pitest) on a Gradle project, and read the mutation score. Use this skill whenever the user wants mutation testing added to a build, configured, run or re-run, wants a mutation score or a mutation report interpreted, asks why a particular mutant survived, or asks what should be excluded from mutation analysis, or wants something added to those exclusions — in any language, and whether or not the tool is named. Also use it when the task calls for it: check", "repo": "https://github.com/Amplicode/spring-skills/tree/HEAD/skills/mutation-testing", "install": ["npx skills add Amplicode/spring-skills --skill mutation-testing"], "stars": 138, "pushed": "2026-09-06T10:25:50Z", "license": null, "plat": "gradle", "live": "Not checked (runs locally)"}, {"id": "skill:Amplicode/spring-skills/skills/run-tests", "name": "run-tests", "kind": "skill", "official": false, "desc": "Run a Gradle project's tests by test type or module — unit, integration, or all. Use this skill whenever the user wants to run, re-run, or check the project's tests (e.g. \"run the unit tests\", \"run all tests\", \"run the integration tests for the vet module\", \"did the tests pass?\").", "repo": "https://github.com/Amplicode/spring-skills/tree/HEAD/skills/run-tests", "install": ["npx skills add Amplicode/spring-skills --skill run-tests"], "stars": 138, "pushed": "2026-09-06T10:25:50Z", "license": null, "plat": "gradle", "live": "Not checked (runs locally)"}, {"id": "skill:Parcha-ai/parcha-skills/autoqa/skills/autoqa", "name": "autoqa", "kind": "skill", "official": false, "desc": "Self-QA a repo's running application end-to-end — discover how it runs, build a feature×modality test plan, execute it against a live instance, and produce a witnessed pass/fail report. Use when the user says \"autoqa\", \"QA this repo/branch\", \"verify every feature works\", \"release readiness check\", \"test this like a QA engineer would\", or another skill needs an automated QA pass before sign-off.", "repo": "https://github.com/Parcha-ai/parcha-skills/tree/HEAD/autoqa/skills/autoqa", "install": ["npx skills add Parcha-ai/parcha-skills --skill autoqa"], "stars": 136, "pushed": "2026-10-22T22:55:35Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:Parcha-ai/parcha-skills/verify-release/skills/verify-release", "name": "verify-release", "kind": "skill", "official": false, "desc": "Verify a specific release in its target environment, follow an in-progress rollout, and resume agreed checks when it is ready. Use for “I deployed it, verify”, “monitor the deployment and continue QA”, or “is this release working in staging/production?”. Discovers the stack and uses live evidence. Not a deployment tool or a full QA campaign by default.", "repo": "https://github.com/Parcha-ai/parcha-skills/tree/HEAD/verify-release/skills/verify-release", "install": ["npx skills add Parcha-ai/parcha-skills --skill verify-release"], "stars": 136, "pushed": "2026-10-22T22:55:35Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:jMerta/codex-skills/bug-triage", "name": "bug-triage", "kind": "skill", "official": false, "desc": "Use when the user reports a bug, regression, runtime error, failing build, or broken test and wants reproduction, diagnosis, root-cause analysis, or an authorized fix. Isolates the shared cause and verifies the smallest relevant change.", "repo": "https://github.com/jMerta/codex-skills/tree/HEAD/bug-triage", "install": ["npx skills add jMerta/codex-skills --skill bug-triage"], "stars": 132, "pushed": "2026-08-18T12:07:12Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:jMerta/codex-skills/focused-tdd", "name": "focused-tdd", "kind": "skill", "official": false, "desc": "Use when the user asks for test-first development, TDD, or a regression test before a fix, or when implementing deterministic business rules, state transitions, authorization boundaries, idempotency, and other behavior where observing a focused failing test would materially reduce risk. Selects strict TDD, regression-first, or proportional validation.", "repo": "https://github.com/jMerta/codex-skills/tree/HEAD/focused-tdd", "install": ["npx skills add jMerta/codex-skills --skill focused-tdd"], "stars": 132, "pushed": "2026-08-18T12:07:12Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:jMerta/codex-skills/review-test-coverage", "name": "review-test-coverage", "kind": "skill", "official": false, "desc": "Use when the user asks for a pre-PR or diff review of tests, CI evidence, test harness changes, screenshots, recordings, or proportional validation. Finds reachable behavior that the changed tests or evidence fail to protect, separates code defects from external CI outages, and recommends the narrowest meaningful check.", "repo": "https://github.com/jMerta/codex-skills/tree/HEAD/review-test-coverage", "install": ["npx skills add jMerta/codex-skills --skill review-test-coverage"], "stars": 132, "pushed": "2026-08-18T12:07:12Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:RayFernando1337/rayfernando-skills/plugins/running-bug-review-board/skills/running-bug-review-board", "name": "running-bug-review-board", "kind": "skill", "official": false, "desc": "Runs real-user QA, manual test plans, UX bug hunts, build sign-off, bug filing, and bug triage for web or iOS/iPadOS apps. Use when asked \"QA this\", \"is this ready to ship?\", or similar. Produces P0/P1/P2 bug reports, YES/NO phase sign-off, tracker sync guidance, and an HTML QA dashboard; keeps Interactive BRB triage in a separate session.", "repo": "https://github.com/RayFernando1337/rayfernando-skills/tree/HEAD/plugins/running-bug-review-board/skills/running-bug-review-board", "install": ["npx skills add RayFernando1337/rayfernando-skills --skill running-bug-review-board"], "stars": 132, "pushed": "2026-07-19T23:39:14Z", "license": "Apache-2.0", "plat": "web, ios", "live": "Not checked (runs locally)"}, {"id": "skill:povvo/claudikins-kernel/skills/strict-enforcement", "name": "strict-enforcement", "kind": "skill", "official": false, "desc": "Use when running claudikins-kernel:verify, checking implementation quality, deciding pass/fail verdicts, or enforcing cross-command gates — requires actual evidence of code working, not just passing tests", "repo": "https://github.com/povvo/claudikins-kernel/tree/HEAD/skills/strict-enforcement", "install": ["npx skills add povvo/claudikins-kernel --skill strict-enforcement"], "stars": 127, "pushed": "2026-04-22T12:19:57Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:avibebuilder/claude-prime/.claude/skills/diagnose", "name": "diagnose", "kind": "skill", "official": false, "desc": "Investigate unexpected behavior and mysterious bugs. Use when the cause of a problem is unknown and the user needs to understand WHY something is happening — symptoms like: sudden unexplained changes in metrics or behavior, works locally but not in staging/production, inconsistent or intermittent failures, correct code producing wrong results, operations succeeding but having no effect, environment-specific failures, duplicate executions, stale data, or any \\\"why did this change?\\\" or \\\"why is t", "repo": "https://github.com/avibebuilder/claude-prime/tree/HEAD/.claude/skills/diagnose", "install": ["npx skills add avibebuilder/claude-prime --skill diagnose"], "stars": 125, "pushed": "2026-05-16T19:59:38Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:avibebuilder/claude-prime/.claude/skills/fix", "name": "fix", "kind": "skill", "official": false, "desc": "Fix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, o", "repo": "https://github.com/avibebuilder/claude-prime/tree/HEAD/.claude/skills/fix", "install": ["npx skills add avibebuilder/claude-prime --skill fix"], "stars": 125, "pushed": "2026-05-16T19:59:38Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:st0012/ruby-skills/plugins/ruby-skills/skills/ruby-test-frameworks", "name": "ruby-test-frameworks", "kind": "skill", "official": false, "desc": "Use when writing or running tests in a Ruby project that uses minitest or test-unit. These frameworks have deceptively similar APIs with critical naming differences that cause NoMethodError at runtime. Consult this before writing assertions, running specific tests, or using setup/teardown lifecycle methods.", "repo": "https://github.com/st0012/ruby-skills/tree/HEAD/plugins/ruby-skills/skills/ruby-test-frameworks", "install": ["npx skills add st0012/ruby-skills --skill ruby-test-frameworks"], "stars": 125, "pushed": "2026-06-13T22:00:03Z", "license": "MIT", "plat": "ruby", "live": "Not checked (runs locally)"}, {"id": "skill:langchain-ai/skills-benchmarks/skills/noise/testing_patterns", "name": "testing-patterns", "kind": "skill", "official": false, "desc": "Unit testing and integration testing best practices", "repo": "https://github.com/langchain-ai/skills-benchmarks/tree/HEAD/skills/noise/testing_patterns", "install": ["npx skills add langchain-ai/skills-benchmarks --skill testing-patterns"], "stars": 120, "pushed": "2026-09-21T17:24:16Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:ejboy/agent-scripts/skills/lite-tools", "name": "lite-tools", "kind": "skill", "official": false, "desc": "Use compact wrappers when running routine Maven builds and tests, supported npm/Node test workflows, or Go tests. Select mvn-lite for supported Maven build and test workflows, npm-lite for npm run verify, npm run test:unit, or node --test, and go-lite for go test.", "repo": "https://github.com/ejboy/agent-scripts/tree/HEAD/skills/lite-tools", "install": ["npx skills add ejboy/agent-scripts --skill lite-tools"], "stars": 118, "pushed": "2026-11-14T00:01:00Z", "license": "MIT", "plat": "maven, npm, go", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:manykarim/rf-mcp", "name": "rf-mcp", "kind": "mcp", "official": null, "desc": "A Robot Framework MCP Server ", "repo": "https://github.com/manykarim/rf-mcp", "install": [], "stars": 118, "pushed": null, "license": null, "plat": "robot framework", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:rapiddweller/datamimic", "name": "datamimic", "kind": "mcp", "official": null, "desc": "Model-driven synthetic test data for CI/CD and analytics - deterministic, privacy-preserving, and domain-aware. Includes Python APIs, XML pipelines, and MCP/IDE integration to orchestrate realistic datasets for finance, healthcare, and other regulated environments.", "repo": "https://github.com/rapiddweller/datamimic", "install": [], "stars": 117, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:gh:2501035-wq/mobile-sim-streamer", "name": "mobile-sim-streamer", "kind": "mcp", "official": null, "desc": "Self-Hosted Mobile Device Streaming for QA Teams 2026", "repo": "https://github.com/2501035-wq/mobile-sim-streamer", "install": [], "stars": 115, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:MADTeacher/mad-agents-skills/flutter-testing", "name": "flutter-testing", "kind": "skill", "official": false, "desc": "Write, fix, review, debug, and validate Flutter tests for apps, packages, and plugins. Use when adding unit tests, widget tests, integration tests, MethodChannel or plugin mocks, Mockito or mocktail test doubles, golden or accessibility checks, CI test commands, test failures, MissingPluginException, pump or pumpAndSettle problems, finder errors, build_runner mock generation, device integration testing, web integration testing, or flaky Flutter tests.", "repo": "https://github.com/MADTeacher/mad-agents-skills/tree/HEAD/flutter-testing", "install": ["npx skills add MADTeacher/mad-agents-skills --skill flutter-testing"], "stars": 112, "pushed": "2026-05-01T14:16:25Z", "license": "MIT", "plat": "flutter", "live": "Not checked (runs locally)"}, {"id": "skill:cigery-useio/useio-skills/debugger-pro", "name": "debugger-pro", "kind": "skill", "official": false, "desc": "系统性调试技能，通过证据驱动的6阶段工作流精准定位和修复bug。以五大核心原则为防护链，确保诊断有证据、修复有评估、验证有回归。支持问题分级（P0-P3）、修复风险评估与门控、Context7文档查询降级策略，输出含分级清单和风险报告的完整调试报告。", "repo": "https://github.com/cigery-useio/useio-skills/tree/HEAD/debugger-pro", "install": ["npx skills add cigery-useio/useio-skills --skill debugger-pro"], "stars": 110, "pushed": "2026-09-23T17:09:12Z", "license": null, "plat": "debugger", "live": "Not checked (runs locally)"}, {"id": "skill:starslingdev/skills/skills/ci-score", "name": "ci-score", "kind": "skill", "official": false, "desc": "Grades a repository's GitHub Actions configuration against CI best practices (the CI Score: eleven pass/fail configuration facts computed from the repo's own workflow YAML) and hands back concrete fixes for every gap, ranked by impact and risk, each with an apply-now option and a paste-able agent prompt. Use when: (1) the user asks to grade or score their CI, or audit CI configuration against best practices (\"grade my CI\", \"CI score\", \"CI best practices audit\", \"how healthy is my CI config\"), (2", "repo": "https://github.com/starslingdev/skills/tree/HEAD/skills/ci-score", "install": ["npx skills add starslingdev/skills --skill ci-score"], "stars": 108, "pushed": "2026-11-14T05:35:56Z", "license": "MIT", "plat": "github actions", "live": "Not checked (runs locally)"}, {"id": "skill:starslingdev/skills/skills/ci-speedup", "name": "ci-speedup", "kind": "skill", "official": false, "desc": "Audits a repository's GitHub Actions workflows for CI optimization opportunities — missing caches, redundant setup, sleep-based readiness, long test jobs without sharding, full-history checkout, dead env vars, build-cache misconfig, and ~60 more patterns across caching, redundancy, parallelization, conditional execution, trigger scope, and hidden failures. Use when: (1) analyzing a repo's CI for optimization opportunities, (2) producing a prioritized report with measured wall-clock and runner-mi", "repo": "https://github.com/starslingdev/skills/tree/HEAD/skills/ci-speedup", "install": ["npx skills add starslingdev/skills --skill ci-speedup"], "stars": 108, "pushed": "2026-11-14T05:35:56Z", "license": "MIT", "plat": "github actions", "live": "Not checked (runs locally)"}, {"id": "skill:FAIRY123456789/human-edge-agent-skills/skills/deployment-proof", "name": "deployment-proof", "kind": "skill", "official": false, "desc": "Convert deployment logs, validation reports, Git history, and comparison notes into a redacted GitHub case study, portfolio entry, interview story, and evidence-backed resume bullets. Use after a software deployment, migration, recovery, or automation project when the user wants to demonstrate learning ability or impact without leaking host identities, credentials, private paths, customer data, or invented metrics. Do not publish or push unless the user explicitly asks.", "repo": "https://github.com/FAIRY123456789/human-edge-agent-skills/tree/HEAD/skills/deployment-proof", "install": ["npx skills add FAIRY123456789/human-edge-agent-skills --skill deployment-proof"], "stars": 108, "pushed": "2026-11-09T10:54:00Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "skill:robium-ai/robium/skills/simulation", "name": "simulation", "kind": "skill", "official": false, "desc": "Choose between Gazebo, Isaac Sim, and MuJoCo and define what the simulation must prove.", "repo": "https://github.com/robium-ai/robium/tree/HEAD/skills/simulation", "install": ["npx skills add robium-ai/robium --skill simulation"], "stars": 108, "pushed": "2026-10-07T14:11:14Z", "license": "MIT", "plat": "gazebo", "live": "Not checked (runs locally)"}, {"id": "skill:starslingdev/skills/skills/sling", "name": "sling", "kind": "skill", "official": false, "desc": "Diagnoses GitHub Actions failures and attributes CI time and cost using StarSling's `sling` CLI. Invoke this BEFORE using `gh` or fetching any logs whenever the user asks why a job or run failed, what made a run slow, about runner minutes or CI cost, asks to re-run or cancel a run, or pastes a GitHub Actions URL — `sling` returns server-classified failure causes and cost attribution that log-grepping misses; state changes route to `gh`. Not for repo-wide audits of workflow files (ci-score, ci-sp", "repo": "https://github.com/starslingdev/skills/tree/HEAD/skills/sling", "install": ["npx skills add starslingdev/skills --skill sling"], "stars": 108, "pushed": "2026-11-14T05:35:56Z", "license": "MIT", "plat": "github actions", "live": "Not checked (runs locally)"}, {"id": "skill:robium-ai/robium/skills/test-assets", "name": "test-assets", "kind": "skill", "official": false, "desc": "Choose and manage reproducible worlds, models, datasets, and recordings for robotics tests.", "repo": "https://github.com/robium-ai/robium/tree/HEAD/skills/test-assets", "install": ["npx skills add robium-ai/robium --skill test-assets"], "stars": 108, "pushed": "2026-10-07T14:11:14Z", "license": "MIT", "plat": "testing", "live": "Not checked (runs locally)"}, {"id": "skill:robium-ai/robium/skills/testing", "name": "testing", "kind": "skill", "official": false, "desc": "Choose proportional evidence for robotics software before claiming it works.", "repo": "https://github.com/robium-ai/robium/tree/HEAD/skills/testing", "install": ["npx skills add robium-ai/robium --skill testing"], "stars": 108, "pushed": "2026-10-07T14:11:14Z", "license": "MIT", "plat": "testing", "live": "Not checked (runs locally)"}, {"id": "skill:zanecole10/software-tailor-skills/13-bug-triage-prioritizer", "name": "bug-triage-prioritizer", "kind": "skill", "official": false, "desc": "Triage bug reports by severity, recommend fix order, generate client communication templates, determine whether to charge for fixes, and provide Claude Code prompts to resolve issues quickly.", "repo": "https://github.com/zanecole10/software-tailor-skills/tree/HEAD/13-bug-triage-prioritizer", "install": ["npx skills add zanecole10/software-tailor-skills --skill bug-triage-prioritizer"], "stars": 107, "pushed": "2025-10-31T02:42:36Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:jnsahaj/skills/skills/explain-then-fix", "name": "explain-then-fix", "kind": "skill", "official": false, "desc": "Work through bugs or reported issues one cause at a time — reproduce the reporter's own case, explain the root cause with annotated evidence and a diagram, lay out fix options, wait for \"go\", then fix and show before/after.", "repo": "https://github.com/jnsahaj/skills/tree/HEAD/skills/explain-then-fix", "install": ["npx skills add jnsahaj/skills --skill explain-then-fix"], "stars": 107, "pushed": "2026-10-05T12:46:07Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:lynxlangya/techne/skills/anchor-repro", "name": "anchor-repro", "kind": "skill", "official": false, "desc": "Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe. Use for bug reports, failing tests, crashes, hangs, regressions, wrong output, and observable behavior that should change.", "repo": "https://github.com/lynxlangya/techne/tree/HEAD/skills/anchor-repro", "install": ["npx skills add lynxlangya/techne --skill anchor-repro"], "stars": 106, "pushed": "2026-07-02T07:50:54Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:unlearndev/skills/skills/first-five", "name": "first-five", "kind": "skill", "official": false, "desc": "Scan a branch or diff against the First Five checklist (Error Handling, Input Boundaries, External Calls, State Mutations, Assumed Dependencies) and report only genuine concerns. Use when the user asks to \"run the first five\" on a branch or diff.", "repo": "https://github.com/unlearndev/skills/tree/HEAD/skills/first-five", "install": ["npx skills add unlearndev/skills --skill first-five"], "stars": 106, "pushed": "2026-11-09T11:02:40Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:unlearndev/skills/skills/preflight", "name": "preflight", "kind": "skill", "official": false, "desc": "Reads the diff between the current branch and main and produces a production pre-flight checklist of everything that must be done or configured once the change merges. Use before merging or deploying a branch.", "repo": "https://github.com/unlearndev/skills/tree/HEAD/skills/preflight", "install": ["npx skills add unlearndev/skills --skill preflight"], "stars": 106, "pushed": "2026-11-09T11:02:40Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:unlearndev/skills/skills/qa-checklist", "name": "qa-checklist", "kind": "skill", "official": false, "desc": "Read the diff for a change and produce a short, manual QA checklist to run against the deployed app — only the behaviour this change actually touched, written as plain-English steps a person can click through. Use when the user asks for a \"QA checklist\", \"manual test plan\", \"what should I test\", \"smoke test steps\", or how to verify a change by hand after deploy.", "repo": "https://github.com/unlearndev/skills/tree/HEAD/skills/qa-checklist", "install": ["npx skills add unlearndev/skills --skill qa-checklist"], "stars": 106, "pushed": "2026-11-09T11:02:40Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:TheOrcDev/skills/point-and-click-adventure/ship-check", "name": "ship-check", "kind": "skill", "official": false, "desc": "Proves a point-and-click adventure change in the builds people actually play, not the editor. Runs the headless import, GUT tests and content lint, exports the desktop and web builds, plays scripted QA scenarios in the exported app and in Chrome, checks what really shipped in the pack, measures per-room frame time, video memory and load time against budgets, records reels, files evidence in docs/qa, and deploys the web build to Vercel. Use when a slice is finished, before a commit or deploy, whe", "repo": "https://github.com/TheOrcDev/skills/tree/HEAD/point-and-click-adventure/ship-check", "install": ["npx skills add TheOrcDev/skills --skill ship-check"], "stars": 106, "pushed": "2026-11-02T11:56:20Z", "license": null, "plat": "godot", "live": "Not checked (runs locally)"}, {"id": "skill:unlearndev/skills/skills/zombies", "name": "zombies", "kind": "skill", "official": false, "desc": "Suggest tests worth writing for a feature using the ZOMBIES heuristic (Zero, One, Many, Boundaries, Interface, Exceptions, Simple scenarios). Pass a free-text feature description, or omit args to use the current branch's diff. Outputs only the categories that apply — not a full ZOMBIES checklist.", "repo": "https://github.com/unlearndev/skills/tree/HEAD/skills/zombies", "install": ["npx skills add unlearndev/skills --skill zombies"], "stars": 106, "pushed": "2026-11-09T11:02:40Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:youdotcom-oss/agent-skills/.agents/skills/tdd", "name": "tdd", "kind": "skill", "official": false, "desc": "Use test-driven development for behavior-changing feature or fix work, and whenever the user mentions TDD, test-first, red-green-refactor, tracer bullets, integration tests, or public-interface behavior tests. Skip for docs-only, path-only rename, formatting-only, or purely mechanical chores unless explicitly requested.", "repo": "https://github.com/youdotcom-oss/agent-skills/tree/HEAD/.agents/skills/tdd", "install": ["npx skills add youdotcom-oss/agent-skills --skill tdd"], "stars": 104, "pushed": "2026-11-11T16:40:58Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "skill:AsyrafHussin/agent-skills/skills/e2e-playwright-testing", "name": "e2e-playwright-testing", "kind": "skill", "official": false, "desc": "End-to-end testing with Playwright for web applications. Use when writing E2E tests, browser automation, form submission testing, or user flow testing. Triggers on \"playwright\", \"e2e test\", \"browser test\", \"end-to-end\", \"form flow testing\", or test files in tests/e2e/.", "repo": "https://github.com/AsyrafHussin/agent-skills/tree/HEAD/skills/e2e-playwright-testing", "install": ["npx skills add AsyrafHussin/agent-skills --skill e2e-playwright-testing"], "stars": 103, "pushed": "2026-08-27T12:29:22Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "skill:AsyrafHussin/agent-skills/skills/laravel-queues", "name": "laravel-queues", "kind": "skill", "official": false, "desc": "Laravel 13 queue and job patterns — driver choice, job design (idempotency, ShouldQueue, model serialisation), retry and failure handling, worker scaling, Bus batching and chaining, Horizon when warranted, queue testing. Use when designing async jobs, scheduling background work, configuring Horizon, debugging stuck jobs, or auditing queue health. Triggers on \"Laravel queue\", \"Laravel job\", \"background job\", \"Horizon setup\", \"failed jobs\", \"Bus batch\", \"queue worker tuning\".", "repo": "https://github.com/AsyrafHussin/agent-skills/tree/HEAD/skills/laravel-queues", "install": ["npx skills add AsyrafHussin/agent-skills --skill laravel-queues"], "stars": 103, "pushed": "2026-08-27T12:29:22Z", "license": "MIT", "plat": "laravel", "live": "Not checked (runs locally)"}, {"id": "skill:AsyrafHussin/agent-skills/skills/laravel-testing", "name": "laravel-testing", "kind": "skill", "official": false, "desc": "Laravel 13 testing with Pest PHP 4 or PHPUnit 12. Use when writing feature tests, unit tests, or any test code in a Laravel application. Triggers on tasks involving HTTP tests, model factories, database assertions, mocking facades, authentication testing, or test organisation patterns.", "repo": "https://github.com/AsyrafHussin/agent-skills/tree/HEAD/skills/laravel-testing", "install": ["npx skills add AsyrafHussin/agent-skills --skill laravel-testing"], "stars": 103, "pushed": "2026-08-27T12:29:22Z", "license": "MIT", "plat": "laravel", "live": "Not checked (runs locally)"}, {"id": "skill:AsyrafHussin/agent-skills/skills/testing-best-practices", "name": "testing-best-practices", "kind": "skill", "official": false, "desc": "Unit testing, integration testing, and test-driven development principles. Use when writing tests, reviewing test code, improving test coverage, or setting up testing strategy. Triggers on \"write tests\", \"review tests\", \"testing best practices\", or \"TDD\".", "repo": "https://github.com/AsyrafHussin/agent-skills/tree/HEAD/skills/testing-best-practices", "install": ["npx skills add AsyrafHussin/agent-skills --skill testing-best-practices"], "stars": 103, "pushed": "2026-08-27T12:29:22Z", "license": "MIT", "plat": "testing", "live": "Not checked (runs locally)"}, {"id": "skill:google-labs-code/jules-skills/skills/local-action-verification", "name": "local-action-verification", "kind": "skill", "official": false, "desc": "Set up a repository for local GitHub Actions verification using act, so Jules can validate CI before pushing", "repo": "https://github.com/google-labs-code/jules-skills/tree/HEAD/skills/local-action-verification", "install": ["npx skills add google-labs-code/jules-skills --skill local-action-verification"], "stars": 102, "pushed": "2026-06-04T16:13:41Z", "license": "Apache-2.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.omarmhaimdat/pepe", "name": "pepe", "kind": "mcp", "official": null, "desc": "Load-test a URL, ping it by phase, ramp to find the capacity, compare runs: JSON reports, guardrails", "repo": "https://github.com/omarmhaimdat/pepe", "install": ["pypi:pepe-http", "oci:ghcr.io/omarmhaimdat/pepe:0.57.0"], "stars": 97, "pushed": "2026-11-10T08:08:38Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.RobelDev/logclaw-mcp-server", "name": "io.github.RobelDev/logclaw-mcp-server", "kind": "mcp", "official": null, "desc": "Connect AI coding tools to LogClaw incidents, logs, and anomaly detections.", "repo": "https://github.com/logclaw/logclaw", "install": ["npm:logclaw-mcp-server"], "stars": 79, "pushed": "2026-05-11T18:34:00Z", "license": null, "plat": "logclaw", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.e2e-inc/testerarmy", "name": "TesterArmy", "kind": "mcp", "official": null, "desc": "Agents that test your web and mobile app like real users, on every pull request.", "repo": "https://github.com/e2e-inc/cli", "install": ["https://tester.army/mcp"], "stars": 75, "pushed": "2026-11-12T09:35:03Z", "license": "MIT", "plat": "testerarmy", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.tester-army/testerarmy", "name": "TesterArmy", "kind": "mcp", "official": null, "desc": "Agents that test your web and mobile app like real users, on every pull request.", "repo": "https://github.com/tester-army/cli", "install": ["https://tester.army/mcp"], "stars": 75, "pushed": "2026-11-12T09:35:03Z", "license": "MIT", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.glqff/huaweicloud-devkit", "name": "HuaweiCloud DevKit (Community Preview)", "kind": "mcp", "official": null, "desc": "Community preview of HuaweiCloud DevKit MCP server (official: io.github.huaweicloud)", "repo": "https://github.com/huaweicloud/huaweicloud-devkit", "install": ["https://erx5uqu4-8931.cn-north-4-bridge.myhuaweicloud.com/mcp"], "stars": 71, "pushed": "2026-11-13T03:00:09Z", "license": "Apache-2.0", "plat": "windbg", "live": "Down · URLError: <urlopen error [Errno 11001] getaddrinfo failed> (checked 2026-11-13)"}, {"id": "mcp:io.github.lapfelix/xcodemcp", "name": "io.github.lapfelix/xcodemcp", "kind": "mcp", "official": null, "desc": "Control Xcode directly via JXA for build, test, debug operations with XCLogParser integration", "repo": "https://github.com/lapfelix/XcodeMCP", "install": ["npm:xcodemcp"], "stars": 59, "pushed": "2026-02-05T01:09:05Z", "license": "Apache-2.0", "plat": "xcode", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ooples/mcp-console-automation", "name": "io.github.ooples/mcp-console-automation", "kind": "mcp", "official": null, "desc": "MCP server for AI-driven console application automation and monitoring", "repo": "https://github.com/ooples/mcp-console-automation", "install": ["npm:mcp-console-automation"], "stars": 54, "pushed": "2026-11-04T06:14:54Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.cypress.mcp/cypress-cloud", "name": "Cypress Cloud MCP", "kind": "mcp", "official": null, "desc": "Direct access to Cypress tests results and accessibility reports in your AI workflow.", "repo": "https://github.com/cypress-io/ai-toolkit", "install": ["https://mcp.cypress.io/mcp"], "stars": 48, "pushed": "2026-11-06T19:05:41Z", "license": "MIT", "plat": "cypress cloud", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.VinvAI/vinv", "name": "Vinv", "kind": "mcp", "official": null, "desc": "Vinv runs, tests, and finds issues in your services — with zero code changes.", "repo": "https://github.com/VinvAI/VinvAI", "install": ["npm:vinv-mcp"], "stars": 48, "pushed": "2026-11-03T03:16:14Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:com.wormaceptor/wormaceptor", "name": "WormaCeptor", "kind": "mcp", "official": null, "desc": "Inspect a running Android debug app: network traffic, crashes, logs, databases and preferences", "repo": "https://github.com/wormaceptor/WormaCeptor", "install": ["npm:wormaceptor-mcp"], "stars": 46, "pushed": "2026-11-13T07:18:16Z", "license": "MIT", "plat": "android", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.uarlouski/testrail-mcp-server", "name": "io.github.uarlouski/testrail-mcp-server", "kind": "mcp", "official": null, "desc": "Connect AI assistants to TestRail: manage test cases, suites, runs, results, and attachments.", "repo": "https://github.com/uarlouski/testrail-mcp-server", "install": ["npm:@uarlouski/testrail-mcp-server"], "stars": 45, "pushed": "2026-11-08T10:29:29Z", "license": "Apache-2.0", "plat": "testrail", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Klievan/jlink-mcp", "name": "J-Link MCP", "kind": "mcp", "official": null, "desc": "Debug embedded firmware on real hardware: J-Link probes, Cortex-M faults, RTT logs, GDB.", "repo": "https://github.com/Klievan/jlink-mcp", "install": ["npm:jlink-mcp"], "stars": 43, "pushed": "2026-10-26T11:28:00Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.goldbergyoni/test-coverage-mcp", "name": "io.github.goldbergyoni/test-coverage-mcp", "kind": "mcp", "official": null, "desc": "Analyze test coverage from LCOV files - makes AI agents coverage-aware without wasting tokens", "repo": "https://github.com/goldbergyoni/test-coverage-mcp", "install": ["npm:test-coverage-mcp"], "stars": 42, "pushed": "2026-02-03T14:29:17Z", "license": null, "plat": "lcov", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Softinator-TechLabs/feedbacks", "name": "Feedbacks", "kind": "mcp", "official": null, "desc": "Visual website feedback, screenshots and team discussion for coding assistants. Self-hosted.", "repo": "https://github.com/Softinator-TechLabs/feedbacks-oss", "install": ["mcpb:https://github.com/Softinator-TechLabs/feedbacks-plugins/releases/download/v0.2.3/feedbacks-mcp-0.2.3.mcpb"], "stars": 37, "pushed": "2026-11-13T01:38:06Z", "license": "Apache-2.0", "plat": "website", "live": "Not checked (runs locally)"}, {"id": "mcp:io.qase/mcp-server", "name": "Qase Test Management", "kind": "mcp", "official": null, "desc": "Official MCP server for Qase — manage test cases, runs, suites, defects via AI tools.", "repo": "https://github.com/qase-tms/qase-mcp-server", "install": ["npm:@qase/mcp-server", "https://mcp.qase.io/mcp"], "stars": 37, "pushed": "2026-11-13T00:39:13Z", "license": "MIT", "plat": "qase", "live": "Not checked (runs locally)"}, {"id": "plugin:anthropics/claude-plugins-official:postman", "name": "postman", "kind": "claude-plugin", "official": null, "desc": "Work with Postman from your agent: bootstrap a repo's Postman setup, mock an API before it's implemented, run collection and governance checks in CI, monitor a live endpoint, deploy and debug Postman Flows, and publish generated API documentation.", "repo": "https://github.com/postmanlabs/postman-plugin.git", "install": ["claude plugin install postman@claude-plugins-official"], "stars": 34, "pushed": "2026-11-12T18:51:46Z", "license": "Apache-2.0", "plat": "postman", "live": "Not checked (runs locally)"}, {"id": "mcp:com.antithesis/snouty", "name": "snouty", "kind": "mcp", "official": null, "desc": "Launch and triage Antithesis runs, run commands at a moment of a run, and search the docs", "repo": "https://github.com/antithesishq/snouty", "install": ["npm:snouty"], "stars": 33, "pushed": "2026-11-13T02:48:04Z", "license": "Apache-2.0", "plat": "antithesis", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.GoldenSupremeSaltedFish/diffsense", "name": "DiffSense", "kind": "mcp", "official": null, "desc": "MR/PR risk audit MCP server: semantic diff + rule engine, strict read-only. Run as image or pip.", "repo": "https://github.com/GoldenSupremeSaltedFish/DiffSense", "install": ["pypi:diffsense"], "stars": 30, "pushed": "2026-10-27T01:52:39Z", "license": null, "plat": "mcp server", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.kpanuragh/xdebug", "name": "io.github.kpanuragh/xdebug", "kind": "mcp", "official": null, "desc": "MCP server for PHP Xdebug debugging with breakpoints, stepping, and variable inspection", "repo": "https://github.com/kpanuragh/xdebug-mcp", "install": ["npm:xdebug-mcp"], "stars": 28, "pushed": "2026-10-16T19:11:43Z", "license": "MIT", "plat": "php xdebug", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.msc24x/hunter", "name": "Hunter", "kind": "mcp", "official": null, "desc": "Create, manage, and judge coding contests end to end on Hunter.", "repo": "https://github.com/msc24x/hunter", "install": ["https://hunter.cambo.in/api/mcp"], "stars": 24, "pushed": "2026-11-11T11:00:33Z", "license": "NOASSERTION", "plat": "hunter", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.HeroSizy/cucumberstudio", "name": "io.github.HeroSizy/cucumberstudio", "kind": "mcp", "official": null, "desc": "MCP server for Cucumber Studio - test scenarios, action words, and execution data", "repo": "https://github.com/HeroSizy/cucumberstudio-mcp", "install": ["npm:cucumberstudio-mcp"], "stars": 22, "pushed": "2026-03-28T06:05:36Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.las-team/lastest", "name": "io.github.las-team/lastest", "kind": "mcp", "official": null, "desc": "Run visual regression tests, review diffs, and manage baselines on a Lastest instance.", "repo": "https://github.com/las-team/lastest", "install": ["npm:@lastest/mcp-server"], "stars": 22, "pushed": "2026-11-11T19:29:45Z", "license": "NOASSERTION", "plat": "lastest", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.imatza-rh/mcp-zuul", "name": "io.github.imatza-rh/mcp-zuul", "kind": "mcp", "official": null, "desc": "Zuul CI — build failure analysis, log search, pipeline status, and job configuration", "repo": "https://github.com/imatza-rh/mcp-zuul", "install": ["pypi:mcp-zuul"], "stars": 21, "pushed": "2026-11-08T09:56:09Z", "license": "Apache-2.0", "plat": "zuul ci", "live": "Not checked (runs locally)"}, {"id": "mcp:ai.orangepro/mcp", "name": "OrangePro", "kind": "mcp", "official": null, "desc": "Find test gaps, generate grounded tests, and dynamically prove behavior with mutation testing.", "repo": "https://github.com/OrangeproAI/orangepro-mcp", "install": ["npm:@orangepro/mcp-server"], "stars": 20, "pushed": "2026-11-10T20:19:55Z", "license": "MIT", "plat": "mutation testing", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.OrangeproAI/orangepro", "name": "OrangePro", "kind": "mcp", "official": null, "desc": "Find test gaps, generate grounded tests, and dynamically prove behavior with mutation testing.", "repo": "https://github.com/OrangeproAI/orangepro-mcp", "install": ["npm:@orangepro/mcp-server"], "stars": 20, "pushed": "2026-11-10T20:19:55Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "plugin:anthropics/claude-plugins-official:buildkite", "name": "buildkite", "kind": "claude-plugin", "official": null, "desc": "Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API", "repo": "https://github.com/buildkite/skills.git", "install": ["claude plugin install buildkite@claude-plugins-official"], "stars": 19, "pushed": "2026-10-22T20:44:22Z", "license": "MIT", "plat": "buildkite", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.gal-a/qikly", "name": "qikly", "kind": "mcp", "official": null, "desc": "Generates tests from acceptance criteria, then converges code with an agent that never sees them.", "repo": "https://github.com/gal-a/qikly", "install": ["pypi:qikly"], "stars": 19, "pushed": "2026-11-11T17:51:07Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:ai.momentic/momentic", "name": "Momentic", "kind": "mcp", "official": null, "desc": "Bug bash apps and PRs with Mo, review findings, and list Momentic test runs and quarantines.", "repo": "https://github.com/momentic-ai/skills", "install": ["https://mcp.momentic.ai"], "stars": 17, "pushed": "2026-11-12T06:48:41Z", "license": "NOASSERTION", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.FarzamHabibi/prodcheck", "name": "io.github.FarzamHabibi/prodcheck", "kind": "mcp", "official": null, "desc": "4,685 pre-production checks: security, performance, scale, integrations, post-launch, people.", "repo": "https://github.com/FarzamHabibi/pre-production-checklist", "install": ["npm:prodcheck"], "stars": 16, "pushed": "2026-10-19T14:27:14Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.multiplex-ai/muggleai", "name": "Muggle Works", "kind": "mcp", "official": null, "desc": "Acceptance test agent for coding agents: real-browser tests, with screenshots on the PR.", "repo": "https://github.com/multiplex-ai/muggle-ai-works", "install": ["npm:@muggleai/works"], "stars": 16, "pushed": "2026-11-13T09:34:42Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.magna-nz/aspnetcore-debugger-mcp", "name": "ASP.NET Core Debugger — MCP Server for AI Agents", "kind": "mcp", "official": null, "desc": "MCP server giving AI agents interactive .NET / ASP.NET Core debugging via netcoredbg + DAP.", "repo": "https://github.com/magna-nz/aspnetcore-debugger-mcp", "install": ["nuget:AspNetCoreDebuggerMcp"], "stars": 15, "pushed": "2026-09-14T10:26:09Z", "license": "MIT", "plat": "asp.net core", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.sgebb/bussin-mcp", "name": "io.github.sgebb/bussin-mcp", "kind": "mcp", "official": null, "desc": "MCP server for Azure Service Bus. Peek, search and replay dead-letter messages from any MCP client.", "repo": "https://github.com/sgebb/bussin", "install": ["npm:bussin-mcp"], "stars": 15, "pushed": "2026-11-11T14:51:16Z", "license": "NOASSERTION", "plat": "azure service bus", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.shreyassaw5394/dea", "name": "io.github.shreyassaw5394/dea", "kind": "mcp", "official": null, "desc": "Observe any running process from your agent. strace, py-spy, perf, lsof, tcpdump as evidence.", "repo": "https://github.com/shreyassaw5394/dea", "install": ["npm:dea-agents"], "stars": 14, "pushed": "2026-11-13T01:48:06Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.shreyassaw5394/debuganything", "name": "io.github.shreyassaw5394/debuganything", "kind": "mcp", "official": null, "desc": "Observe any running process from your agent. strace, py-spy, perf, lsof, tcpdump as evidence.", "repo": "https://github.com/shreyassaw5394/debuganything", "install": ["npm:debuganything"], "stars": 14, "pushed": "2026-11-13T01:48:06Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mshobeyri/multimeter", "name": "Multimeter", "kind": "mcp", "official": null, "desc": "Scaffold, validate, format, and run YAML .mmt API tests. Do not invent syntax.", "repo": "https://github.com/mshobeyri/multimeter", "install": ["npm:mmt-mcp"], "stars": 14, "pushed": "2026-11-11T22:25:17Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:sh.antrieb/antrieb", "name": "sh.antrieb/antrieb", "kind": "mcp", "official": null, "desc": "Validates AI infra code on real VMs. Self-corrects until it works. No containers, no sandboxes.", "repo": "https://github.com/jade-pico/antrieb-mcp-server", "install": ["https://antrieb.sh/mcp"], "stars": 14, "pushed": "2026-05-01T15:14:14Z", "license": "Apache-2.0", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.avivgerz-hue/ghost-qa", "name": "ghost-qa", "kind": "mcp", "official": null, "desc": "Autonomous headless browser QA & self-healing verification loop for AI coding agents.", "repo": "https://github.com/avivgerz-hue/ghost-qa", "install": ["npm:ghost-qa"], "stars": 13, "pushed": "2026-11-12T15:43:30Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.cocaxcode/api-testing-mcp", "name": "io.github.cocaxcode/api-testing-mcp", "kind": "mcp", "official": null, "desc": "MCP server for API testing. 35 tools: HTTP, assertions, flows, OpenAPI, collections.", "repo": "https://github.com/cocaxcode/api-testing-mcp", "install": ["npm:@cocaxcode/api-testing-mcp"], "stars": 13, "pushed": "2026-11-10T22:03:03Z", "license": "MIT", "plat": "mcp servers", "live": "Not checked (runs locally)"}, {"id": "mcp:jp.debuff/debuff", "name": "debuff", "kind": "mcp", "official": null, "desc": "Let coding agents play, test and tune your 2D web game: live state, explained errors, replays, fuzz.", "repo": "https://github.com/debuffjp/debuff", "install": ["npm:@debuffjp/mcp"], "stars": 12, "pushed": "2026-11-13T06:28:22Z", "license": "MIT", "plat": "2d web game testing", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.enessubass/mobiloop-mcp", "name": "MobiLoop", "kind": "mcp", "official": null, "desc": "Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.", "repo": "https://github.com/enessubass/mobiloop-mcp", "install": ["oci:ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15"], "stars": 12, "pushed": "2026-10-15T20:15:25Z", "license": "MIT", "plat": "appium", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Nari-Ab/agent-roast", "name": "Agent Roast", "kind": "mcp", "official": null, "desc": "Offline, read-only review that flags agent changes weakening tests, assertions, coverage or CI.", "repo": "https://github.com/Nari-Ab/agent-roast", "install": ["npm:agent-roast"], "stars": 11, "pushed": "2026-11-13T02:49:40Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Ostico/bruno-mcp-studio", "name": "Bruno MCP Studio", "kind": "mcp", "official": null, "desc": "Author, edit and run Bruno collections as files: HTTP, WebSocket, gRPC, per-request pass/fail.", "repo": "https://github.com/Ostico/bruno-mcp-studio", "install": ["npm:@ostico/bruno-mcp"], "stars": 11, "pushed": "2026-09-24T14:33:44Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.genclass-dev/genclass", "name": "GenClass", "kind": "mcp", "official": null, "desc": "Find race conditions in your web app by reordering its responses, replay one, prove the fix.", "repo": "https://github.com/genclass-dev/GenClass", "install": ["npm:@genclass/mcp"], "stars": 11, "pushed": "2026-11-13T05:26:17Z", "license": "Apache-2.0", "plat": "web app", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.howardpen9/grok-mcp", "name": "io.github.howardpen9/grok-mcp", "kind": "mcp", "official": null, "desc": "Use xAI Grok as a peer reviewer + PR gate from Claude Code, Cursor, Cline and any MCP host.", "repo": "https://github.com/howardpen9/grok-mcp", "install": ["npm:grok-cli-mcp"], "stars": 11, "pushed": "2026-07-28T04:34:27Z", "license": "MIT", "plat": "anthropic", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.segentic-lab/periscope-mcp", "name": "io.github.segentic-lab/periscope-mcp", "kind": "mcp", "official": null, "desc": "Web-app QA for AI agents: 73 Playwright tools — auth, E2E, a11y/SEO/GEO, Web Vitals + Lighthouse", "repo": "https://github.com/segentic-lab/periscope-mcp", "install": [], "stars": 10, "pushed": "2026-07-18T22:07:06Z", "license": "AGPL-3.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.testdino-inc/testdino-mcp", "name": "io.github.testdino-inc/testdino-mcp", "kind": "mcp", "official": null, "desc": "A MCP server for TestDino", "repo": "https://github.com/testdino-inc/testdino-mcp", "install": ["npm:testdino-mcp"], "stars": 10, "pushed": "2026-11-12T04:54:00Z", "license": "MIT", "plat": "testdino", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.katalon-studio/testops-mcp", "name": "Katalon True Platform MCP", "kind": "mcp", "official": null, "desc": "Katalon True Platform MCP: design tests, run with AI, upload reports, assess release readiness.", "repo": "https://github.com/katalon-labs/true-skills", "install": ["https://platform.katalon.io/mcp"], "stars": 10, "pushed": "2026-10-20T15:04:55Z", "license": "MIT", "plat": "katalon", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.BojanKovachki/recovery-probe", "name": "io.github.BojanKovachki/recovery-probe", "kind": "mcp", "official": null, "desc": "Fail reads in web and Electron test apps, inspect recovery, and compare before/after evidence.", "repo": "https://github.com/BojanKovachki/recovery-probe", "install": ["npm:recovery-probe"], "stars": 9, "pushed": "2026-11-12T12:53:46Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:ai.com.mcp/petstore", "name": "Petstore MCP Server", "kind": "mcp", "official": null, "desc": "Swagger Petstore API (v1.0.27) as MCP for testing and prototyping powered by the HAPI MCP server", "repo": "https://github.com/la-rebelion/hapimcp", "install": ["https://petstore.run.mcp.com.ai/mcp"], "stars": 9, "pushed": "2026-08-24T00:44:51Z", "license": "MIT", "plat": "swagger petstore", "live": "Live · 2353 ms · 19 tools · free to try: `getUserByName` answered without a key (checked 2026-11-13)"}, {"id": "mcp:io.github.stramanu/esp32sim-mcp", "name": "ESP32 Simulator", "kind": "mcp", "official": null, "desc": "Boot and test ESP32 firmware in a local emulator: UART asserts, buttons, virtual WiFi, screenshots.", "repo": "https://github.com/stramanu/esp32sim-mcp", "install": ["npm:esp32sim-mcp"], "stars": 8, "pushed": "2026-10-19T20:29:43Z", "license": "MIT", "plat": "esp32", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.LinuxSuRen/atest-mcp-server", "name": "io.github.LinuxSuRen/atest-mcp-server", "kind": "mcp", "official": null, "desc": "Auto-download & launch https://github.com/LinuxSuRen/atest-mcp-server", "repo": "https://github.com/LinuxSuRen/atest-mcp-server", "install": ["npm:atest-mcp-server-launcher"], "stars": 8, "pushed": "2025-11-11T23:14:29Z", "license": null, "plat": "atest", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ivanostanin/lucius-mcp", "name": "Lucius MCP", "kind": "mcp", "official": null, "desc": "MCP server for managing Allure TestOps tests, launches, plans, defects, and metadata.", "repo": "https://github.com/ivanostanin/lucius-mcp", "install": ["pypi:lucius-mcp", "oci:ghcr.io/ivanostanin/lucius-mcp:0.17.0", "mcpb:https://github.com/ivanostanin/lucius-mcp/releases/download/v0.17.0/lucius-mcp-0.17.0-uv.mcpb", "mcpb:https://github.com/ivanostanin/lucius-mcp/releases/download/v0.17.0/lucius-mcp-0.17.0-python.mcpb"], "stars": 8, "pushed": "2026-11-12T15:03:30Z", "license": "Apache-2.0", "plat": "allure testops", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.chriswu727/argus", "name": "Argus — Testing for Coding Agents", "kind": "mcp", "official": null, "desc": "Testing MCP for coding agents: exercise real user journeys, find bugs, verify them with evidence.", "repo": "https://github.com/chriswu727/argus", "install": ["pypi:argus-testing"], "stars": 7, "pushed": "2026-11-12T22:22:03Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.fastslack/e2e-runner", "name": "io.github.fastslack/e2e-runner", "kind": "mcp", "official": null, "desc": "JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.", "repo": "https://github.com/fastslack/mtw-e2e-runner", "install": ["npm:@matware/e2e-runner", "oci:docker.io/fastslack/e2e-runner-mcp:1.3.0"], "stars": 7, "pushed": "2026-06-08T01:13:25Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.gvasile29/qai-consultant-mcp", "name": "io.github.gvasile29/qai-consultant-mcp", "kind": "mcp", "official": null, "desc": "Keyless local MCP server for QA: standards retrieval, effort estimation, doc review, test analysis.", "repo": "https://github.com/gvasile29/qai-consultant", "install": ["pypi:qai-consultant-mcp"], "stars": 7, "pushed": "2026-11-09T10:14:39Z", "license": "NOASSERTION", "plat": "qa", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.OpenFault/openfault", "name": "OpenFault", "kind": "mcp", "official": null, "desc": "Self-hosted, Sentry-compatible error tracker. Agents read and triage issues over MCP.", "repo": "https://github.com/OpenFault/openfault", "install": ["https://{host}/mcp"], "stars": 7, "pushed": "2026-11-08T17:53:29Z", "license": "MIT", "plat": "sentry", "live": "Down · URLError: <urlopen error [Errno 11001] getaddrinfo failed> (checked 2026-11-13)"}, {"id": "mcp:io.github.kiranreddi/sentinel-dv", "name": "Sentinel DV", "kind": "mcp", "official": null, "desc": "MCP tools for UVM/cocotb logs, coverage, regressions, and waveform triage.", "repo": "https://github.com/kiranreddi/sentinel-dv", "install": ["pypi:sentinel-dv"], "stars": 7, "pushed": "2026-08-02T23:55:07Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:ai.testiv/mcp", "name": "TestivAI", "kind": "mcp", "official": null, "desc": "Local-first visual regression for AI agents: verdicts, diff images, explain_snapshot. No API key.", "repo": "https://github.com/testivai/testivai-oss", "install": ["npm:@testivai/mcp"], "stars": 7, "pushed": "2026-11-12T23:21:57Z", "license": "MIT", "plat": "visual regression testing", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.grahamnotgrant/blacksmith", "name": "io.github.grahamnotgrant/blacksmith", "kind": "mcp", "official": null, "desc": "MCP server for Blacksmith CI - query runs, analyze test failures, detect flaky tests.", "repo": "https://github.com/grahamnotgrant/blacksmith-mcp", "install": ["npm:blacksmith-mcp"], "stars": 6, "pushed": "2026-04-30T17:04:39Z", "license": "MIT", "plat": "blacksmith ci", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.emirmrkaljevic/behave", "name": "behave", "kind": "mcp", "official": null, "desc": "Record how any CLI behaves and check that a rewrite behaves the same (golden tests).", "repo": "https://github.com/emirmrkaljevic/behave", "install": ["mcpb:https://github.com/emirmrkaljevic/behave/releases/download/v0.1.7/behave_0.1.7_linux_amd64.mcpb", "mcpb:https://github.com/emirmrkaljevic/behave/releases/download/v0.1.7/behave_0.1.7_linux_arm64.mcpb", "mcpb:https://github.com/emirmrkaljevic/behave/releases/download/v0.1.7/behave_0.1.7_darwin_amd64.mcpb", "mcpb:https://github.com/emirmrkaljevic/behave/releases/download/v0.1.7/behave_0.1.7_darwin_arm64.mcpb"], "stars": 5, "pushed": "2026-11-12T18:54:01Z", "license": "MIT", "plat": "cli", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.appcreationsca/bumpguard", "name": "BumpGuard", "kind": "mcp", "official": null, "desc": "Reports which of your code's API usages break when you upgrade a dependency (Python, .NET, Java).", "repo": "https://github.com/appcreationsca/bumpguard-mcp", "install": ["pypi:bumpguard-mcp"], "stars": 5, "pushed": "2026-06-17T23:03:19Z", "license": "MIT", "plat": "bumpguard", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.zrk222/code-factory", "name": "io.github.zrk222/code-factory", "kind": "mcp", "official": null, "desc": "Read-only audit evidence for security, tests, native coverage, runtime failures and repair status.", "repo": "https://github.com/zrk222/code-factory", "install": ["pypi:factoryline-code-factory"], "stars": 5, "pushed": "2026-11-12T09:08:41Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.jrpool/kilotest", "name": "Kilotest", "kind": "mcp", "official": null, "desc": "Ensemble testing of web pages for accessibility, usability, and web standards", "repo": "https://github.com/jrpool/kilotest", "install": ["https://kilotest.com/mcp"], "stars": 5, "pushed": "2026-11-13T06:26:07Z", "license": "MIT", "plat": "kilotest", "live": "Live · 2509 ms · 12 tools · free to try: `listSites` answered without a key (checked 2026-11-13)"}, {"id": "mcp:io.github.microhenrio/openocd-mcp", "name": "OpenOCD Debugger", "kind": "mcp", "official": null, "desc": "Debug microcontrollers via OpenOCD: flash, breakpoints, memory, registers and variables.", "repo": "https://github.com/microhenrio/openocd-mcp", "install": ["pypi:openocd-mcp"], "stars": 5, "pushed": "2026-07-02T14:02:49Z", "license": "MIT", "plat": "microcontrollers", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.piyushpathakqa/vigilis-mcp", "name": "Vigilis", "kind": "mcp", "official": null, "desc": "Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt.", "repo": "https://github.com/piyushpathakqa/Vigilis", "install": ["npm:vigilis-mcp"], "stars": 5, "pushed": "2026-08-19T18:16:39Z", "license": "MIT", "plat": "ai tests", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.bugbug-io/mcp", "name": "BugBug", "kind": "mcp", "official": null, "desc": "BugBug test automation workflows for AI agents", "repo": "https://github.com/bugbug-io/agent-plugin", "install": ["https://mcp.bugbug.io/mcp"], "stars": 4, "pushed": "2026-11-12T06:08:06Z", "license": "MIT", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.aarwitz/tapp", "name": "io.github.aarwitz/tapp", "kind": "mcp", "official": null, "desc": "Test iOS, Android, and web apps with agent exploration, replayable flows, and CI gates.", "repo": "https://github.com/aarwitz/tapp", "install": ["npm:@aarwitz/tapp"], "stars": 4, "pushed": "2026-11-13T00:19:18Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Aboudjem/sniff", "name": "io.github.Aboudjem/sniff", "kind": "mcp", "official": null, "desc": "QA + a11y scanner: walks your running app's real user flows and reports what's broken.", "repo": "https://github.com/Aboudjem/sniff", "install": [], "stars": 4, "pushed": "2026-09-06T18:45:11Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Algiras/debugium", "name": "io.github.Algiras/debugium", "kind": "mcp", "official": null, "desc": "AI-driven live debugger with MCP bridge for Python, JS, TS, Rust, Java, C/C++", "repo": "https://github.com/Algiras/debugium", "install": ["npm:@algiras/debugium"], "stars": 4, "pushed": "2026-03-16T10:19:18Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Arjun0606/smolanalytics", "name": "io.github.Arjun0606/smolanalytics", "kind": "mcp", "official": null, "desc": "End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.", "repo": "https://github.com/Arjun0606/smolanalytics", "install": ["oci:ghcr.io/arjun0606/smolanalytics:v0.92.1", "npm:smolanalytics"], "stars": 4, "pushed": "2026-09-24T19:08:18Z", "license": "MIT", "plat": "smolanalytics", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.fullstackdegen/agent-audit", "name": "io.github.fullstackdegen/agent-audit", "kind": "mcp", "official": null, "desc": "Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot.", "repo": "https://github.com/fullstackdegen/agent-audit", "install": ["npm:@fullstackdegen/agent-audit"], "stars": 4, "pushed": "2026-09-02T02:11:31Z", "license": "MIT", "plat": "lighthouse", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.rayson-tech/nomarmy", "name": "nomArmy", "kind": "mcp", "official": null, "desc": "Sandboxed coding workers, verified: tests rerun fresh and must fail with the change reverted.", "repo": "https://github.com/rayson-tech/nomarmy", "install": ["npm:nomarmy"], "stars": 4, "pushed": "2026-11-09T21:39:58Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Quality-Max/qmax-mcp", "name": "QualityMax QA MCP", "kind": "mcp", "official": null, "desc": "Final release; the checks moved to 9lives (9l mcp). Local QA MCP: scan, inspect, repro, run tests.", "repo": "https://github.com/Quality-Max/qmax-mcp", "install": ["npm:@qualitymax/qmax-mcp"], "stars": 4, "pushed": "2026-11-09T12:36:26Z", "license": "MIT", "plat": "9lives", "live": "Not checked (runs locally)"}, {"id": "mcp:com.eclipsesource/review-guard", "name": "ReviewGuard", "kind": "mcp", "official": null, "desc": "Safety boundary for agent written GitHub PR reviews: pending and invisible, submitting is opt-in", "repo": "https://github.com/eclipsesource/review-guard", "install": ["npm:@eclipsesource/review-guard-mcp"], "stars": 4, "pushed": "2026-11-12T12:29:00Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Zeraissh/stm32-gdb-mcp", "name": "STM32 GDB Debugger", "kind": "mcp", "official": null, "desc": "Debug STM32 firmware on real hardware via GDB + OpenOCD/ST-Link/J-Link with decoded results.", "repo": "https://github.com/Zeraissh/stm32-gdb-mcp", "install": ["pypi:stm32-gdb-mcp"], "stars": 4, "pushed": "2026-10-24T07:13:44Z", "license": "MIT", "plat": "stm32", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.MikhailHal/ariadne", "name": "ariadne", "kind": "mcp", "official": null, "desc": "Returns only the unit tests affected by your current Kotlin/Android code changes.", "repo": "https://github.com/MikhailHal/ariadne", "install": ["oci:ghcr.io/mikhailhal/ariadne:0.4.0"], "stars": 3, "pushed": "2026-09-20T15:46:42Z", "license": "Apache-2.0", "plat": "kotlin", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.jarbon/carbon", "name": "CARBON", "kind": "mcp", "official": null, "desc": "AI testing harness with Jay: risk-based checks, bug investigation, and local evidence reports.", "repo": "https://github.com/jarbon/carbon-free", "install": ["npm:@testers-ai/carbon-mcp"], "stars": 3, "pushed": "2026-11-02T10:08:49Z", "license": "MIT", "plat": "carbon", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.weskerllc/cronicorn-mcp-server", "name": "Cronicorn", "kind": "mcp", "official": null, "desc": "Manage adaptive cron jobs and HTTP endpoint scheduling via AI assistants.", "repo": "https://github.com/weskerllc/cronicorn", "install": ["npm:@cronicorn/mcp-server"], "stars": 3, "pushed": "2026-02-13T19:26:26Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.DefectDojo/defectdojo-mcp", "name": "DefectDojo", "kind": "mcp", "official": null, "desc": "Search, triage and import findings in DefectDojo through its REST API v2.", "repo": "https://github.com/DefectDojo/defectdojo-mcp", "install": ["pypi:defectdojo-mcp-server", "oci:ghcr.io/defectdojo/defectdojo-mcp:0.1.0"], "stars": 3, "pushed": "2026-11-12T05:14:59Z", "license": "BSD-3-Clause", "plat": "defectdojo", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.DiffCI/diffci", "name": "DiffCI", "kind": "mcp", "official": null, "desc": "Verification for AI coding agents: runs the tests and checks a change affects, with a receipt.", "repo": "https://github.com/DiffCI/core", "install": ["npm:@diffci.com/diffci", "https://diffci.com/mcp/v1"], "stars": 3, "pushed": "2026-11-12T16:41:21Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.sekharsdet/five46", "name": "five46", "kind": "mcp", "official": null, "desc": "BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.", "repo": "https://github.com/sekharsdet/five46", "install": ["npm:five46"], "stars": 3, "pushed": "2026-10-19T12:49:16Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mshegolev/allure-testops-mcp", "name": "io.github.mshegolev/allure-testops-mcp", "kind": "mcp", "official": null, "desc": "Allure TestOps MCP — projects, launches, test cases, test results via REST API.", "repo": "https://github.com/mshegolev/allure-testops-mcp", "install": ["pypi:allure-testops-mcp"], "stars": 3, "pushed": "2026-10-29T21:07:30Z", "license": "MIT", "plat": "allure testops", "live": "Not checked (runs locally)"}, {"id": "mcp:com.qualityclouds/mcp-server-qualityclouds", "name": "LiveCheck AI", "kind": "mcp", "official": null, "desc": "Secure MCP runtime server for scanning and autofixing code issues", "repo": "https://github.com/qualityclouds/qualityclouds", "install": ["https://mcp.qualityclouds.com/mcp", "https://mcp.qualityclouds.com/mcp"], "stars": 3, "pushed": "2026-10-14T09:41:45Z", "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.SpecLeft/specleft", "name": "SpecLeft", "kind": "mcp", "official": null, "desc": "Python intent tracing MCP: map specs to pytest tests, monitor implementation progress, offline-only.", "repo": "https://github.com/SpecLeft/specleft", "install": ["pypi:specleft"], "stars": 3, "pushed": "2026-04-15T16:37:14Z", "license": "Apache-2.0", "plat": "pytest", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.barissozudogru/test-intel", "name": "Test Intel", "kind": "mcp", "official": null, "desc": "Coverage analysis, untested function detection and complexity scoring for TS and JS.", "repo": "https://github.com/barissozudogru/test-intel-mcp", "install": ["npm:@barissozudogru/test-intel-mcp"], "stars": 3, "pushed": "2026-11-11T12:14:46Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Huldoser/test-inventory", "name": "Test Inventory", "kind": "mcp", "official": null, "desc": "Discover tests, skip reasons and affected tests, and compare inventories without running tests.", "repo": "https://github.com/Huldoser/test-inventory-mcp", "install": ["npm:test-inventory-mcp"], "stars": 3, "pushed": "2026-11-13T13:13:58Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Karzone/TestAtlas.Mcp", "name": "TestAtlas", "kind": "mcp", "official": null, "desc": "Semantic map of a .NET test-automation solution for AI agents — search, impact, endpoints", "repo": "https://github.com/Karzone/TestAtlas", "install": ["nuget:TestAtlas.Mcp"], "stars": 3, "pushed": "2026-10-26T20:34:43Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.kikutano/tinyprobe", "name": "tinyprobe", "kind": "mcp", "official": null, "desc": "API testing in YAML: inspect, call and run endpoints and workflows, with the guide to write them.", "repo": "https://github.com/kikutano/tinyprobe", "install": ["oci:ghcr.io/kikutano/tinyprobe:0.25.0"], "stars": 3, "pushed": "2026-11-10T12:22:15Z", "license": "GPL-3.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.anzar-ahsan-commits/api-shakedown", "name": "API Shakedown", "kind": "mcp", "official": null, "desc": "Turn an OpenAPI spec into WireMock stubs, contract tests and chaos scenarios, on local LLMs.", "repo": "https://github.com/anzar-ahsan-commits/api-shakedown", "install": ["pypi:api-shakedown", "oci:ghcr.io/anzar-ahsan-commits/api-shakedown:0.1.3"], "stars": 2, "pushed": "2026-11-01T04:18:35Z", "license": "MIT", "plat": "wiremock", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ksgisang/awt", "name": "AWT (AI Watch Tester)", "kind": "mcp", "official": null, "desc": "AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.", "repo": "https://github.com/ksgisang/awt-skill", "install": ["pypi:aat-devqa"], "stars": 2, "pushed": "2026-11-06T12:46:30Z", "license": "AGPL-3.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.De-Ioannidis/carmaker-mcp", "name": "CarMaker", "kind": "mcp", "official": null, "desc": "Drive IPG CarMaker for Simulink: run test runs, read results, edit vehicle data and parameters.", "repo": "https://github.com/De-Ioannidis/carmaker-mcp", "install": ["pypi:carmaker-mcp"], "stars": 2, "pushed": "2026-11-01T16:54:51Z", "license": "MIT", "plat": "simulink", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.dimitr-io/carmaker-mcp", "name": "CarMaker", "kind": "mcp", "official": null, "desc": "Drive IPG CarMaker for Simulink: run test runs, read results, edit vehicle data and parameters.", "repo": "https://github.com/dimitr-io/carmaker-mcp", "install": ["pypi:carmaker-mcp"], "stars": 2, "pushed": "2026-11-01T16:54:51Z", "license": "MIT", "plat": "simulink", "live": "Not checked (runs locally)"}, {"id": "mcp:dev.endform/mcp", "name": "Endform", "kind": "mcp", "official": null, "desc": "Find failing, flaky, and slow Playwright tests on Endform and keep your suite healthy as it grows.", "repo": "https://github.com/endformdev/skills", "install": ["npm:endform", "https://endform.dev/mcp"], "stars": 2, "pushed": "2026-11-12T13:03:17Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.fluttersdk/telescope", "name": "FlutterSDK Telescope", "kind": "mcp", "official": null, "desc": "Inspect a running Flutter app: HTTP traffic, logs, exceptions and queries. Debug only.", "repo": "https://github.com/fluttersdk/telescope", "install": [], "stars": 2, "pushed": "2026-10-12T23:02:38Z", "license": "MIT", "plat": "flutter", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.arnavranjan005/mcp-telemetry-server", "name": "io.github.arnavranjan005/mcp-telemetry-server", "kind": "mcp", "official": null, "desc": "Streams live progress from mcp-telemetry-sdk-instrumented tools to any connected MCP client.", "repo": "https://github.com/arnavranjan005/mcp-telemetry", "install": ["npm:mcp-telemetry-server"], "stars": 2, "pushed": "2026-10-07T13:24:18Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.astrogilda/waitbus", "name": "io.github.astrogilda/waitbus", "kind": "mcp", "official": null, "desc": "Workstation-local event bus: agents wait on or emit CI/pytest/Docker/filesystem events, no polling.", "repo": "https://github.com/astrogilda/waitbus", "install": ["pypi:waitbus"], "stars": 2, "pushed": "2026-11-09T05:43:22Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Hyeonu-Cha/dotnet-coverage-mcp", "name": "io.github.Hyeonu-Cha/dotnet-coverage-mcp", "kind": "mcp", "official": null, "desc": "MCP server for .NET coverage: run tests, parse Cobertura, find uncovered branches, append tests.", "repo": "https://github.com/Hyeonu-Cha/dotnet-coverage-mcp", "install": ["nuget:dotnet-coverage-mcp"], "stars": 2, "pushed": "2026-09-20T20:54:38Z", "license": "MIT", "plat": "net", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.magnusmalm/smolmux-gdb-mcp", "name": "io.github.magnusmalm/smolmux-gdb-mcp", "kind": "mcp", "official": null, "desc": "GDB/SWD MCP server over a smolmux broker: breakpoints, memory, Cortex-M fault decode, board probing.", "repo": "https://github.com/magnusmalm/smolmux", "install": [], "stars": 2, "pushed": "2026-10-22T07:05:57Z", "license": "MIT", "plat": "gdb", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.magnusmalm/smolmux-mcp", "name": "io.github.magnusmalm/smolmux-mcp", "kind": "mcp", "official": null, "desc": "Serial console MCP server over a smolmux broker: shared UART, send/expect, history, boot stages.", "repo": "https://github.com/magnusmalm/smolmux", "install": [], "stars": 2, "pushed": "2026-10-22T07:05:57Z", "license": "MIT", "plat": "uart", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ormastes/t32-mcp-server", "name": "io.github.ormastes/t32-mcp-server", "kind": "mcp", "official": null, "desc": "TRACE32 debugger MCP — session, dialog, field, history, resource inspection", "repo": "https://github.com/ormastes/simple", "install": ["npm:@simple-lang/t32-mcp-server"], "stars": 2, "pushed": "2026-11-13T11:00:16Z", "license": "NOASSERTION", "plat": "trace32", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.prufa-dev/prufa-mcp", "name": "io.github.prufa-dev/prufa-mcp", "kind": "mcp", "official": null, "desc": "The full Prufa QA agent over MCP: audits, flows, monitors, gremlin chaos, discovery.", "repo": "https://github.com/prufa-dev/prufa-mcp", "install": ["pypi:prufa-mcp"], "stars": 2, "pushed": "2026-07-01T20:05:21Z", "license": "Apache-2.0", "plat": "prufa", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ej-technologies/jprofiler-mcp", "name": "JProfiler", "kind": "mcp", "official": null, "desc": "Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more.", "repo": "https://github.com/ej-technologies/jprofiler-mcp", "install": ["npm:@ej-technologies/jprofiler-mcp"], "stars": 2, "pushed": "2026-11-13T09:28:04Z", "license": "MIT", "plat": "jprofiler", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.teralabx/logbear", "name": "LogBear", "kind": "mcp", "official": null, "desc": "Local dev server logs for coding agents: errors, runs and diffs as read-only SQL.", "repo": "https://github.com/teralabx/logbear", "install": ["cargo:logbear-mcp"], "stars": 2, "pushed": "2026-11-10T07:47:56Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.vulinh1704/mantis", "name": "Mantis", "kind": "mcp", "official": null, "desc": "Real-browser UI checks and speed audits for coding agents, catching fixes that only hide the bug.", "repo": "https://github.com/vulinh1704/mantis", "install": ["npm:@vulinh1704/mantis"], "stars": 2, "pushed": "2026-11-01T04:11:48Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.xsignon-secure/E2E", "name": "Playwright E2E MCP", "kind": "mcp", "official": null, "desc": "Diagnose and fix Playwright tests (TS, pytest): CI reports, traces, verified fixes, flaky verdicts.", "repo": "https://github.com/xsignon-secure/E2E", "install": ["npm:playwright-e2e-mcp"], "stars": 2, "pushed": "2026-11-11T22:13:05Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.SpeedosDK/predictive-debugger", "name": "Predictive Debugger", "kind": "mcp", "official": null, "desc": "Predicts where JavaScript and TypeScript code will fail at runtime, for coding agents.", "repo": "https://github.com/SpeedosDK/predictive-debugger", "install": ["npm:predictive-debugger"], "stars": 2, "pushed": "2026-09-27T12:31:09Z", "license": "MIT", "plat": "javascript/typescript", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.aliengineering-byte/resilireplay", "name": "ResiliReplay", "kind": "mcp", "official": null, "desc": "Run bounded, deterministic MCP reliability tests and generate executable regressions.", "repo": "https://github.com/aliengineering-byte/resilireplay", "install": ["npm:resilireplay"], "stars": 2, "pushed": "2026-11-01T06:29:27Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.eyrockscript/test-card-hub", "name": "Test Card Hub", "kind": "mcp", "official": null, "desc": "Sandbox test cards, Playwright tests, real-card scanner and decline codes for LATAM gateways.", "repo": "https://github.com/eyrockscript/test-card-hub", "install": ["npm:test-card-hub-mcp"], "stars": 2, "pushed": "2026-11-12T17:39:25Z", "license": "MIT", "plat": "latam gateways", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.jarbon/carbon-lite", "name": "Testers.ai CARBON Test Harness Lite", "kind": "mcp", "official": null, "desc": "Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.", "repo": "https://github.com/jarbon/carbon-lite", "install": ["mcpb:https://github.com/jarbon/carbon-lite/releases/download/mcp-v0.1.0/carbon-lite-mcp-0.1.0.mcpb"], "stars": 2, "pushed": "2026-11-02T10:08:52Z", "license": "MIT", "plat": "testers.ai", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Backas03/vitaminmcp", "name": "VitaminMCP", "kind": "mcp", "official": null, "desc": "Test Minecraft plugins end to end: drive a real Paper server and real protocol bots.", "repo": "https://github.com/Backas03/VitaminMCP", "install": ["npm:vitaminmcp"], "stars": 2, "pushed": "2026-10-20T15:13:41Z", "license": "MIT", "plat": "minecraft", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.hpdkhoa/weaponlab-mcp", "name": "Weapon Lab", "kind": "mcp", "official": null, "desc": "Find and fix first-person weapon bugs behind a gate: your game's probe measures, the Gate judges", "repo": "https://github.com/hpdkhoa/weaponlab-mcp", "install": ["pypi:weaponlab-mcp"], "stars": 2, "pushed": "2026-11-01T06:22:52Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:com.99tests/mcp", "name": "99tests", "kind": "mcp", "official": null, "desc": "Order human-run real-device app tests from your coding agent; verified bugs return as fix prompts.", "repo": "https://github.com/99tests/mcp-server", "install": ["https://99tests.com/api/mcp"], "stars": 1, "pushed": "2026-11-13T07:13:17Z", "license": "MIT", "plat": "99tests", "live": "Live · 3276 ms · 5 tools · free to try: `get_sample_report` answered without a key (checked 2026-11-13)"}, {"id": "mcp:io.github.fantasyce/agent-runtime-proof", "name": "Agent Runtime Proof", "kind": "mcp", "official": null, "desc": "Verify whether a local Agent or MCP runtime matches an approved artifact.", "repo": "https://github.com/fantasyce/agent-runtime-proof", "install": ["mcpb:https://github.com/fantasyce/agent-runtime-proof/releases/download/v1.1.0/agent-runtime-proof_1.1.0.mcpb"], "stars": 1, "pushed": "2026-09-13T01:09:25Z", "license": "Apache-2.0", "plat": "agent", "live": "Not checked (runs locally)"}, {"id": "mcp:io.usefulapi/atera", "name": "Atera MCP by usefulapi", "kind": "mcp", "official": null, "desc": "Check devices, alerts and tickets in Atera, and open tickets, comment or resolve alerts.", "repo": "https://github.com/m190/usefulapi-mcp", "install": ["https://atera.usefulapi.io/mcp"], "stars": 1, "pushed": "2026-11-13T06:39:36Z", "license": "MIT", "plat": "atera", "live": "Live · 403 ms · 20 tools · `atera_get_agent` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:io.usefulapi/clockify", "name": "Clockify MCP by usefulapi", "kind": "mcp", "official": null, "desc": "Track time in Clockify: time entries, projects, clients, tags and reports; start, stop and log time.", "repo": "https://github.com/m190/usefulapi-mcp", "install": ["https://clockify.usefulapi.io/mcp"], "stars": 1, "pushed": "2026-11-13T06:39:36Z", "license": "MIT", "plat": "clockify", "live": "Live · 1113 ms · 21 tools · `clockify_list_tags` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:io.usefulapi/codecov", "name": "Codecov MCP by usefulapi", "kind": "mcp", "official": null, "desc": "Read Codecov coverage reports, commits, pulls, flags and components.", "repo": "https://github.com/m190/usefulapi-mcp", "install": ["https://codecov.usefulapi.io/mcp"], "stars": 1, "pushed": "2026-11-13T06:39:36Z", "license": "MIT", "plat": "codecov", "live": "Live · 1338 ms · 24 tools · `codecov_get_pull` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:com.maxoperf/maxoperf", "name": "com.maxoperf/maxoperf", "kind": "mcp", "official": null, "desc": "Load & browser performance testing — drive MaxoPerf from your AI agent with your API key.", "repo": "https://github.com/maxoperf/mcp", "install": ["https://app.maxoperf.com/mcp"], "stars": 1, "pushed": "2026-07-22T23:15:42Z", "license": null, "plat": "maxoperf", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.JeanFrancoisGagne/crapkit", "name": "crapkit", "kind": "mcp", "official": null, "desc": "Twelve tools to inspect CRAP scores, find work, and check edited functions against their ceiling.", "repo": "https://github.com/JeanFrancoisGagne/crapkit", "install": ["pypi:crapkit"], "stars": 1, "pushed": "2026-11-11T15:38:53Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Bannawat01/devdoctor", "name": "DevDoctor", "kind": "mcp", "official": null, "desc": "Read-only local diagnostics for Rust, Node, Docker, ports, and environment configuration.", "repo": "https://github.com/Bannawat01/DevDoctor", "install": ["cargo:devdoctor-mcp"], "stars": 1, "pushed": "2026-11-08T13:59:39Z", "license": "Apache-2.0", "plat": "local diagnostics", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.FlyTrap-QA/mcp", "name": "FlyTrap", "kind": "mcp", "official": null, "desc": "FlyTrap mobile QA results for agents: bugs with evidence, screen graphs, network hosts, SDKs, diffs.", "repo": "https://github.com/FlyTrap-QA/mcp", "install": ["npm:@flytrap-qa/mcp"], "stars": 1, "pushed": "2026-11-09T20:35:33Z", "license": "MIT", "plat": "mobile", "live": "Not checked (runs locally)"}, {"id": "mcp:sh.gaffer/mcp", "name": "Gaffer", "kind": "mcp", "official": null, "desc": "Test analytics for AI agents: test history, flaky tests, failure clusters, coverage.", "repo": "https://github.com/gaffer-sh/mcp", "install": ["npm:@gaffer-sh/mcp", "https://app.gaffer.sh/mcp"], "stars": 1, "pushed": "2026-11-12T19:44:37Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.sanjoy1234/gauntlex", "name": "GAUNTLEX", "kind": "mcp", "official": null, "desc": "Concurrent Builder + Breaker agents generate code and adversarial tests at once, gated in CI.", "repo": "https://github.com/sanjoy1234/gauntlex", "install": ["pypi:gauntlex-ai"], "stars": 1, "pushed": "2026-10-04T04:45:40Z", "license": "MIT", "plat": "ci", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.0xmortuex/gdbstub-mcp", "name": "io.github.0xmortuex/gdbstub-mcp", "kind": "mcp", "official": null, "desc": "Debug kernels through QEMU's gdbstub with no gdb binary - and explain triple faults.", "repo": "https://github.com/0xmortuex/gdbstub-mcp", "install": ["pypi:gdbstub-mcp"], "stars": 1, "pushed": "2026-10-11T12:07:50Z", "license": "MIT", "plat": "qemu", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.acabala/apidog-tests-mcp", "name": "io.github.acabala/apidog-tests-mcp", "kind": "mcp", "official": null, "desc": "MCP server for managing Apidog test cases, scenarios, suites, and test data", "repo": "https://github.com/acabala/apidog-tests-mcp", "install": ["npm:@acabala/apidog-tests-mcp"], "stars": 1, "pushed": "2026-08-12T20:01:51Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Akkshay10/MCPClientMock", "name": "io.github.Akkshay10/MCPClientMock", "kind": "mcp", "official": null, "desc": "MCP server for James Bloom MockServer - create expectations, verify requests, and manage mock state", "repo": "https://github.com/Akkshay10/MCPClientMock", "install": ["npm:mockserver-mcp"], "stars": 1, "pushed": "2025-12-17T04:27:05Z", "license": "MIT", "plat": "james bloom mockserver", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.cyanheads/evals-mcp-server", "name": "io.github.cyanheads/evals-mcp-server", "kind": "mcp", "official": null, "desc": "Author verifiable eval records through a draft→review→revise→submit loop with enforced graders.", "repo": "https://github.com/cyanheads/evals-mcp-server", "install": ["npm:@cyanheads/evals-mcp-server", "npm:@cyanheads/evals-mcp-server"], "stars": 1, "pushed": "2026-10-17T23:14:07Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.frozo-ai/edgegate-mcp", "name": "io.github.frozo-ai/edgegate-mcp", "kind": "mcp", "official": null, "desc": "Regression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.", "repo": "https://github.com/frozo-ai/edgegate-mcp", "install": ["npm:edgegate-mcp"], "stars": 1, "pushed": "2026-10-09T11:23:31Z", "license": "MIT", "plat": "snapdragon and jetson", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.jmshinhwa/coverage-gate-lint", "name": "io.github.jmshinhwa/coverage-gate-lint", "kind": "mcp", "official": null, "desc": "Finds the coverage gates in your repo that can never fail a build", "repo": "https://github.com/jmshinhwa/readystack-themes", "install": ["npm:@readystack/coverage-gate-lint"], "stars": 1, "pushed": "2026-11-02T04:17:54Z", "license": "NOASSERTION", "plat": "code coverage", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.jmshinhwa/pytest-deprecation-lint", "name": "io.github.jmshinhwa/pytest-deprecation-lint", "kind": "mcp", "official": null, "desc": "Marks the lines in your test suite that current pytest no longer runs — and the config keys it silen", "repo": "https://github.com/jmshinhwa/readystack-themes", "install": ["npm:@readystack/pytest-deprecation-lint"], "stars": 1, "pushed": "2026-11-02T04:17:54Z", "license": "NOASSERTION", "plat": "pytest", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.meta-taro/git-qa", "name": "io.github.meta-taro/git-qa", "kind": "mcp", "official": null, "desc": "Open-source human-in-the-loop QA runner: an AI agent works the test sheet, a person signs off.", "repo": "https://github.com/meta-taro/git-qa", "install": [], "stars": 1, "pushed": "2026-11-13T04:30:21Z", "license": "MIT", "plat": "ai agent testing", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.miroslavmyrha/cypress-mcp", "name": "io.github.miroslavmyrha/cypress-mcp", "kind": "mcp", "official": null, "desc": "Shows an AI assistant the last cypress run: command log, errors, screenshots, DOM of failed tests.", "repo": "https://github.com/miroslavmyrha/cypress-mcp", "install": ["npm:@miroslavmyrha/cypress-mcp"], "stars": 1, "pushed": "2026-10-13T13:02:32Z", "license": "MIT", "plat": "cypress", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.pamela-0/safe-fix-mcp", "name": "io.github.pamela-0/safe-fix-mcp", "kind": "mcp", "official": null, "desc": "Finds real dead code and proposes a safe, test-gated branch+PR to remove it.", "repo": "https://github.com/pamela-0/safe-fix-mcp", "install": ["pypi:safe-fix-mcp"], "stars": 1, "pushed": "2026-08-21T21:51:16Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ryudi84/api-tester", "name": "io.github.ryudi84/api-tester", "kind": "mcp", "official": null, "desc": "MCP server for API testing: HTTP requests, cURL generation, health checks.", "repo": "https://github.com/ryudi84/sovereign-mcp-servers", "install": ["npm:sovereign-api-tester-mcp"], "stars": 1, "pushed": "2026-02-25T20:13:35Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.vschernoff/forge-test-mcp", "name": "io.github.vschernoff/forge-test-mcp", "kind": "mcp", "official": null, "desc": "Runs Foundry tests and builds; returns compact, structured failures to AI coding agents", "repo": "https://github.com/vschernoff/forge-test-mcp", "install": ["npm:forge-test-mcp"], "stars": 1, "pushed": "2026-11-11T17:46:40Z", "license": "MIT", "plat": "foundry", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.raimondasl/isitdone", "name": "isitdone", "kind": "mcp", "official": null, "desc": "Make a coding agent prove it: run the repo's real tests, typecheck and lint before it says done.", "repo": "https://github.com/raimondasl/isitdone", "install": ["npm:@aivolution/isitdone"], "stars": 1, "pushed": "2026-10-20T14:41:34Z", "license": "MIT", "plat": "code", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.kengrary/jvmind-mat", "name": "JVMind MAT Heap Dump Analyzer", "kind": "mcp", "official": null, "desc": "Analyze Java heap dumps locally with Eclipse MAT, including live JVM capture.", "repo": "https://github.com/kengrary/web_mat_project", "install": ["pypi:jvmind-mat-mcp"], "stars": 1, "pushed": "2026-10-23T14:26:06Z", "license": "MIT", "plat": "java", "live": "Not checked (runs locally)"}, {"id": "mcp:com.mendapi/mendapi", "name": "mendapi", "kind": "mcp", "official": null, "desc": "Detect API breaking changes, scan your codebase for impact, and draft the fix. Runs locally.", "repo": "https://github.com/mendapi/mendapi", "install": ["npm:mendapi"], "stars": 1, "pushed": "2026-08-05T08:39:03Z", "license": "AGPL-3.0", "plat": "mendapi", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.prodpoke/prodpoke-mcp", "name": "ProdPoke", "kind": "mcp", "official": null, "desc": "AI QA tester — real browsers scan sites for bugs, SEO, perf, and accessibility issues via chat.", "repo": "https://github.com/prodpoke/prodpoke-mcp", "install": ["https://prodpoke.com/v1/mcp"], "stars": 1, "pushed": "2026-04-22T13:59:21Z", "license": "MIT", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.ProvarTesting/provar", "name": "Provar MCP Server", "kind": "mcp", "official": null, "desc": "Provar MCP: AI-powered Salesforce test automation. Generate, validate, migrate, and run tests.", "repo": "https://github.com/ProvarTesting/provardx-cli", "install": ["npm:@provartesting/provardx-cli"], "stars": 1, "pushed": "2026-07-24T12:14:30Z", "license": "BSD-3-Clause", "plat": "salesforce", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.NJ-Burrito/qa-wrap-bridge", "name": "QA Wrap bridge", "kind": "mcp", "official": null, "desc": "Read-only MCP server: a coding agent reads test sessions recorded in QA Wrap. Local only.", "repo": "https://github.com/NJ-Burrito/QA-Wrap", "install": ["npm:qa-wrap-bridge"], "stars": 1, "pushed": "2026-11-12T14:48:59Z", "license": "MIT", "plat": "qa wrap", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.OpenPowerShift/raptor-studio", "name": "Raptor Studio", "kind": "mcp", "official": null, "desc": "Build, validate and simulate reliability block diagrams (RAM analysis) from an AI assistant.", "repo": "https://github.com/openpowershift/RaptorStudio", "install": ["pypi:raptor-studio-mcp"], "stars": 1, "pushed": "2026-11-12T12:00:27Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.compscidr/sair", "name": "SAIR", "kind": "mcp", "official": null, "desc": "Run Android tests on real phones, or lease one: install, shell, screenshot, logcat.", "repo": "https://github.com/compscidr/sair", "install": ["mcpb:https://github.com/compscidr/sair/releases/download/v0.1.36/sair-mcp.mcpb"], "stars": 1, "pushed": "2026-11-05T04:20:56Z", "license": "Apache-2.0", "plat": "android", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.igor-holt/sear", "name": "SEAR", "kind": "mcp", "official": null, "desc": "Benchmark-first release surface with a read-only MCP endpoint and operator CLI.", "repo": "https://github.com/igor-holt/sear", "install": ["https://sear.genesisconductor.io/api/mcp"], "stars": 1, "pushed": "2026-09-24T08:32:40Z", "license": null, "plat": "sear", "live": "Down · ValueError: no JSON-RPC response (checked 2026-11-13)"}, {"id": "mcp:io.github.TranQui004/signalint", "name": "Signalint", "kind": "mcp", "official": null, "desc": "Local stdio MCP server for cached, loop-aware JS/TS diagnostics (Oxlint, tsc, Biome, ESLint).", "repo": "https://github.com/TranQui004/signalint", "install": ["npm:signalint-mcp"], "stars": 1, "pushed": "2026-11-06T15:34:20Z", "license": "MIT", "plat": "signalint", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.igorolv/sonar-mcp-server", "name": "Sonar MCP Server", "kind": "mcp", "official": null, "desc": "Read-only SonarQube Community Build access for AI agents: issues, hotspots, rules, code snippets", "repo": "https://github.com/igorolv/sonar-mcp-server", "install": ["oci:ghcr.io/igorolv/sonar-mcp-server:0.1.0"], "stars": 1, "pushed": "2026-09-18T11:21:03Z", "license": "MIT", "plat": "sonarqube", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.tactual-dev/tactual", "name": "Tactual", "kind": "mcp", "official": null, "desc": "Screen-reader navigation cost analyzer. Scores AT user effort to find, reach, and operate content.", "repo": "https://github.com/tactual-dev/tactual", "install": ["npm:tactual"], "stars": 1, "pushed": "2026-06-28T17:53:23Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.kioie/tiny-go-mcp", "name": "Tiny Go MCP Server", "kind": "mcp", "official": null, "desc": "Demo stdio MCP server (tools, resource, prompt) for tinymcp tests—not production use.", "repo": "https://github.com/kioie/tiny-go-mcp-server", "install": ["oci:ghcr.io/kioie/tiny-go-mcp:1.1.2"], "stars": 1, "pushed": "2026-09-16T04:33:23Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.davidscotttufts/tracegate-ci", "name": "Tracegate CI", "kind": "mcp", "official": null, "desc": "Local CI broker and test-impact ledger for coding agents: queue, lane modes and red-run packets.", "repo": "https://github.com/davidscotttufts/tracegate-ci", "install": ["npm:tracegate-ci"], "stars": 1, "pushed": "2026-11-11T17:11:48Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.HMAKT99/vedha", "name": "Vedha", "kind": "mcp", "official": null, "desc": "Browser testing on Playwright that checks the server, not just the screen, before it reports a pass.", "repo": "https://github.com/HMAKT99/VEDHA", "install": ["npm:@vedhajs/mcp"], "stars": 1, "pushed": "2026-11-10T13:36:07Z", "license": "Apache-2.0", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "mcp:ai.verificate/mcp", "name": "Verificate MCP", "kind": "mcp", "official": null, "desc": "Merge gate for AI-written code: deterministic vetoes plus a Claude Haiku 5.5 review. No signup.", "repo": "https://github.com/VerificateAI/verificate-mcp-quickstart", "install": ["https://mcp.verificate.ai/mcp"], "stars": 1, "pushed": "2026-11-10T05:47:22Z", "license": "MIT", "plat": "verificate", "live": "Live · 1464 ms · 5 tools (checked 2026-11-13)"}, {"id": "mcp:dev.3tg/mcp", "name": "3TG Test Generation", "kind": "mcp", "official": null, "desc": "3rd Generation Testing (3TG) — generate deterministic test suites from Markdown spec tables via MCP.", "repo": null, "install": ["https://mcp.3tg.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Down · HTTP 404 (checked 2026-11-13)"}, {"id": "mcp:com.a2awire/benchmark-r4-qa035-fresh-1103", "name": "A2AWire Benchmark: R4 QA-035 Fresh Probe Capitals", "kind": "mcp", "official": null, "desc": "Free to compete: testnet faucet funds everything. QA-035 retest: fresh benchmark for…", "repo": "https://github.com/ee324/a2awire", "install": ["https://a2awire.com/mcp/benchmarks/r4-qa035-fresh-1103/http"], "stars": null, "pushed": null, "license": null, "plat": "a2awire", "live": "Live · 1747 ms · 29 tools · `check_earnings` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:com.a2awire/benchmark-r5-qa033-shortfall-1103", "name": "A2AWire Benchmark: R5 QA-033 shortfall probe capitals", "kind": "mcp", "official": null, "desc": "Free to compete: testnet faucet funds everything. R5 QA-033 shortfall probe capitals", "repo": "https://github.com/ee324/a2awire", "install": ["https://a2awire.com/mcp/benchmarks/r5-qa033-shortfall-1103/http"], "stars": null, "pushed": null, "license": null, "plat": "a2awire", "live": "Live · 1216 ms · 29 tools · `check_earnings` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:com.a2awire/benchmark-support-agent-trials", "name": "A2AWire Benchmark: Support Agent Trials", "kind": "mcp", "official": null, "desc": "Free to compete: testnet faucet funds everything. Support trials. Get scored, get hired.", "repo": "https://github.com/ee324/a2awire", "install": ["https://a2awire.com/mcp/benchmarks/support-agent-trials/http"], "stars": null, "pushed": null, "license": null, "plat": "a2awire", "live": "Live · 1716 ms · 29 tools · `check_earnings` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:com.a2awire/benchmark-support-agent-trials-hard", "name": "A2AWire Benchmark: Support Agent Trials - Hard Mode", "kind": "mcp", "official": null, "desc": "Free to compete: testnet faucet funds everything. Hard support trials. Scored, ranked.", "repo": "https://github.com/ee324/a2awire", "install": ["https://a2awire.com/mcp/benchmarks/support-agent-trials-hard/http"], "stars": null, "pushed": null, "license": null, "plat": "a2awire", "live": "Live · 1894 ms · 29 tools · `check_earnings` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:ac.snag/snag", "name": "ac.snag/snag", "kind": "mcp", "official": null, "desc": "Gives your coding agent the captured console, network, replay and screenshot evidence for a bug.", "repo": null, "install": ["https://mcp.snag.ac/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.ankitsxchdeva/account-pool-mcp", "name": "Account Pool", "kind": "mcp", "official": null, "desc": "Exclusive, crash-safe leases on a pool of test accounts for parallel agent QA runs.", "repo": "https://github.com/ankitsxchdeva/account-pool-mcp", "install": ["npm:account-pool-mcp"], "stars": 0, "pushed": "2026-09-11T19:27:03Z", "license": "MIT", "plat": "account pool", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.logi-cmd/agent-guardrails", "name": "Agent Guardrails", "kind": "mcp", "official": null, "desc": "Merge gates and safety checks for AI coding agents via MCP.", "repo": null, "install": ["npm:agent-guardrails"], "stars": null, "pushed": null, "license": null, "plat": "ai coding agents", "live": "Not checked (runs locally)"}, {"id": "mcp:dev.agentreliability/agent-reliability", "name": "Agent Reliability", "kind": "mcp", "official": null, "desc": "Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence", "repo": "https://github.com/citarium/agentreliability-mcp", "install": ["https://agentreliability.dev/mcp?via=manifest"], "stars": 0, "pushed": "2026-09-07T05:24:08Z", "license": "CC-BY-4.0", "plat": "", "live": "Live · 2964 ms · 9 tools · free to try: `get_latest` answered without a key (checked 2026-11-13)"}, {"id": "mcp:io.github.fantasyce/agent-residue-evidence", "name": "Agent Residue Evidence", "kind": "mcp", "official": null, "desc": "Report local task-scoped test and build residue without cleaning resources.", "repo": "https://github.com/fantasyce/agent-residue-evidence", "install": ["mcpb:https://github.com/fantasyce/agent-residue-evidence/releases/download/v0.3.0/agent-residue-evidence_0.3.0.mcpb"], "stars": 0, "pushed": "2026-09-13T01:09:25Z", "license": "Apache-2.0", "plat": "agent", "live": "Not checked (runs locally)"}, {"id": "mcp:dev.agenttested/agent-tested", "name": "Agent Tested", "kind": "mcp", "official": null, "desc": "Hands-on agent test results for small AI tools and MCP servers, live AI outages, malware name check.", "repo": null, "install": ["https://agenttested.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Live · 2636 ms · 14 tools · free to try: `search_tools` answered without a key (checked 2026-11-13)"}, {"id": "mcp:dev.agenticpipeline/agentic-pipeline", "name": "Agentic Pipeline", "kind": "mcp", "official": null, "desc": "Agent-native CI/CD: follow a push to live deploy, diagnose failing stages, prove fixes, rerun.", "repo": "https://github.com/TeamK2K/agentic-pipeline", "install": ["https://mcp.agenticpipeline.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "agentic pipeline", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.noviantonugroho4/agentq", "name": "AgentQ MCP Server", "kind": "mcp", "official": null, "desc": "AgentQ MCP Server - AI-Powered Software Quality Assurance Platform", "repo": null, "install": ["https://mcp.agentq.id/mcp"], "stars": null, "pushed": null, "license": null, "plat": "agentq", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:ai.canaryusers/canaryusers", "name": "ai.canaryusers/canaryusers", "kind": "mcp", "official": null, "desc": "A flock of AI users tests your deployed app and reports where real people get stuck, with fixes.", "repo": "https://github.com/CanaryUsers-ai/canaryusers-mcp", "install": ["https://www.canaryusers.ai/api/mcp"], "stars": 0, "pushed": "2026-06-13T18:31:57Z", "license": "MIT", "plat": "", "live": "Live · 1226 ms · 3 tools · `list_recent_scans` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:ai.perfloop/perfloop", "name": "ai.perfloop/perfloop", "kind": "mcp", "official": null, "desc": "Always-on performance engineering for your own code: proven pull requests, the merge stays yours.", "repo": null, "install": ["https://app.perfloop.ai/mcp"], "stars": null, "pushed": null, "license": null, "plat": "perfloop", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:ai.smithery/mrugankpednekar-mcp-optimizer", "name": "ai.smithery/mrugankpednekar-mcp-optimizer", "kind": "mcp", "official": null, "desc": "Optimize crew and workforce schedules, resource allocation, and routing with linear and mixed-inte…", "repo": "https://github.com/mrugankpednekar/mcp-optimizer", "install": ["https://server.smithery.ai/@mrugankpednekar/mcp-optimizer/mcp"], "stars": 0, "pushed": "2025-11-22T22:03:22Z", "license": "MIT", "plat": "", "live": "Down · HTTP 404 (checked 2026-11-13)"}, {"id": "mcp:io.github.Dach3r/airbrake-mcp-server", "name": "Airbrake MCP Server", "kind": "mcp", "official": null, "desc": "Query Airbrake errors, notices, deploys, and project stats from MCP clients", "repo": null, "install": ["npm:airbrake-mcp-server"], "stars": null, "pushed": null, "license": null, "plat": "airbrake", "live": "Not checked (runs locally)"}, {"id": "mcp:works.aiva/aiva", "name": "AIVA", "kind": "mcp", "official": null, "desc": "No-code, AI-assisted UI testing: record new tests, run existing ones, and monitor the results.", "repo": null, "install": ["https://api.aiva.works/mcp"], "stars": null, "pushed": null, "license": null, "plat": "aiva", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.pipeworx-io/amplitude", "name": "Amplitude", "kind": "mcp", "official": null, "desc": "Amplitude MCP Pack", "repo": "https://github.com/pipeworx-io/mcp-amplitude", "install": ["npm:@pipeworx/mcp-amplitude", "https://gateway.pipeworx.io/amplitude/mcp"], "stars": 0, "pushed": "2026-11-09T13:26:13Z", "license": "MIT", "plat": "amplitude", "live": "Not checked (runs locally)"}, {"id": "mcp:ai.apithreshold/apithreshold", "name": "APIThreshold", "kind": "mcp", "official": null, "desc": "Quality scoring and progressive gates for AI-generated API tests. Stripe/Twilio profiles. Free tier.", "repo": null, "install": ["oci:ghcr.io/apithreshold/apithreshold:0.1.0"], "stars": null, "pushed": null, "license": null, "plat": "stripe, twilio", "live": "Not checked (runs locally)"}, {"id": "mcp:app.faylee/faylee", "name": "app.faylee/faylee", "kind": "mcp", "official": null, "desc": "Read browser bug recordings: video, console, network, steps. Fix the bug and comment back.", "repo": null, "install": ["https://app.faylee.app/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.applitools/applitools", "name": "Applitools", "kind": "mcp", "official": null, "desc": "Create, update, review, and resolve visual tests with Applitools Eyes across any supported SDK.", "repo": "https://github.com/applitools/mcp", "install": ["npm:@applitools/mcp"], "stars": 0, "pushed": "2026-11-12T08:42:45Z", "license": "NOASSERTION", "plat": "applitools", "live": "Not checked (runs locally)"}, {"id": "mcp:com.assertline/assertline", "name": "Assertline", "kind": "mcp", "official": null, "desc": "Find your recorded end-to-end web tests, run them and read step-by-step results.", "repo": null, "install": ["https://app.assertline.com/api/mcp"], "stars": null, "pushed": null, "license": null, "plat": "assertline", "live": "Responds, sign-in needed (checked 2026-11-14)"}, {"id": "mcp:io.github.Praxso/attested", "name": "attested", "kind": "mcp", "official": null, "desc": "Run tests into a Sigstore-signed receipt; get a redacted failure packet on red. No images posted.", "repo": "https://github.com/Praxso/attested", "install": ["npm:@praxso/attested-mcp"], "stars": 0, "pushed": "2026-11-03T19:50:04Z", "license": "Apache-2.0", "plat": "sigstore", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.FSQ-lab/autogenesis-appium", "name": "AutoGenesis Appium", "kind": "mcp", "official": null, "desc": "BDD automation runtime for iOS, Android, and macOS through Appium.", "repo": "https://github.com/FSQ-lab/AutoGenesis", "install": ["pypi:autogenesis-appium-mcp"], "stars": 0, "pushed": "2026-11-12T12:44:02Z", "license": "NOASSERTION", "plat": "appium", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.FSQ-lab/autogenesis-windows", "name": "AutoGenesis Windows", "kind": "mcp", "official": null, "desc": "BDD automation runtime for Windows desktop applications through pywinauto.", "repo": "https://github.com/FSQ-lab/AutoGenesis", "install": ["pypi:autogenesis-windows-mcp"], "stars": 0, "pushed": "2026-11-12T12:44:02Z", "license": "NOASSERTION", "plat": "pywinauto", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ahamdjin/automation-auditor-mcp", "name": "Automation Auditor MCP", "kind": "mcp", "official": null, "desc": "Inspect n8n, Dify, Trigger.dev and Activepieces automation exports before deployment.", "repo": "https://github.com/ahamdjin/automation-auditor-mcp", "install": ["pypi:automation-auditor-mcp"], "stars": 0, "pushed": "2026-10-21T16:49:17Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:com.avalyz/avalyz", "name": "Avalyz", "kind": "mcp", "official": null, "desc": "Acceptance tests for any web app, however it's built: full journeys on apps you're allowed to test.", "repo": null, "install": ["https://avalyz.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.bhuman-ai/beforeusersdo", "name": "Before Users Do", "kind": "mcp", "official": null, "desc": "Browser-backed QA with evidence and fix-ready reports for coding agents.", "repo": "https://github.com/bhuman-ai/QAbro", "install": ["https://mcp.beforeusersdo.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "coding agents", "live": "Down · HTTP 503 (checked 2026-11-13)"}, {"id": "mcp:br.com.bfocus/bfocus", "name": "bFocus", "kind": "mcp", "official": null, "desc": "Monitoring errors, tickets, tasks, projects and release notes from bFocus, with the app's rules.", "repo": null, "install": ["https://api.bfocus.com.br/mcp"], "stars": null, "pushed": null, "license": null, "plat": "bfocus", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:com.hibonzai.mcp/bonzai", "name": "Bonzai", "kind": "mcp", "official": null, "desc": "Finds what's broken in your product, explains why, and fixes it from your agent.", "repo": null, "install": ["https://mcp.hibonzai.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.1019666077-bit/cc-helper", "name": "Bot Bridge CC Helper", "kind": "mcp", "official": null, "desc": "Bridge a remote bot to a local Bot Bridge CC Helper: dispatch coding tasks and read progress.", "repo": "https://github.com/1019666077-bit/botbridge-cc-helper-vscode", "install": ["mcpb:https://github.com/1019666077-bit/botbridge-cc-helper-vscode/releases/download/v0.1.0-mcpb/botbridge-cc-helper.mcpb"], "stars": 0, "pushed": "2026-10-12T12:05:22Z", "license": "MIT", "plat": "bot bridge", "live": "Not checked (runs locally)"}, {"id": "mcp:ai.cybernative/breakage-calendar", "name": "Breakage Calendar", "kind": "mcp", "official": null, "desc": "Which dated upstream breaks hit your repository or dependency list, and the tested fix.", "repo": "https://github.com/CyberNative-AI/breakage-calendar-mcp", "install": ["mcpb:https://github.com/CyberNative-AI/breakage-calendar-mcp/releases/download/v0.1.0/breakage-calendar-mcp-0.1.0.mcpb"], "stars": 0, "pushed": "2026-11-14T01:36:09Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.briefport/agent-delivery", "name": "BriefPort Agent Delivery", "kind": "mcp", "official": null, "desc": "Coding agents read frozen requirements, report progress, and submit delivery evidence.", "repo": null, "install": ["https://briefport.io/mcp"], "stars": null, "pushed": null, "license": null, "plat": "briefport", "live": "Down · URLError: <urlopen error timed out> (checked 2026-11-13)"}, {"id": "mcp:io.github.madhavi-opsera/bug-detector", "name": "Bug Detector", "kind": "mcp", "official": null, "desc": "Analyzes code for bugs, security vulnerabilities, and code smells", "repo": "https://github.com/madhavi-opsera/bug-detector", "install": ["oci:ghcr.io/madhavi-opsera/bug-detector:1.0.0"], "stars": 0, "pushed": "2025-10-22T19:15:45Z", "license": null, "plat": "code", "live": "Not checked (runs locally)"}, {"id": "mcp:io.bugasura/bugasura", "name": "Bugasura", "kind": "mcp", "official": null, "desc": "Bug tracking and test management: issues, test cases, sprints, runs, requirements and KB.", "repo": "https://github.com/Bugasura/bugasura-mcp-server", "install": ["https://mcp.bugasura.io/mcp"], "stars": 0, "pushed": "2026-11-05T10:18:21Z", "license": "MIT", "plat": "bugasura", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.viveksinra/bugmojo", "name": "BugMojo", "kind": "mcp", "official": null, "desc": "Bug tracking for AI agents: session replay, console/network logs, repro packs, test plans, evidence.", "repo": "https://github.com/viveksinra/bugmojo-sdk", "install": ["npm:@bugmojo/mcp-server", "https://www.bugmojo.com/api/mcp"], "stars": 0, "pushed": "2026-10-19T09:06:21Z", "license": "MIT", "plat": "ai agents", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.sidinsearch/bugproof", "name": "BugProof", "kind": "mcp", "official": null, "desc": "Capture, replay, and debug failures with portable, executable bug artifacts", "repo": "https://github.com/sidinsearch/BugProof", "install": ["npm:bugproof"], "stars": 0, "pushed": "2026-05-31T23:10:51Z", "license": "AGPL-3.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:app.bugscreen/mcp", "name": "BugScreen", "kind": "mcp", "official": null, "desc": "Configure mobile bug reporting and investigate retained reports with your coding assistant.", "repo": null, "install": ["https://www.bugscreen.app/mcp"], "stars": null, "pushed": null, "license": null, "plat": "mobile", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:ai.bugtape/bugtape", "name": "BugTape", "kind": "mcp", "official": null, "desc": "Production bugs with replay, network, console and stack, ranked for your coding agent to fix.", "repo": null, "install": ["https://app.bugtape.ai/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.BuildPulseLLC/buildpulse-mcp", "name": "BuildPulse", "kind": "mcp", "official": null, "desc": "BuildPulse for AI agents: CI runner usage, cost and savings, plus flaky tests, failures, coverage.", "repo": "https://github.com/BuildPulseLLC/buildpulse-mcp", "install": ["npm:@buildpulse/mcp", "https://mcp.buildpulse.io/mcp"], "stars": 0, "pushed": "2026-11-05T18:03:17Z", "license": "MIT", "plat": "ci runner", "live": "Not checked (runs locally)"}, {"id": "mcp:dev.busymate/busymate-devtools", "name": "Busymate DevTools", "kind": "mcp", "official": null, "desc": "Capture, inspect & debug HTTPS traffic across iOS, Android, browsers & backends — 304 MCP tools.", "repo": "https://github.com/serebano/busymate-devtools", "install": ["https://mcp.busymate.dev"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Live · 1749 ms · 53 tools · `get_entry` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:ai.calaf/seeds", "name": "Calaf Seed Tools", "kind": "mcp", "official": null, "desc": "Author and validate Calaf workspace seeds against the app's real importer. No account needed.", "repo": "https://github.com/gallaghern51-art/calaf-mcp", "install": ["https://calaf.ai/api/mcp"], "stars": 0, "pushed": "2026-08-22T22:21:47Z", "license": null, "plat": "", "live": "Live · 751 ms · 2 tools (checked 2026-11-13)"}, {"id": "mcp:com.powmcp/caption-file-check", "name": "Caption File Check", "kind": "mcp", "official": null, "desc": "Parse WebVTT, SRT, or TTML for conformance, timing, overlaps, line length, and reading speed.", "repo": "https://github.com/powmcp/mcp-server-guide", "install": ["https://powmcp.com/caption-file-check/mcp"], "stars": 0, "pushed": "2026-09-22T18:59:15Z", "license": "MIT", "plat": "", "live": "Live · 760 ms · 2 tools (checked 2026-11-13)"}, {"id": "mcp:io.github.wcharysz/charlotte", "name": "Charlotte", "kind": "mcp", "official": null, "desc": "Query, replay and rewrite your app's real HTTPS traffic, captured locally by Charlotte.", "repo": null, "install": [], "stars": null, "pushed": null, "license": null, "plat": "charlotte", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.sorokinvj/checkmyapp", "name": "CheckMyApp", "kind": "mcp", "official": null, "desc": "Your agent says “done”. CheckMyApp uses your live app as a real user and tells it what broke.", "repo": "https://github.com/checkmyapp/checkmyapp-mcp", "install": ["https://checkmyapp.dev/mcp"], "stars": 0, "pushed": "2026-11-06T12:59:56Z", "license": "MIT", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.WJDdidi-1/ci-triage", "name": "ci-triage", "kind": "mcp", "official": null, "desc": "Group failed GitHub Actions runs by root cause; separate real regressions from flaky failures.", "repo": "https://github.com/WJDdidi-1/ci-triage", "install": ["npm:ci-triage-cli"], "stars": 0, "pushed": "2026-11-13T12:51:59Z", "license": "Apache-2.0", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:com.subcloak/cloak-proxy", "name": "Cloak Proxy", "kind": "mcp", "official": null, "desc": "Read, mock, pause and replay HTTPS traffic captured by Cloak Proxy, a free macOS debugging proxy.", "repo": "https://github.com/subcloak/cloak-proxy", "install": ["mcpb:https://github.com/subcloak/cloak-proxy/releases/download/v0.7.4/cloak-proxy-0.7.4-macos.mcpb"], "stars": 0, "pushed": "2026-10-30T03:54:58Z", "license": "NOASSERTION", "plat": "cloak proxy", "live": "Not checked (runs locally)"}, {"id": "mcp:com.httpstatus/mcp-server", "name": "com.httpstatus/mcp-server", "kind": "mcp", "official": null, "desc": "AI-callable tools for API mocking, testing, monitoring, security, and automation.", "repo": null, "install": ["https://mcp.httpstatus.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:com.nyx-intelligence/val", "name": "com.nyx-intelligence/val", "kind": "mcp", "official": null, "desc": "QA agent for vibecoded apps. Real browser checks, your AI fixes them. Ship to green.", "repo": "https://github.com/Wakizara/val-action", "install": ["npm:@nyx-intelligence/val-mcp"], "stars": 0, "pushed": "2026-05-28T07:40:32Z", "license": "NOASSERTION", "plat": "vibecoded apps", "live": "Not checked (runs locally)"}, {"id": "mcp:com.offensive360/o360-mcp", "name": "com.offensive360/o360-mcp", "kind": "mcp", "official": null, "desc": "Run Offensive360 SAST scans (60+ languages) on local code; findings with file/line and fixes", "repo": "https://github.com/offensive360/mcp-server", "install": ["npm:o360-mcp"], "stars": 0, "pushed": "2026-08-02T13:26:05Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:com.testrigor/mcp-server", "name": "com.testrigor/mcp-server", "kind": "mcp", "official": null, "desc": "Manage test suites, run tests, view results, and automate QA workflows via AI with testRigor.", "repo": null, "install": ["https://api2.testrigor.com/api/v1/mcp"], "stars": null, "pushed": null, "license": null, "plat": "testrigor", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.codecomber/comber", "name": "comber", "kind": "mcp", "official": null, "desc": "Every-click AI QA: walks your whole app from a preview URL and reports broken clicks and errors.", "repo": "https://gitlab.com/getcomber/comber-public", "install": ["npm:comber-mcp"], "stars": null, "pushed": null, "license": null, "plat": "ai agent", "live": "Not checked (runs locally)"}, {"id": "mcp:com.complexqa/cqa-mcp", "name": "ComplexQA", "kind": "mcp", "official": null, "desc": "ComplexQA projects, cases, bugs, and autotest runs for an external agent.", "repo": null, "install": ["https://mcp.complexqa.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "external agent", "live": "Responds, sign-in needed (checked 2026-11-14)"}, {"id": "mcp:io.github.convertcom/convert-mcp", "name": "Convert Experiences", "kind": "mcp", "official": null, "desc": "Run Convert A/B testing from AI assistants: audit, QA, build drafts and analyze experiment results.", "repo": null, "install": ["npm:@convertcom/mcp-server", "https://mcp.ai.app.convert.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.SuresoftTechnologies/covera-mcp", "name": "COVERA COVER coverage tools", "kind": "mcp", "official": null, "desc": "Drive Suresoft COVER EE from a coding agent: coverage builds, coverage lookup, toolchain recovery.", "repo": "https://github.com/SuresoftTechnologies/covera-plugin", "install": ["mcpb:https://github.com/SuresoftTechnologies/covera-plugin/releases/download/mcp-v0.1.0/covera-mcp.mcpb"], "stars": 0, "pushed": "2026-11-10T06:53:56Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.tylerscomic-lab/cron-schedule-audit-mcp", "name": "Cron Schedule Audit", "kind": "mcp", "official": null, "desc": "Validates cron expressions and finds DST bugs that make jobs silently skip or double-fire.", "repo": "https://github.com/tylerscomic-lab/cron-schedule-audit-mcp", "install": ["https://cron-schedule-audit-mcp.mcpize.run/mcp"], "stars": 0, "pushed": "2026-07-25T16:47:34Z", "license": "MIT", "plat": "", "live": "Down · HTTP 404 (checked 2026-11-13)"}, {"id": "mcp:net.dabloons/dabloons", "name": "Dabloons", "kind": "mcp", "official": null, "desc": "Bounty board where AI agents hire other agents for PR reviews, bug repros, installs and site QA", "repo": "https://github.com/randall-inc/dabloons", "install": ["https://dabloons.net/mcp"], "stars": 0, "pushed": "2026-10-23T21:43:45Z", "license": "Apache-2.0", "plat": "bounty board", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:com.heydeacon/deacon", "name": "Deacon", "kind": "mcp", "official": null, "desc": "Your customers tell Deacon's chat what broke. Your coding agent reads it and fixes the code.", "repo": null, "install": ["https://heydeacon.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:sh.deterministic/deterministic", "name": "Deterministic", "kind": "mcp", "official": null, "desc": "Physics-based validation of simulation results: receipts with per-check verdicts, via MCP.", "repo": null, "install": ["https://deterministic.sh/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:dev.dungbeetle/mcp", "name": "dev.dungbeetle/mcp", "kind": "mcp", "official": null, "desc": "Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.", "repo": "https://github.com/DungbeetleTech/cloud", "install": ["npm:dungbeetle-mcp"], "stars": null, "pushed": null, "license": null, "plat": "ai agents", "live": "Not checked (runs locally)"}, {"id": "mcp:dev.workers.cronping-oren.cronping/heartbeat-monitor", "name": "dev.workers.cronping-oren.cronping/heartbeat-monitor", "kind": "mcp", "official": null, "desc": "Dead-man's-switch for cron jobs & AI agents. Import a crontab to arm one silent-miss alert per job.", "repo": null, "install": ["https://cronping.cronping-oren.workers.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "cronping", "live": "Down · HTTP 404 (checked 2026-11-13)"}, {"id": "mcp:io.github.CE-RISE-software/dpawb", "name": "Digital Passport Assessment Workbench", "kind": "mcp", "official": null, "desc": "Deterministic SHACL-based assessment and comparison for digital passport data models.", "repo": "https://github.com/CE-RISE-software/dp-assessment-workbench", "install": ["oci:ghcr.io/ce-rise-software/dpawb-mcp:0.1.2"], "stars": 0, "pushed": "2026-04-27T14:35:27Z", "license": "EUPL-1.2", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.doply/doply", "name": "Doply", "kind": "mcp", "official": null, "desc": "Check your Google Play closed test on Doply: progress, devices, crashes, screenshots.", "repo": null, "install": ["https://www.doply.io/mcp"], "stars": null, "pushed": null, "license": null, "plat": "doply", "live": "Live · 2626 ms · 4 tools · free to try: `get_requirements` answered without a key (checked 2026-11-13)"}, {"id": "mcp:io.github.RadW2020/downtrace", "name": "Downtrace", "kind": "mcp", "official": null, "desc": "Downtrace tells you when a change breaks the performance of your Node.js backend.", "repo": "https://github.com/RadW2020/downtrace-agent", "install": ["npm:@downtrace/mcp"], "stars": 0, "pushed": "2026-11-12T18:43:19Z", "license": "MIT", "plat": "node.js", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.SuresoftTechnologies/dvera-mcp", "name": "DVERA C/C++ Unit and Integration Verification", "kind": "mcp", "official": null, "desc": "CT C/C++ unit and integration verification for functional-safety projects via coding agents and MCP.", "repo": "https://github.com/SuresoftTechnologies/dvera-plugin", "install": ["mcpb:https://github.com/SuresoftTechnologies/dvera-plugin/releases/download/v0.1.5/dvera-mcp.mcpb"], "stars": 0, "pushed": "2026-11-11T03:32:54Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:dev.easytdd/easytdd", "name": "EasyTdd", "kind": "mcp", "official": null, "desc": "Generate C# builders, FluentMocks, tests and test cases from your .NET solution.", "repo": null, "install": ["nuget:EasyTdd.Mcp"], "stars": null, "pushed": null, "license": null, "plat": "c#", "live": "Not checked (runs locally)"}, {"id": "mcp:com.powmcp/epub-check", "name": "Ebook File Check", "kind": "mcp", "official": null, "desc": "Run EPUBCheck for EPUB specification errors and compare two exports.", "repo": "https://github.com/powmcp/mcp-server-guide", "install": ["https://powmcp.com/epub-check/mcp"], "stars": 0, "pushed": "2026-09-22T18:59:15Z", "license": "MIT", "plat": "", "live": "Live · 828 ms · 2 tools (checked 2026-11-13)"}, {"id": "mcp:io.github.est57/echoproof", "name": "Echoproof", "kind": "mcp", "official": null, "desc": "Replay real HTTP traffic against base and changed builds; flag behavior changes the intent omits.", "repo": "https://github.com/est57/echoproof", "install": ["cargo:echoproof"], "stars": 0, "pushed": "2026-10-15T13:56:37Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/eclipse-benchkit-mcp", "name": "Eclipse Benchkit", "kind": "mcp", "official": null, "desc": "Free vendor self-bench SDK — Assay scorecard format + verifier spot-check sampling.", "repo": "https://github.com/CYAN-ECLIPSE-TECHNOLOGIES-LLC/eclipse-benchkit-mcp", "install": [], "stars": null, "pushed": null, "license": null, "plat": "eclipse", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Energixe/edgehound-mcp", "name": "Edgehound", "kind": "mcp", "official": null, "desc": "Writes adversarial test suites for AI-built code. Your agent's test engineer.", "repo": "https://github.com/Energixe/edgehound-mcp", "install": ["https://gauntlet.mcpize.run/mcp"], "stars": 0, "pushed": "2026-09-17T05:35:22Z", "license": "MIT", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.colt2822/payload-validator", "name": "ELYREON Payload Validator", "kind": "mcp", "official": null, "desc": "Deterministic, read-only JSON payload validation (bounded JSON Schema 2020-12 subset).", "repo": null, "install": ["https://elyreon-payload-validator.colt2822.workers.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "elyreon", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.colt2822/workflow-rescue", "name": "ELYREON Workflow Rescue", "kind": "mcp", "official": null, "desc": "Offline static analysis of n8n workflow exports: dead ends, cycles, missing triggers, secrets.", "repo": null, "install": ["npm:elyreon-workflow-rescue"], "stars": null, "pushed": null, "license": null, "plat": "elyreon", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.LBarimi/failtrace", "name": "FailTrace", "kind": "mcp", "official": null, "desc": "Debugging experiments for coding agents: reproduce failures and verify fixes with test evidence.", "repo": "https://github.com/LBarimi/FailTrace", "install": ["npm:failtrace"], "stars": 0, "pushed": "2026-09-07T09:06:48Z", "license": "MIT", "plat": "failtrace", "live": "Not checked (runs locally)"}, {"id": "mcp:io.flareapp/flare", "name": "Flare", "kind": "mcp", "official": null, "desc": "Error tracking for Laravel and PHP apps. Let your agent fetch errors, stack traces and context.", "repo": null, "install": ["https://flareapp.io/mcp"], "stars": null, "pushed": null, "license": null, "plat": "flare", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:gg.gamebeast/mcp", "name": "Gamebeast", "kind": "mcp", "official": null, "desc": "Analytics, A/B tests, remote configs and player sentiment for games and apps, run by your AI agent.", "repo": null, "install": ["https://api.gamebeast.gg/mcp"], "stars": null, "pushed": null, "license": null, "plat": "game analytics", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.fhs1220888/groundline", "name": "Groundline", "kind": "mcp", "official": null, "desc": "Verifiable test-data analysis: deterministic tools, evidence ledger, number-level checks.", "repo": "https://github.com/fhs1220888/Groundline", "install": ["pypi:groundline"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.happo/mcp", "name": "Happo", "kind": "mcp", "official": null, "desc": "Review Happo's visual and accessibility diffs: inspect comparisons, accept or reject, report flakes.", "repo": null, "install": ["https://happo.io/api/mcp"], "stars": null, "pushed": null, "license": null, "plat": "visual and accessibility diffs", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:dev.hookspot/hookspot", "name": "Hookspot", "kind": "mcp", "official": null, "desc": "Debug webhooks and set up their routing: requests, deliveries, responses, sources and routes.", "repo": null, "install": ["https://app.hookspot.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:studio.inite/ideaudit-tools", "name": "ideaudit", "kind": "mcp", "official": null, "desc": "The scoring behind an audit allowed to say no. Twenty deterministic tools, offline, no account.", "repo": "https://github.com/inite-ai/ideaudit-mcp", "install": ["npm:@inite/ideaudit-tools", "https://api.inite.studio/mcp"], "stars": 0, "pushed": "2026-10-30T17:14:25Z", "license": "NOASSERTION", "plat": "ideaudit", "live": "Not checked (runs locally)"}, {"id": "mcp:app.interbang/interbang", "name": "Interbang", "kind": "mcp", "official": null, "desc": "Moderated usability testing: read sessions, notes, transcripts, reports, and draft test scenarios.", "repo": null, "install": ["https://interbang.app/api/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.interfere-inc/interfere", "name": "Interfere", "kind": "mcp", "official": null, "desc": "Investigate application problems, sessions, and releases with your workspace permissions.", "repo": null, "install": ["https://mcp.interfere.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.adamgusky/mintqa-mcp", "name": "io.github.adamgusky/mintqa-mcp", "kind": "mcp", "official": null, "desc": "MCP server for Mint — AI-powered QA that runs your app in a real browser on every PR.", "repo": "https://github.com/adamgusky/mint", "install": ["npm:mintqa-mcp", "https://mintqa.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "mint", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ai-debugger-inc/aidb", "name": "io.github.ai-debugger-inc/aidb", "kind": "mcp", "official": null, "desc": "Debug any supported language with breakpoints, variable/state inspection, and stepping.", "repo": null, "install": ["pypi:ai-debugger-inc"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ajrogier/aiqaramba", "name": "io.github.ajrogier/aiqaramba", "kind": "mcp", "official": null, "desc": "Browser-based QA for AI-built software. Test pages with real browsers via agents.", "repo": null, "install": ["https://mcp.aiqaramba.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "github", "live": "Down · URLError: <urlopen error [Errno 11001] getaddrinfo failed> (checked 2026-11-13)"}, {"id": "mcp:io.github.baopeak/verirun", "name": "io.github.baopeak/verirun", "kind": "mcp", "official": null, "desc": "Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.", "repo": "https://github.com/baopeak/verirun", "install": ["npm:verirun"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.charliemtnez/ghost-inspector-mcp", "name": "io.github.charliemtnez/ghost-inspector-mcp", "kind": "mcp", "official": null, "desc": "Analyze, validate and safely update Ghost Inspector end-to-end browser tests", "repo": "https://github.com/charliemtnez/ghost-inspector-mcp", "install": ["npm:ghost-inspector-mcp"], "stars": 0, "pushed": "2026-09-28T15:23:10Z", "license": "MIT", "plat": "ghost inspector", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/buildtime", "name": "io.github.CloudCorpRecords/buildtime", "kind": "mcp", "official": null, "desc": "Build bottleneck profiler: slowest steps, run trend, and cache correlation across CI runs.", "repo": "https://github.com/CloudCorpRecords/buildtime", "install": ["npm:@reneturcios/buildtime", "oci:ghcr.io/cloudcorprecords/buildtime:0.1.0"], "stars": 0, "pushed": "2026-11-02T13:31:19Z", "license": "MIT", "plat": "ci", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/cachemiss", "name": "io.github.CloudCorpRecords/cachemiss", "kind": "mcp", "official": null, "desc": "CI cache-miss analysis: which hashed key inputs changed and why runs missed or fell back.", "repo": "https://github.com/CloudCorpRecords/cachemiss", "install": ["npm:@reneturcios/cachemiss", "oci:ghcr.io/cloudcorprecords/cachemiss:0.1.0"], "stars": 0, "pushed": "2026-11-02T15:35:24Z", "license": "MIT", "plat": "ci", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/cidiff", "name": "io.github.CloudCorpRecords/cidiff", "kind": "mcp", "official": null, "desc": "Base-vs-head CI differ: which PR failures are introduced, pre-existing, external, or fixed.", "repo": "https://github.com/CloudCorpRecords/cidiff", "install": ["npm:@reneturcios/cidiff", "oci:ghcr.io/cloudcorprecords/cidiff:0.1.2"], "stars": 0, "pushed": "2026-10-26T08:09:20Z", "license": "MIT", "plat": "io.github.cloudcorprecords", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/enginegate", "name": "io.github.CloudCorpRecords/enginegate", "kind": "mcp", "official": null, "desc": "Gateway to a running Unreal Editor: search, describe, execute, and configure capabilities.", "repo": "https://github.com/CloudCorpRecords/enginegate", "install": ["npm:@reneturcios/enginegate", "oci:ghcr.io/cloudcorprecords/enginegate:0.1.0"], "stars": 0, "pushed": "2026-11-01T21:58:51Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/envdiff", "name": "io.github.CloudCorpRecords/envdiff", "kind": "mcp", "official": null, "desc": "Diff local vs CI environments: Node, OS, lockfile, and env vars — keys named, values never echoed.", "repo": "https://github.com/CloudCorpRecords/envdiff", "install": ["npm:@reneturcios/envdiff", "oci:ghcr.io/cloudcorprecords/envdiff:0.1.0"], "stars": 0, "pushed": "2026-11-02T11:58:24Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/envdoc", "name": "io.github.CloudCorpRecords/envdoc", "kind": "mcp", "official": null, "desc": "Check .env.example against actual env usage in code: missing, stale, and undocumented vars.", "repo": "https://github.com/CloudCorpRecords/envdoc", "install": ["npm:@reneturcios/envdoc", "oci:ghcr.io/cloudcorprecords/envdoc:0.1.0"], "stars": 0, "pushed": "2026-10-25T10:22:44Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/envdoctor", "name": "io.github.CloudCorpRecords/envdoctor", "kind": "mcp", "official": null, "desc": "Local environment doctor: runtime, tools, env files, and services, pass or fail.", "repo": "https://github.com/CloudCorpRecords/envdoctor", "install": ["npm:@reneturcios/envdoctor", "oci:ghcr.io/cloudcorprecords/envdoctor:0.1.0"], "stars": 0, "pushed": "2026-10-30T15:30:42Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/errorcatalog", "name": "io.github.CloudCorpRecords/errorcatalog", "kind": "mcp", "official": null, "desc": "Catalogue every error a codebase throws, and whether each message is documented.", "repo": "https://github.com/CloudCorpRecords/errorcatalog", "install": ["npm:@reneturcios/errorcatalog", "oci:ghcr.io/cloudcorprecords/errorcatalog:0.1.0"], "stars": 0, "pushed": "2026-11-02T15:04:13Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/evalsnap", "name": "io.github.CloudCorpRecords/evalsnap", "kind": "mcp", "official": null, "desc": "Snapshot diff for agent and tool outputs: changed cases, score regressions, pass/fail verdict.", "repo": "https://github.com/CloudCorpRecords/evalsnap", "install": ["npm:@reneturcios/evalsnap", "oci:ghcr.io/cloudcorprecords/evalsnap:0.1.0"], "stars": 0, "pushed": "2026-11-02T15:50:43Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/flakyguard", "name": "io.github.CloudCorpRecords/flakyguard", "kind": "mcp", "official": null, "desc": "Flaky-test evidence tracker: per-test pass/fail history, flakiness rates, and a quarantine list.", "repo": "https://github.com/CloudCorpRecords/flakyguard", "install": ["npm:@reneturcios/flakyguard", "oci:ghcr.io/cloudcorprecords/flakyguard:0.1.0"], "stars": 0, "pushed": "2026-11-02T15:19:50Z", "license": "MIT", "plat": "github actions", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/gapproof", "name": "io.github.CloudCorpRecords/gapproof", "kind": "mcp", "official": null, "desc": "Find untested functions: link tests to code, score coverage, record proven runs locally.", "repo": "https://github.com/CloudCorpRecords/gapproof", "install": ["npm:@reneturcios/gapproof", "oci:ghcr.io/cloudcorprecords/gapproof:0.1.0"], "stars": 0, "pushed": "2026-11-02T04:20:20Z", "license": "MIT", "plat": "code coverage", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/logdigest", "name": "io.github.CloudCorpRecords/logdigest", "kind": "mcp", "official": null, "desc": "Condense a CI log to its failure sections and root-cause lines, with original line anchors.", "repo": "https://github.com/CloudCorpRecords/logdigest", "install": ["npm:@reneturcios/logdigest", "oci:ghcr.io/cloudcorprecords/logdigest:0.1.0"], "stars": 0, "pushed": "2026-10-25T14:06:09Z", "license": "MIT", "plat": "ci", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/matrixshrink", "name": "io.github.CloudCorpRecords/matrixshrink", "kind": "mcp", "official": null, "desc": "Finds redundant CI matrix combinations from run history and coverage overlap.", "repo": "https://github.com/CloudCorpRecords/matrixshrink", "install": ["npm:@reneturcios/matrixshrink", "oci:ghcr.io/cloudcorprecords/matrixshrink:0.1.0"], "stars": 0, "pushed": "2026-11-02T16:32:45Z", "license": "MIT", "plat": "ci", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/parallelmap", "name": "io.github.CloudCorpRecords/parallelmap", "kind": "mcp", "official": null, "desc": "Dependency graph of jobs or tests that can safely parallelize: levels, critical path, schedule.", "repo": "https://github.com/CloudCorpRecords/parallelmap", "install": ["npm:@reneturcios/parallelmap", "oci:ghcr.io/cloudcorprecords/parallelmap:0.1.0"], "stars": 0, "pushed": "2026-11-02T16:20:50Z", "license": "MIT", "plat": "jobs or tests", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/reprocheck", "name": "io.github.CloudCorpRecords/reprocheck", "kind": "mcp", "official": null, "desc": "Red-first repro verifier: a fix counts only when the repro fails on the base and passes on the fix.", "repo": "https://github.com/CloudCorpRecords/reprocheck", "install": ["npm:@reneturcios/reprocheck", "oci:ghcr.io/cloudcorprecords/reprocheck:0.2.0"], "stars": 0, "pushed": "2026-10-26T07:02:35Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/rerunplan", "name": "io.github.CloudCorpRecords/rerunplan", "kind": "mcp", "official": null, "desc": "Rerun or fix? Classify a failed check from past-run evidence: infra flake, flaky, or real.", "repo": "https://github.com/CloudCorpRecords/rerunplan", "install": ["npm:@reneturcios/rerunplan", "oci:ghcr.io/cloudcorprecords/rerunplan:0.1.0"], "stars": 0, "pushed": "2026-11-02T12:06:25Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/shipcheck", "name": "io.github.CloudCorpRecords/shipcheck", "kind": "mcp", "official": null, "desc": "Release verification for Node and Python: tag, npm, PyPI, Registry, and GHCR must agree, or NO-GO.", "repo": "https://github.com/CloudCorpRecords/shipcheck", "install": ["npm:@reneturcios/shipcheck", "oci:ghcr.io/cloudcorprecords/shipcheck:0.2.0"], "stars": 0, "pushed": "2026-10-26T06:48:48Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/testdelta", "name": "io.github.CloudCorpRecords/testdelta", "kind": "mcp", "official": null, "desc": "Base-vs-head test result differ: named tests added, removed, and changed, never raw counts.", "repo": "https://github.com/CloudCorpRecords/testdelta", "install": ["npm:@reneturcios/testdelta", "oci:ghcr.io/cloudcorprecords/testdelta:0.1.0"], "stars": 0, "pushed": "2026-10-25T11:19:48Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CloudCorpRecords/testfinder", "name": "io.github.CloudCorpRecords/testfinder", "kind": "mcp", "official": null, "desc": "Find the tests relevant to a source file from an import map, ranked, with the run command.", "repo": "https://github.com/CloudCorpRecords/testfinder", "install": ["npm:@reneturcios/testfinder", "oci:ghcr.io/cloudcorprecords/testfinder:0.1.0"], "stars": 0, "pushed": "2026-11-02T17:23:30Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.CSOAI-ORG/test-case-generator-ai-mcp", "name": "io.github.CSOAI-ORG/test-case-generator-ai-mcp", "kind": "mcp", "official": null, "desc": "AI-powered test case generator ai MCP server for agents. Supports generate test cases, generate", "repo": "https://github.com/CSOAI-ORG/test-case-generator-ai-mcp", "install": ["pypi:test-case-generator-ai-mcp"], "stars": 0, "pushed": "2026-10-08T04:26:57Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.daedalus/mcp-gdbserver", "name": "io.github.daedalus/mcp-gdbserver", "kind": "mcp", "official": null, "desc": "MCP server for remote debugging with gdbserver", "repo": "https://github.com/daedalus/mcp-gdbserver", "install": ["pypi:mcp-gdbserver"], "stars": 0, "pushed": "2026-04-22T03:58:05Z", "license": "MIT", "plat": "gdbserver", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Dgotlieb/verdict-mcp", "name": "io.github.Dgotlieb/verdict-mcp", "kind": "mcp", "official": null, "desc": "Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history", "repo": "https://github.com/Dgotlieb/verdict-mcp", "install": ["pypi:verdict-mcp"], "stars": 0, "pushed": "2026-08-29T12:23:11Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.DiegoBr4nd/godot-gut-mcp", "name": "io.github.DiegoBr4nd/godot-gut-mcp", "kind": "mcp", "official": null, "desc": "Servidor MCP que permite ejecutar tests de Godot con GUT desde cualquier IA", "repo": "https://github.com/DiegoBr4nd/godot-gut-mcp", "install": ["pypi:godot-gut-mcp"], "stars": 0, "pushed": "2026-07-01T22:18:12Z", "license": null, "plat": "godot", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.dinosaur24/nodehero", "name": "io.github.dinosaur24/nodehero", "kind": "mcp", "official": null, "desc": "AI workflow error analysis for n8n, Make, Zapier, and 10+ platforms.", "repo": "https://github.com/dinosaur24/zapguard", "install": ["npm:nodehero-mcp"], "stars": null, "pushed": null, "license": null, "plat": "error analysis", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Eason0in/testlink-mcp", "name": "io.github.Eason0in/testlink-mcp", "kind": "mcp", "official": null, "desc": "AI-friendly, safety-first TestLink MCP server", "repo": "https://github.com/Eason0in/testlink-mcp", "install": ["npm:testlink-mcp"], "stars": 0, "pushed": "2026-08-29T14:59:57Z", "license": "MIT", "plat": "testlink", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ethanasm/mcp-queue-doctor", "name": "io.github.ethanasm/mcp-queue-doctor", "kind": "mcp", "official": null, "desc": "Diagnoses pg-boss and graphile-worker job queues: retry storms, stuck workers, missed schedules.", "repo": "https://github.com/ethanasm/mcp-queue-doctor", "install": ["npm:mcp-queue-doctor"], "stars": 0, "pushed": "2026-08-07T04:08:11Z", "license": "MIT", "plat": "mcp-queue-doctor", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.farssaadeldin7-ux/professor-mind-reader", "name": "io.github.farssaadeldin7-ux/professor-mind-reader", "kind": "mcp", "official": null, "desc": "Reverse-engineer a marking rubric into the handful of criteria that actually move the mark, then...", "repo": "https://github.com/farssaadeldin7-ux/claude-plugin-suite", "install": ["mcpb:https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/professor-mind-reader.mcpb"], "stars": 0, "pushed": "2026-10-25T18:12:45Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.fasteningcode/claudetest", "name": "io.github.fasteningcode/claudetest", "kind": "mcp", "official": null, "desc": "Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs.", "repo": null, "install": ["npm:@fasteningcode/claudetest"], "stars": null, "pushed": null, "license": null, "plat": "anthropic", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.FixtureForge/seedweaver-mcp", "name": "io.github.FixtureForge/seedweaver-mcp", "kind": "mcp", "official": null, "desc": "Schema-aware relational test data generator with working foreign keys, for any MCP client.", "repo": "https://github.com/FixtureForge/seedweaver-mcp", "install": ["npm:seedweaver-mcp"], "stars": 0, "pushed": "2026-05-29T11:06:11Z", "license": null, "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.FixtureForge/timeweaver-mcp", "name": "io.github.FixtureForge/timeweaver-mcp", "kind": "mcp", "official": null, "desc": "Synthetic time-series test data with trend, seasonality, noise, and anomalies, for any MCP client.", "repo": "https://github.com/FixtureForge/timeweaver-mcp", "install": ["npm:timeweaver-mcp"], "stars": 0, "pushed": "2026-05-30T12:41:37Z", "license": null, "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.habibafaisal/wherewent", "name": "io.github.habibafaisal/wherewent", "kind": "mcp", "official": null, "desc": "Zero-config SQL flight recorder for slow Python/SQLAlchemy jobs: exact call site, count, and fix.", "repo": "https://github.com/habibafaisal/wherewent", "install": ["pypi:wherewent"], "stars": 0, "pushed": "2026-07-30T21:13:11Z", "license": "MIT", "plat": "sqlalchemy", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Hashi-Kazu/ai-test-process-mcp", "name": "io.github.Hashi-Kazu/ai-test-process-mcp", "kind": "mcp", "official": null, "desc": "AI-assisted MCP server for JSTQB-based test planning, design, review, and analysis.", "repo": "https://github.com/Hashi-Kazu/ai-test-process-mcp", "install": ["npm:ai-test-process-mcp"], "stars": 0, "pushed": "2026-08-14T15:01:35Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.hmamut39/tewip", "name": "io.github.hmamut39/tewip", "kind": "mcp", "official": null, "desc": "Proves software work: triages failing tests, checks whether a test can fail, and reads migrations.", "repo": "https://github.com/hmamut39/tewip", "install": ["npm:tewip-ai"], "stars": 0, "pushed": "2026-11-08T21:35:45Z", "license": "Apache-2.0", "plat": "tewip", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.hubertgajewski/playwright-report-mcp", "name": "io.github.hubertgajewski/playwright-report-mcp", "kind": "mcp", "official": null, "desc": "Run Playwright tests and surface structured results for AI agents doing test failure analysis.", "repo": "https://github.com/hubertgajewski/playwright-report-mcp", "install": ["npm:playwright-report-mcp"], "stars": 0, "pushed": "2026-11-11T17:04:38Z", "license": "MIT", "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Ifeanyiejindu/qarunbook", "name": "io.github.Ifeanyiejindu/qarunbook", "kind": "mcp", "official": null, "desc": "Shared app-testing runbook: read the plan, record results per platform, raise and fix issues.", "repo": "https://github.com/Ifeanyiejindu/qarunbook", "install": ["https://qarunbook.com/api/mcp"], "stars": 0, "pushed": "2026-11-13T09:35:24Z", "license": "MIT", "plat": "qarunbook", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.jorgesandoval/spectra", "name": "io.github.jorgesandoval/spectra", "kind": "mcp", "official": null, "desc": "Generates unit tests for Python code with coverage before/after reports and concrete edge cases.", "repo": null, "install": ["https://spectra.mcpize.run"], "stars": null, "pushed": null, "license": null, "plat": "python", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.joshuaworth/pullsheet-diagnostics", "name": "io.github.joshuaworth/pullsheet-diagnostics", "kind": "mcp", "official": null, "desc": "AI-powered diagnostics for elevator, escalator, and vertical transportation equipment", "repo": "https://github.com/joshuaworth/pullsheetintent", "install": ["https://pullsheet-mcp-server.hgfbxjxghp.workers.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "elevator, escalator", "live": "Down · HTTP 404 (checked 2026-11-13)"}, {"id": "mcp:io.github.katatan-org/katatan-TEST", "name": "io.github.katatan-org/katatan-TEST", "kind": "mcp", "official": null, "desc": "KATATAN E2E testing agent set — Playwright + KATATAN MCP integration", "repo": "https://github.com/katatan-org/katatan-TEST", "install": ["npm:@katatan/agents"], "stars": null, "pushed": null, "license": null, "plat": "katatan", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.kosiakMD/artillery-mcp", "name": "io.github.kosiakMD/artillery-mcp", "kind": "mcp", "official": null, "desc": "MCP server for Artillery 2.x — full flags, Fargate, raw-text parser, project launcher (MIT)", "repo": "https://github.com/kosiakMD/artillery-mcp", "install": ["npm:@kosiakmd/artillery-mcp", "oci:docker.io/kosiakmd/artillery-mcp:0.1.7", "oci:ghcr.io/kosiakmd/artillery-mcp:0.1.7"], "stars": 0, "pushed": "2026-07-20T21:54:43Z", "license": "MIT", "plat": "artillery", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.lazymac2x/api-mock-server", "name": "io.github.lazymac2x/api-mock-server", "kind": "mcp", "official": null, "desc": "Cloudflare Workers MCP server: api-mock-server", "repo": "https://github.com/lazymac2x/api-mock-server-api", "install": ["https://api.lazy-mac.com/api-mock-server/mcp"], "stars": 0, "pushed": "2026-04-09T16:03:47Z", "license": null, "plat": "cloudflare workers", "live": "Live · 2900 ms · 6 tools · free to try: `list_mocks` answered without a key (checked 2026-11-13)"}, {"id": "mcp:io.github.lchampz/heimdall", "name": "io.github.lchampz/heimdall", "kind": "mcp", "official": null, "desc": "🛡️ MCP Heimdall - Advanced Environment Architect & Diagnostic Tool.", "repo": "https://github.com/lchampz/mcp-heimdall", "install": ["npm:@lchampz/mcp-heimdall"], "stars": 0, "pushed": "2026-09-17T14:58:06Z", "license": null, "plat": "cloudflare workers", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Madnands5/owl24-mcp", "name": "io.github.Madnands5/owl24-mcp", "kind": "mcp", "official": null, "desc": "Hand a production error to the coding agent you already use — it claims it and writes the fix.", "repo": "https://github.com/Madnands5/owl24-mcp", "install": ["npm:owl24-mcp"], "stars": 0, "pushed": "2026-10-03T12:41:38Z", "license": "MIT", "plat": "owl24-mcp", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mrfentmen/api-deprecation-radar-mcp", "name": "io.github.mrfentmen/api-deprecation-radar-mcp", "kind": "mcp", "official": null, "desc": "Count local API deprecation markers by broad severity without returning endpoint names, paths,...", "repo": "https://github.com/mrfentmen/api-deprecation-radar-mcp", "install": ["npm:api-deprecation-radar-mcp"], "stars": 0, "pushed": "2026-08-09T02:57:34Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mrfentmen/artifact-gauge-mcp", "name": "io.github.mrfentmen/artifact-gauge-mcp", "kind": "mcp", "official": null, "desc": "Local build artifact size and dependency weight inspection without file content output. Tools...", "repo": "https://github.com/mrfentmen/artifact-gauge-mcp", "install": ["npm:artifact-gauge-mcp"], "stars": 0, "pushed": "2026-08-09T00:34:00Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mrfentmen/atml-mcp", "name": "io.github.mrfentmen/atml-mcp", "kind": "mcp", "official": null, "desc": "ATML MCP: parse test descriptions, validate test items, stations and results.", "repo": "https://github.com/mrfentmen/awesome-servers", "install": ["npm:@mrfentmen/atml-mcp"], "stars": 0, "pushed": "2026-11-10T07:18:37Z", "license": null, "plat": "atml", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mrfentmen/build-cache-mcp", "name": "io.github.mrfentmen/build-cache-mcp", "kind": "mcp", "official": null, "desc": "Summarize local build and cache footprint using size and age buckets without returning paths or...", "repo": "https://github.com/mrfentmen/build-cache-mcp", "install": ["npm:build-cache-mcp"], "stars": 0, "pushed": "2026-08-09T02:57:30Z", "license": null, "plat": "build cache", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mrfentmen/flaky-history-mcp", "name": "io.github.mrfentmen/flaky-history-mcp", "kind": "mcp", "official": null, "desc": "Local aggregate test-history stability analysis without test names or raw result contents.", "repo": "https://github.com/mrfentmen/awesome-servers", "install": ["npm:flaky-history-mcp"], "stars": 0, "pushed": "2026-11-10T07:18:37Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mrfentmen/robotframework-mcp", "name": "io.github.mrfentmen/robotframework-mcp", "kind": "mcp", "official": null, "desc": "Robot Framework MCP: real tools for real work.", "repo": "https://github.com/mrfentmen/awesome-servers", "install": ["npm:@mrfentmen/robotframework-mcp"], "stars": 0, "pushed": "2026-11-10T07:18:37Z", "license": null, "plat": "robot framework", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mrfentmen/test-shape-mcp", "name": "io.github.mrfentmen/test-shape-mcp", "kind": "mcp", "official": null, "desc": "Audit local test structure using aggregate as MCP: real tools for real work.", "repo": "https://github.com/mrfentmen/awesome-servers", "install": ["npm:test-shape-mcp"], "stars": 0, "pushed": "2026-11-10T07:18:37Z", "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.mrfentmen/waf-mcp", "name": "io.github.mrfentmen/waf-mcp", "kind": "mcp", "official": null, "desc": "Waf MCP: parse wscript files, validate build functions and targets.", "repo": "https://github.com/mrfentmen/awesome-servers", "install": ["npm:@mrfentmen/waf-mcp"], "stars": 0, "pushed": "2026-11-10T07:18:37Z", "license": null, "plat": "waf", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.MUSE-CODE-SPACE/test-genie", "name": "io.github.MUSE-CODE-SPACE/test-genie", "kind": "mcp", "official": null, "desc": "AI-powered app test automation for iOS, Android, Flutter, React Native, Web", "repo": "https://github.com/MUSE-CODE-SPACE/test-genie-mcp", "install": ["npm:test-genie-mcp"], "stars": 0, "pushed": "2026-10-22T08:04:12Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.NEVELSK65/agenthub-monitor", "name": "io.github.NEVELSK65/agenthub-monitor", "kind": "mcp", "official": null, "desc": "Renders a pipeline DAG and test-harness dashboard inline as an MCP App", "repo": "https://github.com/NEVELSK65/mcp-agenthub-monitor", "install": ["mcpb:https://github.com/NEVELSK65/mcp-agenthub-monitor/releases/download/v1.0.0/agenthub-monitor.mcpb"], "stars": 0, "pushed": "2026-09-07T12:56:45Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ninelegsdog/qualityforge", "name": "io.github.ninelegsdog/qualityforge", "kind": "mcp", "official": null, "desc": "Evidence-first browser QA with read-only MCP server for AI agent debugging.", "repo": "https://github.com/ninelegsdog/qualityforge", "install": ["npm:qualityforge"], "stars": 0, "pushed": "2026-11-13T01:29:32Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.OctoPerf/octoperf", "name": "io.github.OctoPerf/octoperf", "kind": "mcp", "official": null, "desc": "Drive OctoPerf load testing from any AI agent: import, edit, validate, run scenarios, read metrics.", "repo": "https://github.com/OctoPerf/octoperf-claude-plugins", "install": ["https://api.octoperf.com/mcp"], "stars": 0, "pushed": "2026-10-25T08:43:06Z", "license": "Apache-2.0", "plat": "octoperf", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.oguzc/playwright-wizard-mcp", "name": "io.github.oguzc/playwright-wizard-mcp", "kind": "mcp", "official": null, "desc": "MCP server providing Playwright test generation wizard with intelligent prompts and best practices", "repo": null, "install": ["npm:playwright-wizard-mcp"], "stars": null, "pushed": null, "license": null, "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.phoenice-labs/universal-test-framework", "name": "io.github.phoenice-labs/universal-test-framework", "kind": "mcp", "official": null, "desc": "Polyglot MCP test generation with 8-section contract enforcement across Python, TS, Java, Go, C++.", "repo": "https://github.com/phoenice-labs/Universal-Test-Framework", "install": ["pypi:universal-test-framework"], "stars": 0, "pushed": "2026-04-14T20:59:16Z", "license": "NOASSERTION", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.qatouch/qatouch", "name": "io.github.qatouch/qatouch", "kind": "mcp", "official": null, "desc": "MCP Server for software testing, test case management, test execution, and defect tracking.", "repo": "https://github.com/qatouch/qatouch-mcp-server", "install": ["npm:qatouch-mcp-server"], "stars": 0, "pushed": "2026-09-03T13:27:59Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.reiarseni/mockpost", "name": "io.github.reiarseni/mockpost", "kind": "mcp", "official": null, "desc": "Local multi-channel message emulator for E2E testing, with MCP tools for LLM agents.", "repo": null, "install": ["pypi:mockpost"], "stars": null, "pushed": null, "license": null, "plat": "e2e testing", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.rog0x/testing", "name": "io.github.rog0x/testing", "kind": "mcp", "official": null, "desc": "Test generation, mocks, coverage analysis for AI agents", "repo": "https://github.com/rog0x/mcp-testing-tools", "install": ["npm:@rog0x/mcp-testing-tools"], "stars": 0, "pushed": "2026-03-21T20:21:26Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.RubenGlez/devicecloud", "name": "io.github.RubenGlez/devicecloud", "kind": "mcp", "official": null, "desc": "Triage failing DeviceCloud Maestro test runs: fail reasons, screenshots, flaky-flow analytics", "repo": "https://github.com/RubenGlez/devicecloud-mcp", "install": ["npm:devicecloud-mcp"], "stars": 0, "pushed": "2026-11-08T13:50:55Z", "license": "MIT", "plat": "devicecloud", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.salehrifai42/qtm4j-mcp-server", "name": "io.github.salehrifai42/qtm4j-mcp-server", "kind": "mcp", "official": null, "desc": "MCP server for QMetry Test Management for Jira (QTM4J): test cases, cycles, executions, plans.", "repo": "https://github.com/salehrifai42/qmetrymcp", "install": ["npm:qtm4j-mcp-server"], "stars": 0, "pushed": "2026-06-11T04:28:50Z", "license": "MIT", "plat": "qtm4j", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.sigship/sigship", "name": "io.github.sigship/sigship", "kind": "mcp", "official": null, "desc": "Go/no-go check for AI-built apps. Finds production problems locally and returns fixes.", "repo": "https://github.com/sigship/sigship", "install": ["npm:sigship"], "stars": 0, "pushed": "2026-11-11T10:13:40Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.sudo-ai-git/mcp-benchmark-hygiene", "name": "io.github.sudo-ai-git/mcp-benchmark-hygiene", "kind": "mcp", "official": null, "desc": "Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.", "repo": "https://github.com/sudo-ai-git/mcp-benchmark-hygiene", "install": ["pypi:mcp-benchmark-hygiene"], "stars": 0, "pushed": "2026-08-28T18:31:56Z", "license": "MIT", "plat": "pytest", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.taltal-beep/mcp-server-celery", "name": "io.github.taltal-beep/mcp-server-celery", "kind": "mcp", "official": null, "desc": "Read-only Celery debugging: workers, queue depths and stuck-task diagnosis.", "repo": "https://github.com/taltal-beep/mcp-server-celery", "install": ["pypi:mcp-server-celery"], "stars": 0, "pushed": "2026-10-19T22:34:44Z", "license": "MIT", "plat": "github", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.tdalbanmoreynas/keel", "name": "io.github.tdalbanmoreynas/keel", "kind": "mcp", "official": null, "desc": "Catches your AI coding agent when it games the tests - locked-test hashes, tamper detection.", "repo": "https://github.com/tdalbanmoreynas/keel", "install": [], "stars": 0, "pushed": "2026-07-07T15:37:28Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.tesults/tesults-mcp", "name": "io.github.tesults/tesults-mcp", "kind": "mcp", "official": null, "desc": "Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.", "repo": "https://github.com/tesults/tesults-mcp", "install": ["npm:tesults-mcp"], "stars": 0, "pushed": "2026-10-17T23:14:27Z", "license": null, "plat": "tesults", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.thebotclub/tribunal", "name": "io.github.thebotclub/tribunal", "kind": "mcp", "official": null, "desc": "Tribunal — Enterprise Claude Code plugin. TDD enforcement, quality gates, vault of rules and agents.", "repo": "https://github.com/thebotclub/tribunal-public", "install": ["npm:tribunal"], "stars": null, "pushed": null, "license": null, "plat": "anthropic", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.therealMrFunGuy/cron-pilot", "name": "io.github.therealMrFunGuy/cron-pilot", "kind": "mcp", "official": null, "desc": "Scheduled HTTP requests and shell commands with retries, timeouts, and webhook alerts.", "repo": null, "install": ["https://cron.rjctdlabs.xyz/sse"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Down · HTTP 502 (checked 2026-11-13)"}, {"id": "mcp:io.github.thisis-najeeb/api-test-mcp", "name": "io.github.thisis-najeeb/api-test-mcp", "kind": "mcp", "official": null, "desc": "Call the real API and check the response against your OpenAPI spec.", "repo": "https://github.com/thisis-najeeb/api-test-mcp", "install": ["npm:api-test-mcp"], "stars": 0, "pushed": "2026-08-31T19:59:21Z", "license": "MIT", "plat": "openapi", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.vinur1992/testing_repo", "name": "io.github.vinur1992/testing_repo", "kind": "mcp", "official": null, "desc": "An MCP server that created for demo", "repo": "https://github.com/vinur1992/testing_repo", "install": [], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.vola-trebla/ast-impact-mapper-mcp", "name": "io.github.vola-trebla/ast-impact-mapper-mcp", "kind": "mcp", "official": null, "desc": "MCP server that uses TypeScript AST to find which tests are affected by a code change", "repo": "https://github.com/vola-trebla/ast-impact-mapper-mcp", "install": ["npm:ast-impact-mapper-mcp"], "stars": 0, "pushed": "2026-05-21T12:59:02Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.vola-trebla/flakiness-knowledge-graph-mcp", "name": "io.github.vola-trebla/flakiness-knowledge-graph-mcp", "kind": "mcp", "official": null, "desc": "MCP server + Playwright reporter that builds a flakiness knowledge graph from test run history", "repo": "https://github.com/vola-trebla/flakiness-knowledge-graph-mcp", "install": ["npm:flakiness-knowledge-graph-mcp"], "stars": 0, "pushed": "2026-05-19T00:43:13Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.vola-trebla/release-readiness-triage-mcp", "name": "io.github.vola-trebla/release-readiness-triage-mcp", "kind": "mcp", "official": null, "desc": "Aggregates CI failures, cross-references flakiness history, and outputs GO/NO_GO release verdicts.", "repo": "https://github.com/vola-trebla/release-readiness-triage-mcp", "install": ["npm:release-readiness-triage-mcp"], "stars": 0, "pushed": "2026-05-20T03:55:16Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.zyf8827/tern", "name": "io.github.zyf8827/tern", "kind": "mcp", "official": null, "desc": "Model Context Protocol (MCP) server for Tern E2E testing platform", "repo": null, "install": ["npm:@zyf8827/tern-mcp"], "stars": null, "pushed": null, "license": null, "plat": "tern", "live": "Not checked (runs locally)"}, {"id": "mcp:app.netlify.shigoto-dogu/order-eval", "name": "Japanese Order Eval", "kind": "mcp", "official": null, "desc": "Regression checks for Japanese order automations: six free cases, strict JSON scoring and CI gates.", "repo": null, "install": ["https://shigoto-dogu.netlify.app/mcp/order-eval"], "stars": null, "pushed": null, "license": null, "plat": "japanese order eval", "live": "Down · HTTP 400 (checked 2026-11-13)"}, {"id": "mcp:io.github.Invarato/jarroba-tools-logs", "name": "Jarroba Tools · Logs", "kind": "mcp", "official": null, "desc": "Lets your AI read a CI log far too big for its context. 12 tools, takes a file path.", "repo": "https://github.com/Invarato/jarroba-mcp", "install": ["npm:@jarroba/mcp-logs"], "stars": 0, "pushed": "2026-10-26T18:07:07Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Invarato/jarroba-tools-tests", "name": "Jarroba Tools · Test audit", "kind": "mcp", "official": null, "desc": "Audits tests instead of writing them: what each one really asserts. 4 tools, local.", "repo": "https://github.com/Invarato/jarroba-mcp", "install": ["npm:@jarroba/mcp-tests"], "stars": 0, "pushed": "2026-10-26T18:07:07Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.K11-Software-Solutions/api-functional-qa", "name": "k11 API Functional QA", "kind": "mcp", "official": null, "desc": "Functional API tests: story-to-flow, negative tests from the spec, DB checks, evidence.", "repo": "https://github.com/K11-Software-Solutions/k11techlab-api-functional-qa-mcp", "install": ["pypi:k11-api-functional-qa-mcp"], "stars": 0, "pushed": "2026-11-13T15:13:34Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.K11-Software-Solutions/playwright-qa", "name": "k11 Playwright QA", "kind": "mcp", "official": null, "desc": "User stories to verified Playwright tests, and self-healing locators with an audit trail.", "repo": "https://github.com/K11-Software-Solutions/k11techlab-playwright-qa-mcp", "install": ["npm:k11-playwright-qa-mcp"], "stars": 0, "pushed": "2026-11-13T04:46:00Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.K11-Software-Solutions/release-gate", "name": "k11 Release Gate", "kind": "mcp", "official": null, "desc": "Ship, conditions, needs a person, or block: one release decision from QA evidence and policy.", "repo": "https://github.com/K11-Software-Solutions/k11techlab-release-gate-mcp", "install": ["pypi:k11-release-gate-mcp"], "stars": 0, "pushed": "2026-11-13T18:01:17Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.K11-Software-Solutions/selenium-qa", "name": "k11 Selenium QA", "kind": "mcp", "official": null, "desc": "Selenium tests from user stories (Python or Java) and self-healing locators with an audit trail.", "repo": "https://github.com/K11-Software-Solutions/k11techlab-selenium-qa-mcp", "install": ["pypi:k11-selenium-qa-mcp"], "stars": 0, "pushed": "2026-11-13T05:17:18Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:tech.kaiku/kaiku", "name": "Kaiku", "kind": "mcp", "official": null, "desc": "Issue tracker and wiki for teams and their agents; answer your agents' questions from your phone.", "repo": null, "install": ["https://app.kaiku.tech/mcp", "https://mcp.kaiku.tech/mcp", "https://{workspace}.kaiku.tech/mcp"], "stars": null, "pushed": null, "license": null, "plat": "kaiku", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.kovca/mcp", "name": "Kovca", "kind": "mcp", "official": null, "desc": "Build, test, publish, and run Kovca workflows from AI agents over remote MCP.", "repo": null, "install": ["https://kovca.io/api/v1/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.Ilya-a-sergeyev-ger/krauncher-mcp", "name": "Krauncher analyzer", "kind": "mcp", "official": null, "desc": "How long a GPU job will run and cost, before running it — static code analysis, never executed.", "repo": "https://github.com/Ilya-a-sergeyev-ger/krauncher", "install": ["pypi:krauncher-mcp"], "stars": 0, "pushed": "2026-10-07T10:29:43Z", "license": "MIT", "plat": "gpu", "live": "Not checked (runs locally)"}, {"id": "mcp:com.llamalogger/mcp", "name": "Llama Logger", "kind": "mcp", "official": null, "desc": "Exception tracking for .NET. Let your AI coding agent search and triage errors and stack traces.", "repo": null, "install": ["https://mcp.llamalogger.com/api/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:com.loadster/loadster-mcp", "name": "Loadster", "kind": "mcp", "official": null, "desc": "Load testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.", "repo": "https://github.com/loadster/loadster-mcp", "install": ["https://api.loadster.com/mcp"], "stars": 0, "pushed": "2026-11-12T23:54:32Z", "license": "MIT", "plat": "loadster", "live": "Live · 863 ms · 62 tools · `get_script` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:app.loutre/loutre", "name": "Loutre", "kind": "mcp", "official": null, "desc": "Hosted mock APIs from OpenAPI, TypeScript or Postman: realistic data, errors and latency on demand.", "repo": null, "install": ["https://api.loutre.app/mcp"], "stars": null, "pushed": null, "license": null, "plat": "loutre", "live": "Live · 980 ms · 17 tools · `list_mocks` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:io.github.LuxorLabs/luxor-mcp", "name": "Luxor Sandbox MCP", "kind": "mcp", "official": null, "desc": "Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.", "repo": "https://github.com/LuxorLabs/tenki-mcp", "install": ["npm:@luxorai/mcp"], "stars": 0, "pushed": "2026-11-12T18:24:44Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.LuxorLabs/tenki-mcp", "name": "Luxor Sandbox MCP", "kind": "mcp", "official": null, "desc": "Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.", "repo": "https://github.com/LuxorLabs/tenki-mcp", "install": ["npm:@tenkicloud/mcp"], "stars": 0, "pushed": "2026-11-12T18:24:44Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:com.lvl2player/sandbox", "name": "lvl2player sandbox", "kind": "mcp", "official": null, "desc": "Post a failing test; a coding agent solves it. Test money is held first, released when you accept.", "repo": null, "install": ["https://sandbox.lvl2player.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Live · 1904 ms · 25 tools · `get_job` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:com.mabl/mcp", "name": "mabl", "kind": "mcp", "official": null, "desc": "AI-powered test automation: run tests, analyze failures, query results across mabl workspaces.", "repo": "https://github.com/mablhq/mabl-mcp-server", "install": ["https://mcp.mabl.com/mcp", "https://mcp.mabl.com/sse"], "stars": 0, "pushed": "2026-08-11T20:05:54Z", "license": "MIT", "plat": "mabl", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:live.alpic.test5-ca2cc17f/test5", "name": "Magic 8 Ball QA Demo", "kind": "mcp", "official": null, "desc": "Skybridge demo for QA and playground validation", "repo": null, "install": ["https://test5-ca2cc17f.alpic.live", "https://test5-ca2cc17f.alpic.live"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Down · HTTP 404 (checked 2026-11-13)"}, {"id": "mcp:io.github.LovRanRan/mcp-test-runner", "name": "MCP Test Runner", "kind": "mcp", "official": null, "desc": "Local test execution and coverage summaries for onboarding agents.", "repo": "https://github.com/LovRanRan/mcp-test-runner", "install": ["pypi:lovranran-mcp-test-runner"], "stars": 0, "pushed": "2026-06-15T00:35:38Z", "license": "MIT", "plat": "mcp test runner", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.stillsurge/mcu-debug-mcp", "name": "mcu-debug-mcp", "kind": "mcp", "official": null, "desc": "Embedded debug MCP: serial, flash verify, fault decode, 45-pattern log analyzer, driver library", "repo": "https://github.com/stillsurge/mcu-debug-mcp", "install": ["pypi:mcu-debug-mcp"], "stars": 0, "pushed": "2026-10-23T10:37:34Z", "license": "MIT", "plat": "embedded", "live": "Not checked (runs locally)"}, {"id": "mcp:dev.workers.mockbird.mockbird/mockbird", "name": "Mockbird", "kind": "mcp", "official": null, "desc": "Mock REST APIs, fake OAuth2/OIDC provider, uptime monitors + heartbeats, live badge/QR images.", "repo": null, "install": ["https://mockbird.mockbird.workers.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Live · 2076 ms · 19 tools · free to try: `check_api_status` answered without a key (checked 2026-11-13)"}, {"id": "mcp:ai.mozark/mcp", "name": "Mozark MCP Server", "kind": "mcp", "official": null, "desc": "Mozark's MCP server for AI-powered app testing: device access, test automation, and QA insights.", "repo": null, "install": ["https://mcp.mozark.ai"], "stars": null, "pushed": null, "license": null, "plat": "mozark", "live": "Down · HTTP 405 (checked 2026-11-13)"}, {"id": "mcp:com.nittim/nittim", "name": "nittim", "kind": "mcp", "official": null, "desc": "Production-safety audits for AI-generated code, with a fix for every finding.", "repo": "https://github.com/ilanwolberger/nittim-mcp", "install": ["https://nittim.com/api/mcp"], "stars": 0, "pushed": "2026-10-03T10:42:15Z", "license": "MIT", "plat": "nittim", "live": "Live · 1111 ms · 15 tools · free to try: `describe_protocol` answered without a key (checked 2026-11-13)"}, {"id": "mcp:com.nocticas/nocticas", "name": "Nocticas", "kind": "mcp", "official": null, "desc": "Browser QA agent that won't return a false green: verified PASS/FAIL + access-control probing.", "repo": "https://github.com/Low-Latency-Labs/nocticas-action", "install": ["https://app.nocticas.com/api/mcp"], "stars": 0, "pushed": "2026-06-15T07:59:57Z", "license": "MIT", "plat": "web browser", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:ai.ohmybug/bughunter", "name": "OhMyBug", "kind": "mcp", "official": null, "desc": "Code review for your coding agent's changes: a cloud bug hunt. From $4; $0 if clean or minor-only.", "repo": "https://github.com/OhMyX-AI/ohmybug-plugin", "install": ["https://mcp.ohmybug.ai/mcp"], "stars": 0, "pushed": "2026-11-13T06:38:39Z", "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:dev.omnidebuglink/omnidebuglink", "name": "OmniDebugLink", "kind": "mcp", "official": null, "desc": "remote debug iOS/Android/Unity/Godot/Flutter/RN/Web on real-device.ui-tree/screenshots/taps,tests.", "repo": "https://github.com/omnidebuglink/omnidebuglink", "install": ["https://api.omnidebuglink.dev/mcp"], "stars": 0, "pushed": "2026-09-08T03:13:02Z", "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:one.faf/wjttc", "name": "one.faf/wjttc", "kind": "mcp", "official": null, "desc": "F1-grade MCP certification. 52 tests, 9 tiers (49 scored + T9 Receipt validation). Ecosystem: #2759", "repo": "https://github.com/Wolfe-Jam/wjttc", "install": ["npm:wjttc"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ogormans-deptstack/opentofu-test", "name": "OpenTofu Test", "kind": "mcp", "official": null, "desc": "MCP server for the OpenTofu/Terraform native test framework: scaffold, mock, validate, run tests", "repo": "https://github.com/ogormans-deptstack/opentofu-test-mcp", "install": ["oci:ghcr.io/ogormans-deptstack/opentofu-test-mcp:0.1.0"], "stars": 0, "pushed": "2026-10-19T13:52:15Z", "license": "MIT", "plat": "opentofu/terraform", "live": "Not checked (runs locally)"}, {"id": "mcp:ai.optux/mcp", "name": "Optux", "kind": "mcp", "official": null, "desc": "Create and run A/B tests, patches, split tests and feature flags on your website", "repo": null, "install": ["https://mcp.optux.ai"], "stars": null, "pushed": null, "license": null, "plat": "website", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:ai.pensero/pensero", "name": "Pensero", "kind": "mcp", "official": null, "desc": "Engineering metrics from Pensero: delivery, quality, AI usage and cost, Signals, benchmarks.", "repo": null, "install": ["https://pensero.ai/api/v1/mcp"], "stars": null, "pushed": null, "license": null, "plat": "pensero", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:ai.pensero/pensero-eu", "name": "Pensero (EU)", "kind": "mcp", "official": null, "desc": "Engineering metrics from Pensero: delivery, quality, AI usage and cost, Signals, benchmarks.", "repo": null, "install": ["https://eu.pensero.ai/api/v1/mcp"], "stars": null, "pushed": null, "license": null, "plat": "pensero (eu)", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.EmirhanOzl/playproof", "name": "playproof", "kind": "mcp", "official": null, "desc": "See and playtest browser games: frame-by-frame motion, crash hunting, phone layouts, frame pacing.", "repo": "https://github.com/EmirhanOzl/playproof", "install": ["npm:playproof"], "stars": 0, "pushed": "2026-10-22T20:46:00Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:com.playwrightgen/playwrightgen", "name": "PlaywrightGen", "kind": "mcp", "official": null, "desc": "Approved test intent, reviewed Playwright automation and run evidence, inside your editor.", "repo": "https://github.com/hmamut39/playwrightgen", "install": ["https://playwrightgen.com/api/mcp"], "stars": 0, "pushed": "2026-11-08T22:44:19Z", "license": null, "plat": "playwright", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.tia-forge/plc-cloud-sim", "name": "PLC Cloud Sim — LAD/SCL simulation over MCP", "kind": "mcp", "official": null, "desc": "Cloud PLC simulator: validate and step-run LAD/SCL programs, run scenarios, return PASS/FAIL.", "repo": "https://github.com/tia-forge/plc-cloud-sim", "install": ["https://tia.hubwiz.com/sim/mcp"], "stars": 0, "pushed": "2026-10-24T19:11:46Z", "license": null, "plat": "plc", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.boristane/polylane", "name": "Polylane", "kind": "mcp", "official": null, "desc": "Investigate production issues: what changed, logs, metrics, dependencies and fixes in your stack.", "repo": null, "install": ["https://mcp.polylane.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "polylane", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.godarg/practonaut", "name": "Practonaut", "kind": "mcp", "official": null, "desc": "Local practice gym for AI agents on real apps: practice Excalidraw tasks, get a reproducible score.", "repo": "https://github.com/godarg/practonaut", "install": ["npm:practonaut"], "stars": 0, "pushed": "2026-11-10T14:25:12Z", "license": "Apache-2.0", "plat": "excalidraw", "live": "Not checked (runs locally)"}, {"id": "mcp:si.prodready/prodready", "name": "prodready", "kind": "mcp", "official": null, "desc": "Free enterprise-grade due diligence for your app, run by your coding agent. Then the full SDLC.", "repo": null, "install": ["https://mcp.prodready.si/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:dev.proofsheet/proofsheet", "name": "Proofsheet", "kind": "mcp", "official": null, "desc": "Run e2e flows on real iOS and Android phones through the local Proofsheet hub (macOS).", "repo": null, "install": ["npm:proofsheet-mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:qa.proxymail/proxymail-qa", "name": "Proxy Mail QA", "kind": "mcp", "official": null, "desc": "Test inboxes for your app's sign-up and login emails: get the code or link, or why none came.", "repo": null, "install": ["https://api.proxymail.qa/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.MuratKus/qaradar", "name": "QA Radar", "kind": "mcp", "official": null, "desc": "Tells AI agents which files to test first — churn, coverage, and test mapping as risk scores.", "repo": "https://github.com/Muratkus/qaradar", "install": ["pypi:qaradar"], "stars": 0, "pushed": "2026-06-07T12:41:10Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:live.alpic.qa-test-cli-b955e6a8/qa-test-cli", "name": "QA Test Server", "kind": "mcp", "official": null, "desc": "Testing publish command", "repo": null, "install": ["https://qa-test-cli-b955e6a8.alpic.live", "https://qa-test-cli-b955e6a8.alpic.live"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Down · ValueError: {'code': -32603, 'message': 'MCP error -32603: Internal Server Error'} (checked 2026-11-13)"}, {"id": "mcp:ai.qlane/qlane", "name": "Qlane", "kind": "mcp", "official": null, "desc": "AI QA that runs your app in a browser on every pull request: projects, test targets, test cases.", "repo": "https://github.com/qlaneai/agent-plugin", "install": ["https://mcp.qlane.ai/mcp"], "stars": 0, "pushed": "2026-11-12T23:45:46Z", "license": "MIT", "plat": "qlane", "live": "Responds, sign-in needed (checked 2026-11-15)"}, {"id": "mcp:io.github.denis-platonov/qtm4j", "name": "QTM4J", "kind": "mcp", "official": null, "desc": "MCP server for QMetry Test Management for Jira (QTM4J) Open API.", "repo": "https://github.com/denis-platonov/qtm4j-mcp-server", "install": ["npm:@denis-platonov/qtm4j-mcp-server"], "stars": 0, "pushed": "2026-04-21T20:34:24Z", "license": "MIT", "plat": "qmetry test management for jira", "live": "Not checked (runs locally)"}, {"id": "mcp:pl.qualityisland/mcp", "name": "Quality Island", "kind": "mcp", "official": null, "desc": "QA and IT outsourcing, software, security and WCAG testing, QA trainings and QA talent from Poland.", "repo": null, "install": ["https://mcp.qualityisland.pl/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Live · 2498 ms · 7 tools (checked 2026-11-13)"}, {"id": "mcp:io.github.SLP-DEV1/qwen-dap-mcp", "name": "Qwen DAP MCP", "kind": "mcp", "official": null, "desc": "Native runtime debugging via DAP-to-MCP for crashes, hangs, dumps, symbols, and forensics.", "repo": "https://github.com/SLP-DEV1/qwen-dap-mcp", "install": ["npm:@slp-dev1/qwen-dap-mcp"], "stars": null, "pushed": null, "license": null, "plat": "qwen dap", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.przeslijmi/real-fake-data-mcp", "name": "Real Fake Data", "kind": "mcp", "official": null, "desc": "Realistic synthetic test data — valid PESELs, NIPs, IBANs, addresses, people across 27 EU countries.", "repo": "https://github.com/przeslijmi/real-fake-data-mcp", "install": ["npm:@przeslijmi/real-fake-data-mcp"], "stars": 0, "pushed": "2026-07-04T13:23:43Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.ChanghuLiu/cablecert-qa", "name": "RegEvidenceHub CableCert", "kind": "mcp", "official": null, "desc": "Independent owner-side QA for structured-cabling certification closeout evidence.", "repo": "https://github.com/ChanghuLiu/cablecert-qa", "install": ["https://cablecert.regevidencehub.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "regevidencehub", "live": "Live · 1284 ms · 3 tools · free to try: `cablecert_service_info` answered without a key (checked 2026-11-13)"}, {"id": "mcp:com.regresco/mcp", "name": "Regresco", "kind": "mcp", "official": null, "desc": "Save regression flows for your web app, run them in cloud Chromium, read failures with screenshots.", "repo": null, "install": ["https://regresco.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.RepoAssay/repo-test-architect", "name": "Repo Test Architect", "kind": "mcp", "official": null, "desc": "Audit-first test strategy MCP server for repository-native test planning.", "repo": "https://github.com/repoassay/repo-test-architect", "install": ["npm:repo-test-architect"], "stars": 0, "pushed": "2026-11-13T01:12:40Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:news.prh/revenue-agent", "name": "Revenue Agent — OpenAPI Audit & Change Detection", "kind": "mcp", "official": null, "desc": "Paid OpenAPI audit and API change detection for agents. $0.10 USDC per analysis via x402 on Base.", "repo": null, "install": ["https://agent.prh.news/mcp"], "stars": null, "pushed": null, "license": null, "plat": "revenue agent", "live": "Down · HTTP 502 (checked 2026-11-14)"}, {"id": "mcp:dev.reviewgate/reviewgate", "name": "ReviewGate", "kind": "mcp", "official": null, "desc": "Code review against your team standards, before the pull request: generator finds, judge confirms", "repo": null, "install": ["mcpb:https://github.com/ReviewGate/reviewgate/releases/download/v2.0.6/reviewgate-2.0.6-darwin-arm64.mcpb", "mcpb:https://github.com/ReviewGate/reviewgate/releases/download/v2.0.6/reviewgate-2.0.6-darwin-x64.mcpb", "mcpb:https://github.com/ReviewGate/reviewgate/releases/download/v2.0.6/reviewgate-2.0.6-linux-x64.mcpb", "mcpb:https://github.com/ReviewGate/reviewgate/releases/download/v2.0.6/reviewgate-2.0.6-linux-arm64.mcpb", "mcpb:https://github.com/ReviewGate/reviewgate/releases/download/v2.0.6/reviewgate-2.0.6-linux-x64-musl.mcpb", "mcpb:https://github.com/ReviewGate/reviewgate/releases/download/v2.0.6/reviewgate-2.0.6-win-x64.mcpb"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Be-Sure-Consulting/riskrover-mcp", "name": "RiskRover MCP", "kind": "mcp", "official": null, "desc": "Draft risk-based test plans and assess automated test coverage against product risks with RiskRover.", "repo": "https://github.com/Be-Sure-Consulting/riskrover-mcp", "install": ["npm:riskrover-mcp-server"], "stars": null, "pushed": null, "license": null, "plat": "riskrover", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.krishtoautomate/robotactions", "name": "RobotActions — AI-Driven Mobile + Web Test Automation", "kind": "mcp", "official": null, "desc": "Drive real Android & iOS devices and web browsers from natural language for mobile + web QA.", "repo": "https://github.com/krishtoautomate/robotactions", "install": ["https://{tenant}.robotactions.com/mcp/sse", "https://{tenant}.robotactions.com/mcp"], "stars": 0, "pushed": "2026-10-02T19:05:44Z", "license": null, "plat": "", "live": "Down · URLError: <urlopen error [Errno 11001] getaddrinfo failed> (checked 2026-11-13)"}, {"id": "mcp:com.runheed/runheed", "name": "Runheed", "kind": "mcp", "official": null, "desc": "Production errors your coding agent can read: search, stack traces, context, trends, resolve.", "repo": "https://github.com/getrunheed/runheed-plugin", "install": ["https://runheed.com/api/mcp"], "stars": 0, "pushed": "2026-11-09T01:29:10Z", "license": "MIT", "plat": "error resolution", "live": "Live · 663 ms · 12 tools (checked 2026-11-13)"}, {"id": "mcp:io.github.vince-gonzalez/saydo", "name": "SayDo", "kind": "mcp", "official": null, "desc": "Does the tool do what it says? Conformance receipts for MCP servers, and unknown when unchecked.", "repo": "https://github.com/vince-gonzalez/saydo", "install": ["pypi:saydo"], "stars": 0, "pushed": "2026-09-03T04:25:37Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:design.scoby/journeys", "name": "Scoby journey patterns", "kind": "mcp", "official": null, "desc": "Check a planned flow against shipped apps: missing steps and edge cases.", "repo": "https://github.com/kiyf2004/scoby", "install": ["https://scoby.design/mcp"], "stars": null, "pushed": null, "license": null, "plat": "scoby", "live": "Responds, sign-in needed (checked 2026-11-15)"}, {"id": "mcp:eu.scopematch/labs", "name": "ScopeMatch", "kind": "mcp", "official": null, "desc": "Search accredited testing labs and verify lab scope evidence from ScopeMatch.", "repo": null, "install": ["https://scopematch.eu/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Live · 1908 ms · 3 tools · free to try: `search_labs` answered without a key (checked 2026-11-13)"}, {"id": "mcp:io.github.shibbirweb/sendmock", "name": "SendMock", "kind": "mcp", "official": null, "desc": "Test email, SMS, payments and webhooks locally: read messages, OTPs and webhook deliveries.", "repo": "https://github.com/shibbirweb/sendmock", "install": ["npm:sendmock", "oci:ghcr.io/shibbirweb/sendmock:1.0.0"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:com.session-replay/session-replay", "name": "Session Replay", "kind": "mcp", "official": null, "desc": "Read and triage bug reports captured by Session Replay for your verified domains.", "repo": null, "install": ["https://session-replay.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "session replay", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:co.kymac.shelf/shelf-smoke", "name": "shelf-smoke — url smoke / headless QA", "kind": "mcp", "official": null, "desc": "url smoke / headless QA: desktop+phone → pass/fail JSON. MCP shelf.kymac.co", "repo": null, "install": ["https://shelf.kymac.co/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Down · URLError: <urlopen error [Errno 11001] getaddrinfo failed> (checked 2026-11-13)"}, {"id": "mcp:io.github.ryansmith4/sheriff-mcp", "name": "Sheriff", "kind": "mcp", "official": null, "desc": "MCP server for fixing static analysis issues from SARIF reports with AI agents", "repo": "https://github.com/ryansmith4/sheriff-mcp", "install": ["oci:ghcr.io/ryansmith4/sheriff-mcp:1.0.2"], "stars": 0, "pushed": "2026-07-25T03:12:00Z", "license": "Apache-2.0", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.willnewby/simpletel", "name": "simpletel", "kind": "mcp", "official": null, "desc": "Query your simpletel OpenTelemetry traces and account usage from a coding agent.", "repo": "https://github.com/willnewby/simpletel-mcp", "install": ["oci:ghcr.io/willnewby/simpletel-mcp:20261109.1604.14-d016369"], "stars": 0, "pushed": "2026-10-10T05:03:21Z", "license": "MIT", "plat": "simpletel", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.systasys/skeptopus", "name": "SkeptOpus", "kind": "mcp", "official": null, "desc": "Your AI says it's done. SkeptOpus goes and looks: commits, pushes, tests, files, deploys.", "repo": "https://github.com/systasys/skeptopus", "install": ["npm:skeptopus"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.wminno/slowscan", "name": "SlowScan", "kind": "mcp", "official": null, "desc": "Calm static analysis for AI-generated pages: structure, links and content sanity. No signup.", "repo": "https://github.com/wminno/slowscan", "install": ["https://slowscan.bigfloppy.net/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Live · 1062 ms (checked 2026-11-15)"}, {"id": "mcp:com.snagrelay/snagrelay", "name": "SnagRelay", "kind": "mcp", "official": null, "desc": "Bug reports your coding agent can fix: real element, console errors, failing requests with bodies.", "repo": "https://github.com/snagrelay/agent-plugin", "install": ["https://mcp.snagrelay.com/v1"], "stars": 0, "pushed": "2026-10-11T21:08:22Z", "license": "MIT", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.snapvisor/snapvisor", "name": "SnapVisor", "kind": "mcp", "official": null, "desc": "Visual regression testing over MCP: upload screenshots, review diffs, approve. No CI needed.", "repo": null, "install": ["https://mcp.snapvisor.io/"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.vicc/spill", "name": "Spill", "kind": "mcp", "official": null, "desc": "Pull TestFlight screenshot feedback from App Store Connect into AI coding agents.", "repo": "https://github.com/vicc/spill", "install": ["npm:@viccalexander/spill"], "stars": null, "pushed": null, "license": null, "plat": "app store connect", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.sohaibt/splera", "name": "Splera", "kind": "mcp", "official": null, "desc": "A/B testing for vibe coders: create, track, and ship experiments from your AI coding agent.", "repo": "https://github.com/sohaibt/splera", "install": ["npm:splera-mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Evozim/stack-trace-medic", "name": "Stack Trace Medic", "kind": "mcp", "official": null, "desc": "Coded error stack trace debugger and automated patch generator.", "repo": null, "install": ["https://stack-trace-medic-mcp.vercel.app/api/mcp"], "stars": null, "pushed": null, "license": null, "plat": "code", "live": "Live · 760 ms · 1 tools (checked 2026-11-13)"}, {"id": "mcp:io.github.stackvitals/stackvitals", "name": "StackVitals", "kind": "mcp", "official": null, "desc": "Known flaky tests, failing and slow CI, review flow, delivery and dependency risk from kept history.", "repo": null, "install": ["pypi:stackvitals"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.dii/stlink-mcp", "name": "stlink-mcp", "kind": "mcp", "official": null, "desc": "Program, run and inspect STM32 targets over ST-LINK; every result verified, unverified or failed.", "repo": "https://github.com/dii/stlink-mcp", "install": ["pypi:stlink-mcp"], "stars": 0, "pushed": "2026-11-08T07:42:07Z", "license": "MIT", "plat": "stm32", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.StockSharp/odysseus", "name": "StockSharp Odysseus", "kind": "mcp", "official": null, "desc": "Generate, compile, validate and backtest StockSharp trading strategies through local MCP.", "repo": "https://github.com/StockSharp/Odysseus", "install": ["nuget:StockSharp.Odysseus.Mcp"], "stars": 0, "pushed": "2026-10-09T17:36:07Z", "license": "NOASSERTION", "plat": "stocksharp", "live": "Not checked (runs locally)"}, {"id": "mcp:com.stresix/stresix", "name": "Stresix", "kind": "mcp", "official": null, "desc": "Load test your app on a real server from your agent. Get p95, errors and what ran out first.", "repo": "https://github.com/DevMatei/stresix-mcp", "install": ["https://stresix.com/mcp"], "stars": 0, "pushed": "2026-10-16T12:04:34Z", "license": "MIT", "plat": "", "live": "Down · HTTP 410 (checked 2026-11-13)"}, {"id": "mcp:ai.usesuperflow/tools", "name": "Superflow Free Tools", "kind": "mcp", "official": null, "desc": "19 free website QA and AI-visibility tools. Remote HTTP MCP, no account, no API key.", "repo": null, "install": ["https://usesuperflow.ai/api/mcp"], "stars": null, "pushed": null, "license": null, "plat": "website", "live": "Live · 2148 ms · 16 tools · free to try: `check_ai_visibility` answered without a key (checked 2026-11-13)"}, {"id": "mcp:io.github.GeroPalombo/swipium", "name": "Swipium", "kind": "mcp", "official": null, "desc": "Mobile QA on local Android Emulators and iOS Simulators: autopilot tests, evidence, reports.", "repo": "https://github.com/GeroPalombo/swipium", "install": ["npm:swipium"], "stars": 0, "pushed": "2026-11-10T20:07:35Z", "license": "MIT", "plat": "swipium", "live": "Not checked (runs locally)"}, {"id": "mcp:dev.taada/tada", "name": "Tada: automated QA for AI-written code", "kind": "mcp", "official": null, "desc": "Your coding agent asks Tada to work through a feature in a real browser and gets back a verdict.", "repo": null, "install": ["npm:tada-mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:tech.bugbrain/mcp", "name": "tech.bugbrain/mcp", "kind": "mcp", "official": null, "desc": "BugBrain QA platform for AI coding tools: autonomous exploratory testing, test plans, a11y audits.", "repo": null, "install": ["npm:@bugbrain/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.testchimp/qa", "name": "TestChimp", "kind": "mcp", "official": null, "desc": "QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.", "repo": "https://github.com/TestChimp/testchimp-mcp-client", "install": ["npm:@testchimp/cli", "https://mcp.testchimp.io/mcp"], "stars": 0, "pushed": "2026-11-13T04:44:26Z", "license": "MIT", "plat": "ai agents", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.sslugic/testera", "name": "Testera", "kind": "mcp", "official": null, "desc": "Free test management over MCP: projects, test cases, plans, runs, environments and tasks.", "repo": "https://github.com/sslugic/testera-cursor-plugin", "install": ["https://mcp.testera.io/mcp"], "stars": 0, "pushed": "2026-10-26T20:15:39Z", "license": "MIT", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.testiny/testiny-mcp", "name": "Testiny Test Management", "kind": "mcp", "official": null, "desc": "Create and manage test cases, test runs and results in Testiny from your AI assistant.", "repo": null, "install": ["https://app.testiny.io/api/v1/mcp-server"], "stars": null, "pushed": null, "license": null, "plat": "testiny", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:net.bigfloppy.testlens/testlens", "name": "TestLens", "kind": "mcp", "official": null, "desc": "Paste code + tests, get a strong/weak verdict with killed/survived mutants. Free API + MCP.", "repo": "https://github.com/wminno/testlens", "install": ["https://testlens.bigfloppy.net/mcp"], "stars": 0, "pushed": "2026-10-27T07:53:00Z", "license": null, "plat": "code", "live": "Live · 1852 ms · 2 tools · free to try: `testlens_health` answered without a key (checked 2026-11-13)"}, {"id": "mcp:io.github.LambdaTest/mcp", "name": "TestMu AI (formerly LambdaTest)", "kind": "mcp", "official": null, "desc": "Agentic AI quality engineering: run, debug and triage tests on real browsers and devices", "repo": "https://github.com/LambdaTest/mcp-server-guide", "install": ["https://mcp.lambdatest.com/mcp"], "stars": 0, "pushed": "2026-11-12T15:17:40Z", "license": "MIT", "plat": "testmu ai", "live": "Live · 862 ms · 88 tools · `listTunnels` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:io.github.TestOptim-AI/testoptim", "name": "TestOptim", "kind": "mcp", "official": null, "desc": "Run AI QA test runs on your web app and read the bugs they find, with steps to reproduce.", "repo": "https://github.com/TestOptim-AI/testoptim-mcp", "install": ["https://api.testoptim.com/api/mcp"], "stars": 0, "pushed": "2026-11-09T02:00:16Z", "license": "MIT", "plat": "web app", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:com.testorchestrator/testorchestrator", "name": "TestOrchestrator", "kind": "mcp", "official": null, "desc": "Test management for AI agents: cases, runs, results, cycles and traceability.", "repo": null, "install": ["https://api.testorchestrator.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.sallar-ba/testorim", "name": "Testorim", "kind": "mcp", "official": null, "desc": "AI browser tests from your coding agent: a verdict, failing steps, report, video and trace.", "repo": null, "install": ["npm:@testorim/cli"], "stars": null, "pushed": null, "license": null, "plat": "testorim", "live": "Not checked (runs locally)"}, {"id": "mcp:dev.testsy/testsy", "name": "Testsy", "kind": "mcp", "official": null, "desc": "Run plain-English web QA tests and inspect check results and evidence.", "repo": "https://github.com/testsy-ai/testsy-integrations", "install": ["https://app.testsy.dev/mcp"], "stars": 0, "pushed": "2026-11-10T11:43:13Z", "license": "MIT", "plat": "", "live": "Live · 1527 ms · 48 tools · `get_test` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:dev.testwatch/testwatch", "name": "TestWatch", "kind": "mcp", "official": null, "desc": "Run your end-to-end tests, read why they failed, write new tests. Sign in with OAuth.", "repo": null, "install": ["https://mcp.testwatch.dev/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:io.github.muhamad-0/traceo", "name": "Traceo", "kind": "mcp", "official": null, "desc": "Traceo bug recordings (console, network, user actions, environment) as context for coding agents.", "repo": "https://github.com/muhamad-0/traceo-skills", "install": ["https://www.traceo.dev/mcp"], "stars": 0, "pushed": "2026-11-10T09:48:35Z", "license": "MIT", "plat": "", "live": "Live · 1768 ms · 8 tools (checked 2026-11-13)"}, {"id": "mcp:io.github.AparajeetS/traintools", "name": "TrainTools", "kind": "mcp", "official": null, "desc": "Recommend paper-backed diagnostics for PyTorch and Hugging Face training problems.", "repo": "https://github.com/AparajeetS/Traintools", "install": ["pypi:traintools"], "stars": 0, "pushed": "2026-07-22T12:29:20Z", "license": "MIT", "plat": "pytorch/hugging face", "live": "Not checked (runs locally)"}, {"id": "mcp:io.trunk/mcp-server", "name": "Trunk Flaky Tests", "kind": "mcp", "official": null, "desc": "Flaky test detection, root cause analysis, and fix suggestions for development teams.", "repo": "https://github.com/trunk-io/mcp-server", "install": ["https://mcp.trunk.io/mcp"], "stars": 0, "pushed": "2026-03-13T19:19:02Z", "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:ai.turnsignal/turnsignal", "name": "TurnSignal for Playwright", "kind": "mcp", "official": null, "desc": "Read-only Playwright CI results for agents: new vs known failures, flaky tests, test history.", "repo": null, "install": ["npm:turnsignal"], "stars": null, "pushed": null, "license": null, "plat": "playwright", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.michaelw-pr/veridu", "name": "Veridu", "kind": "mcp", "official": null, "desc": "Verify AI-generated code before you commit: independent reviewers check it. PR review too.", "repo": "https://github.com/michaelw-pr/veridu-plugin", "install": ["https://api.veridu.io/mcp"], "stars": 0, "pushed": "2026-11-06T03:14:01Z", "license": "MIT", "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:com.vibe-fixer/vibefix", "name": "VibeFix", "kind": "mcp", "official": null, "desc": "Free check by an AI agent on your live app. On request: independent code review, fix, live re-check.", "repo": "https://github.com/yos88da/vibefix-mcp", "install": ["https://vibe-fixer.com/mcp"], "stars": 0, "pushed": "2026-11-12T12:28:55Z", "license": "MIT", "plat": "vibefix", "live": "Live · 1094 ms · 7 tools · `list_projects` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:com.getvigilia/vigilia", "name": "Vigilia", "kind": "mcp", "official": null, "desc": "Watches your live app, explains every problem in plain language and writes the fix prompt.", "repo": null, "install": ["https://app.getvigilia.com/mcp"], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Responds, sign-in needed (checked 2026-11-13)"}, {"id": "mcp:com.vinktar/mcp", "name": "Vinktar", "kind": "mcp", "official": null, "desc": "Error tracking for small teams and their coding agents.", "repo": "https://github.com/vinktarhq/agent", "install": ["https://mcp.vinktar.com/mcp"], "stars": 0, "pushed": "2026-10-21T01:02:11Z", "license": "MIT", "plat": "vinktar", "live": "Live · 2438 ms · 31 tools · `check_fix` asked for an API key (checked 2026-11-13)"}, {"id": "mcp:io.github.Weavatrix/weavatrix-quality", "name": "Weavatrix Quality", "kind": "mcp", "official": null, "desc": "Revision-bound quality planning, execution, evidence, proof, and Playwright authoring.", "repo": "https://github.com/Weavatrix/weavatrix-quality", "install": ["npm:@weavatrix/wvq"], "stars": 0, "pushed": "2026-09-19T12:54:10Z", "license": "MIT", "plat": "weavatrix quality", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Krrishkumar125/webhook-crash-lab-mcp", "name": "Webhook Crash Lab", "kind": "mcp", "official": null, "desc": "Lets coding agents crash-test webhook handlers and re-run until they survive retries.", "repo": "https://github.com/Krrishkumar125/webhook-crash-lab-mcp", "install": ["npm:webhook-crash-lab-mcp"], "stars": 0, "pushed": "2026-11-11T15:37:03Z", "license": "MIT", "plat": "", "live": "Not checked (runs locally)"}, {"id": "mcp:io.github.Br0ski777/webhook-tester", "name": "Webhook Tester API", "kind": "mcp", "official": null, "desc": "Test webhook endpoints — send requests, measure latency, validate responses. x402 micropayment.", "repo": "https://github.com/Br0ski777/webhook-tester-x402", "install": ["https://webhook-tester.api.klymax402.com/mcp"], "stars": 0, "pushed": "2026-09-02T19:58:05Z", "license": "MIT", "plat": "", "live": "Down · URLError: <urlopen error [SSL: TLSV1_ALERT_INTERNAL_ERROR] tlsv1 alert internal error (_ssl.c:1082)> (checked 2026-11-13)"}, {"id": "mcp:link.cyberelf.whetstone/tools", "name": "Whetstone", "kind": "mcp", "official": null, "desc": "Verifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.", "repo": "https://github.com/CarlSR9001/whetstone", "install": ["https://whetstone.cyberelf.link/mcp"], "stars": 0, "pushed": "2026-10-30T00:09:50Z", "license": "AGPL-3.0", "plat": "whetstone", "live": "Live · 1407 ms · 14 tools (checked 2026-11-13)"}, {"id": "mcp:com.twelvepermissions/x402-doctor", "name": "x402 Doctor", "kind": "mcp", "official": null, "desc": "Diagnose x402 seller endpoints: what is wrong with your 402 challenge, and how to fix it.", "repo": "https://github.com/tsharpe2282-web/twelve-permissions", "install": ["https://x402-doctor.tsharpe.workers.dev/mcp"], "stars": 0, "pushed": "2026-09-08T05:44:24Z", "license": null, "plat": "x402 seller endpoints", "live": "Live · 743 ms · 3 tools (checked 2026-11-13)"}, {"id": "mcp:pw.xtester/xtester", "name": "XTester Studio", "kind": "mcp", "official": null, "desc": "Desktop strategy development and testing with a built-in local stdio MCP server.", "repo": null, "install": [], "stars": null, "pushed": null, "license": null, "plat": "", "live": "Not checked (runs locally)"}]