90 agent tools in this category, ranked by GitHub stars for now. Hands-on test results will replace this ranking as they finish.
The three most-starred tools here. Not tested together yet.
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
claude plugin install mattpocock-skills@claude-plugins-officialList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defe
npx skills add DietrichGebert/ponytail --skill ponytail-debtShow ponytail measured impact as a scoreboard: less code, less cost, more speed, from the agentic benchmark averages. One-shot display.
npx skills add DietrichGebert/ponytail --skill ponytail-gain| Tool | Stars | Last update | License | |
|---|---|---|---|---|
| mattpocock-skills Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe co PluginAnthropic marketplace | 323,337 | MIT | ||
| ponytail-debt List every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did pon SkillInstall · skills CLI | 190,451 | MIT | ||
| ponytail-gain Show ponytail measured impact as a scoreboard: less code, less cost, more speed, from the agentic benchmark averages. One-shot display. SkillInstall · skills CLI | 190,451 | MIT | ||
| ponytail-gain Show ponytail's measured savings (code, cost, speed) from the benchmark. One-shot display. Use for /ponytail-gain, "what does ponytail save", "ponytai SkillInstall · skills CLI | 190,451 | MIT | ||
| ponytail-help Quick reference for ponytail's modes, skills, and commands. One-shot display. SkillInstall · skills CLI | 190,451 | MIT | ||
| ponytail-help Quick reference for ponytail levels, skills and commands. One-shot display. Use for /ponytail-help, "ponytail help", "how do I use ponytail". SkillInstall · skills CLI | 190,451 | MIT | ||
| constraint-driven-development Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, suppli SkillInstall · skills CLI | 117,221 | MIT | ||
| doubt-driven-development Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before p SkillInstall · skills CLI | 117,221 | MIT | ||
| idea-refine Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need SkillInstall · skills CLI | 117,221 | MIT | ||
| incremental-implementation Delivers changes incrementally in thin, verifiable slices. Use when implementing any feature or change that touches more than one file, or when pickin SkillInstall · skills CLI | 117,221 | MIT | ||
| interview-me Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% c SkillInstall · skills CLI | 117,221 | MIT | ||
| performance-optimization Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performa SkillInstall · skills CLI | 117,221 | MIT | ||
| planning-and-task-breakdown Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels SkillInstall · skills CLI | 117,221 | MIT | ||
| source-driven-development Grounds every implementation decision in official documentation. Use when you want to verify an approach against the official docs before implementing SkillInstall · skills CLI | 117,221 | MIT | ||
| ultrawork The binding ultrawork-mode directive. This file IS the directive; read it only when ultrawork mode is requested and the directive is not already in th SkillInstall · skills CLI | 70,897 | — | ||
| ulw-plan Explore-first planning consultant that writes one decision-complete work plan before coding. Use only on an explicit user request for the ulw-plan wor SkillInstall · skills CLI | 70,897 | — | ||
| example-command An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout SkillOfficial · AnthropicInstall · skills CLI | 47,064 | Apache-2.0 | ||
| example-skill This skill should be used when the user asks to "demonstrate skills", "show skill format", "create a skill template", or discusses skill development p SkillOfficial · AnthropicInstall · skills CLI | 47,064 | Apache-2.0 | ||
| learning-output-style Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style) PluginAnthropic marketplace | 47,064 | Apache-2.0 | ||
| receipts A personal Claude Code impact report for justifying your usage to a manager or a self-review: what you shipped, which projects it went to, and each pr PluginAnthropic marketplace | 47,064 | Apache-2.0 | ||
| writing-hookify-rules This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guid SkillOfficial · AnthropicInstall · skills CLI | 47,064 | Apache-2.0 | ||
| context-driven-development Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a `conductor/` directory. Scaffolds new project SkillInstall · skills CLI | 42,495 | MIT | ||
| track-management Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.m SkillInstall · skills CLI | 42,495 | MIT | ||
| workflow-patterns Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understan SkillInstall · skills CLI | 42,495 | MIT | ||
| create-agentsmd Prompt for generating an AGENTS.md file for a repository SkillInstall · skills CLI | 41,140 | MIT | ||
| create-architectural-decision-record Create an Architectural Decision Record (ADR) document for AI-optimized decision documentation. SkillInstall · skills CLI | 41,140 | MIT | ||
| create-implementation-plan Create a new implementation plan file for new features, refactoring existing code or upgrading packages, design, architecture or infrastructure. SkillInstall · skills CLI | 41,140 | MIT | ||
| create-readme Create a README.md file for the project SkillInstall · skills CLI | 41,140 | MIT | ||
| create-specification Create a new specification file for the solution, optimized for Generative AI consumption. SkillInstall · skills CLI | 41,140 | MIT | ||
| create-technical-spike Create time-boxed technical spike documents for researching and resolving critical development decisions before implementation. SkillInstall · skills CLI | 41,140 | MIT | ||
| krillinai-cli Use when an agent needs to build or operate the embedded KrillinAI CLI, choose a supported command, or interpret its JSON, manifest, subtitle, dubbing SkillInstall · skills CLI | 14,342 | Apache-2.0 | ||
| krillinai-pipeline Use when validating or documenting a multi-stage KrillinAI CLI output plan; the current pipeline command supports dry-run planning only, not end-to-en SkillInstall · skills CLI | 14,342 | Apache-2.0 | ||
| skill-template 技能创建模板。复制此目录并修改 SKILL.md 即可创建新技能。请将所有 <占位符> 替换为实际内容。 SkillInstall · skills CLI | 9,543 | — | ||
| workflow-schema-tuning Use when modifying `resources/workflow-schema.json` in cc-wf-studio to influence how AI agents generate workflows via the cc-workflow-ai-editor skill. SkillInstall · skills CLI | 5,455 | — | ||
| newproject Scaffold a new research project with standard directory structure, CLAUDE.md template, and documented README. Use this at the start of every new proje SkillInstall · skills CLI | 5,013 | — | ||
| sdd Implements the Spec-Driven Development lifecycle (Intent, Requirements, Design, Tasks, Build) for structured feature development. Use when the user wa SkillInstall · skills CLI | 5,013 | — | ||
| ask-then-build Clarify a feature, change, or refactor through questions, then write a build prompt for another agent. Use for /ask-then-build or requests to ask ques SkillInstall · skills CLI | 4,309 | MIT | ||
| skill-designer Design new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt that cr SkillInstall · skills CLI | 4,283 | MIT | ||
| skill-idea-miner Mine Claude Code session logs for skill idea candidates. Use when running the weekly skill generation pipeline to extract, score, and backlog new skil SkillInstall · skills CLI | 4,283 | MIT | ||
| skill-integration-tester Validate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (JSON schema compatibility), file naming c SkillInstall · skills CLI | 4,283 | MIT | ||
| no-comments Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints. SkillInstall · skills CLI | 4,152 | MIT | ||
| setup-pstack Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrid SkillInstall · skills CLI | 4,152 | MIT | ||
| cancel-ralph Codex-compatible cancel command for Ralph loop state, preserving the original command name. SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| ralph-loop Codex-compatible Ralph loop runner with dual engines (compat local state loop + optional open-ralph-wiggum backend). SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| spec-kit-vibe-compat Compatibility router for /speckit.* workflows into /vibe-first Codex execution. SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| speckit-analyze Perform cross-artifact consistency analysis across spec.md, plan.md, and tasks.md. Use after task generation to identify gaps, duplications, and incon SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| speckit-checklist Generate custom quality checklists for validating requirements completeness and clarity. Use to create unit tests for English that ensure spec quality SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| speckit-clarify Structured clarification workflow for underspecified requirements. Use before planning to resolve ambiguities through coverage-based questioning. Reco SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| speckit-constitution Create or update project governing principles and development guidelines. Use at project start to establish code quality, testing standards, and archi SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| speckit-implement Execute all tasks from the task breakdown to build the feature. Use after task generation to systematically implement the planned solution following T SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| speckit-plan Generate technical implementation plans from feature specifications. Use after creating a spec to define architecture, tech stack, and implementation SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| speckit-specify Create or update feature specifications from natural language descriptions. Use when starting new features or refining requirements. Generates spec.md SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| speckit-tasks Break down implementation plans into actionable task lists. Use after planning to create a structured task breakdown. Generates tasks.md with ordered, SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| tdd-guide Test-first development route for TDD, writing failing tests first, RED -> GREEN -> REFACTOR, and behavior-changing feature/bug/refactor work. Do not u SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| verification-before-completion Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready. Requires fresh verification output before suc SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| cc-sdd-new-agent Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end. Use when introducing a new agent, adding SkillInstall · skills CLI | 3,764 | MIT | ||
| kiro-impl Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually. SkillInstall · skills CLI | 3,764 | MIT | ||
| kiro-spec-batch Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by dependency wave. SkillInstall · skills CLI | 3,764 | MIT | ||
| command-creator This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command" SkillInstall · skills CLI | 2,679 | MIT | ||
| agy-delegate Delegate a coding task to the Google Antigravity CLI (`agy`) as a background implementer, then review its diff and land it yourself. Use this whenever SkillInstall · skills CLI | 2,601 | MIT | ||
| aider-delegate Delegate a coding task to Aider (`aider`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to SkillInstall · skills CLI | 2,601 | MIT | ||
| claude-delegate Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. U SkillInstall · skills CLI | 2,601 | MIT | ||
| cline-delegate Delegate a coding task to the Cline coding agent CLI (`cline`) as a background implementer, then review its diff and land it yourself. Use this whenev SkillInstall · skills CLI | 2,601 | MIT | ||
| codex-delegate Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user want SkillInstall · skills CLI | 2,601 | MIT | ||
| commandcode-delegate Delegate a coding task to the Command Code CLI (`cmd`) as a background implementer, then review its diff and land it yourself. Use this whenever the u SkillInstall · skills CLI | 2,601 | MIT | ||
| copilot-delegate Delegate a coding task to the GitHub Copilot CLI (`copilot`) as a background implementer, then review its diff and land it yourself. Use this whenever SkillInstall · skills CLI | 2,601 | MIT | ||
| cursor-delegate Delegate a coding task to the Cursor Agent CLI (`cursor-agent`) as a background implementer, then review its diff and land it yourself. Use this whene SkillInstall · skills CLI | 2,601 | MIT | ||
| delegate-setup Configure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and effort (or variant) dials. Discovers insta SkillInstall · skills CLI | 2,601 | MIT | ||
| grok-delegate Delegate a coding task to the Grok Build CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants SkillInstall · skills CLI | 2,601 | MIT | ||
| kimi-delegate Delegate a coding task to the Kimi Code CLI (`kimi`) as a background implementer, then review its diff and land it yourself. Use this whenever the use SkillInstall · skills CLI | 2,601 | MIT | ||
| mcode-delegate Delegate a coding task to the MiniMax Code CLI (`mcode`) as a background implementer, then review its diff and land it yourself. Use this whenever the SkillInstall · skills CLI | 2,601 | MIT | ||
| muse-delegate Delegate a coding task to Muse Code (`muse`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants SkillInstall · skills CLI | 2,601 | MIT | ||
| omp-delegate Delegate a coding task to Oh My Pi (`omp`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to SkillInstall · skills CLI | 2,601 | MIT | ||
| opencode-delegate Delegate a coding task to the OpenCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to SkillInstall · skills CLI | 2,601 | MIT | ||
| viberank Submit your AI coding usage (Claude Code, Codex, Gemini CLI) to viberank and read the leaderboard. MCP serverGitHub-verified authorLocal · npm | 121 | MIT | ||
| Clairvoyance Software design skills for AI coding agents, inspired by A Philosophy of Software Design. MCP serverVerified domain · clairvoyance.fyiRemote● Live | 18 | MIT | ||
| io.github.dawitlabs/capsule Compact, source-linked context packs that reduce token waste for coding agents. MCP serverGitHub-verified authorLocal · npm | 4 | MIT | ||
| Kitden See the MCP servers, plugins and skills Claude Code, Codex and Cursor load, and which skills got cut MCP serverGitHub-verified authorLocal · PyPI | 1 | Apache-2.0 | ||
| Sentinel-IR Structural IR of JS/TS/Python/Rust files for AI agents: risk and signals instead of raw source. MCP serverGitHub-verified authorLocal · npm | 1 | Apache-2.0 | ||
| AI Success Story First-person AI war-stories from coding sessions, searchable via MCP for prior-art consultation. MCP serverGitHub-verified authorRemoteDown | — | — | ||
| Corpole Requirements authority for AI coding agents: binding requirements and acceptance criteria. MCP serverVerified domain · corpole.comRemoteSign-in needed | — | — | ||
| Foo Guard Library Search and read free, scanned AI agent skills and configs. Read-only, no account. MCP serverVerified domain · fooguard.comRemote● Live | — | — | ||
| io.github.pooriaarab/vibelive Multiplayer for agentic coding terminals: live cursors, presence, chat. MCP serverGitHub-verified authorLocal · npm | 0 | MIT | ||
| io.github.pooriaarab/vibeshare-live Share a live agent coding session by URL. Spectate or invite in. MCP serverGitHub-verified authorLocal · npm | 0 | MIT | ||
| mcp-usage Find out which MCP servers you actually use: local, read-only audit of Claude Code transcripts. MCP serverGitHub-verified authorLocal · npm | 0 | MIT | ||
| Rules-Generator-Pro Automated .cursorrules and system prompt generator. MCP serverBulk publisher · 375 entriesGitHub-verified authorRemote● Live | — | — | ||
| SKILL.md Lint Lint a SKILL.md for frontmatter, structure, secrets and size. All 6 tools free. MCP serverVerified domain · moltlinestudio.comRemote● Live | 0 | MIT | ||
| Stochastly Desktop Local MCP access to Stochastly desktop nodes, diagnostics and research tools. MCP serverVerified domain · stochastly.comLocal · PyPI | 0 | MIT | ||
| thing Artifacts for any coding agent: a durable link with versions, diffs, and comments on the page. MCP serverGitHub-verified authorLocal · npm | 0 | MIT | ||
| turntax Per-turn token cost of AGENTS.md, CLAUDE.md and other agent instruction files, with safe fixes. MCP serverGitHub-verified authorLocal · npm | 0 | MIT |
Filters apply to the top 90 of 90 tools by stars. Full list for agents: ai-coding.json