1,660 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.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, s
npx skills add multica-ai/andrej-karpathy-skills --skill karpathy-guidelinesAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, o
npx skills add anthropics/skills --skill discernment-nudgeGenerate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline
npx skills add thedotmack/claude-mem --skill timeline-report| Tool | Stars | Last update | License | |
|---|---|---|---|---|
| karpathy-guidelines Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical SkillInstall · skills CLI | 232,934 | — | ||
| discernment-nudge After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, pr SkillOfficial · AnthropicInstall · skills CLI | 194,218 | — | ||
| timeline-report Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| weekly-digests Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one co SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| what-the What the? Use when the user wants a plain-English breakdown of something technical — the who, what, where, why, and when. SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| humanizer Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y cont SkillInstall · skills CLI | 68,896 | MIT | ||
| i-have-adhd Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific t SkillInstall · skills CLI | 61,133 | MIT | ||
| copy-editing When the user wants to edit, tighten, proofread, or refresh existing copy, or asks whether to keep, cut, or change a line in it, without rewriting fro SkillInstall · skills CLI | 60,203 | MIT | ||
| copywriting When the user wants to write or rewrite page copy (homepage, landing, pricing, feature), or asks which headline, promise, or message to lead with. Dia SkillInstall · skills CLI | 60,203 | MIT | ||
| skill-creator Create, edit, evaluate, and optimize skills, including benchmarking and description tuning for better triggering. SkillInstall · skills CLI | 53,498 | AGPL-3.0 | ||
| nature-polishing Polish, translate, or tighten existing academic prose while preserving facts, terminology, and evidence boundaries. Use for 论文润色、学术翻译、正文精简, or manuscr SkillInstall · skills CLI | 53,478 | Apache-2.0 | ||
| nature-response Draft, audit, or revise responses to peer review, revision cover letters, and marked-manuscript or LaTeX revision packages. Use for 审稿意见回复、逐点回复、返修信、 r SkillInstall · skills CLI | 53,478 | Apache-2.0 | ||
| nature-reviewer Provide evidence-grounded mock peer review of scientific manuscripts or excerpts, covering significance, validity, and major/minor concerns. Use for 模 SkillInstall · skills CLI | 53,478 | Apache-2.0 | ||
| nature-statistics Audit or improve manuscript statistical reporting, including experimental units, replication, uncertainty, tests, and figure statistics. Use for 统计审查、 SkillInstall · skills CLI | 53,478 | Apache-2.0 | ||
| nature-writing Draft or restructure scientific manuscript arguments, sections, and initial-submission materials from author-provided evidence. Use for 论文写作、章节起草、论证重构 SkillInstall · skills CLI | 53,478 | Apache-2.0 | ||
| researchwrite Compose, revise, or audit research proposals, opening reports, and research plans from supporting evidence. Use for 研究计划、开题报告、科研项目申请书. Invoked as rese SkillInstall · skills CLI | 53,478 | Apache-2.0 | ||
| ai-sre-incident-response Build AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions. SkillInstall · skills CLI | 49,672 | MIT | ||
| context-window-management Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot SkillInstall · skills CLI | 49,672 | MIT | ||
| llm-evaluation Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing. SkillInstall · skills CLI | 49,672 | MIT | ||
| explanatory-output-style Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style) PluginAnthropic marketplace | 47,064 | Apache-2.0 | ||
| math-olympiad "Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates SkillOfficial · AnthropicInstall · skills CLI | 47,064 | Apache-2.0 | ||
| security-guidance Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catch PluginAnthropic marketplace | 47,064 | Apache-2.0 | ||
| siege Work on one hard mathematics problem in rounds: each round a judge writes a few self-contained questions, independent workers answer them, and the jud SkillOfficial · AnthropicInstall · skills CLI | 47,064 | Apache-2.0 | ||
| solo Work on one hard mathematics problem in this session yourself, with no sub-agents: reason in stages, record each settled step in a notes file so that SkillOfficial · AnthropicInstall · skills CLI | 47,064 | Apache-2.0 | ||
| ai-debt-detector Use after generating code, after accepting AI suggestions, or when reviewing AI-written modules. Also use when code works but feels brittle, when erro SkillInstall · skills CLI | 42,495 | MIT | ||
| prompt-engineering-patterns This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", SkillInstall · skills CLI | 42,495 | MIT | ||
| agentic-eval Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Buildi SkillInstall · skills CLI | 41,140 | MIT | ||
| boost-prompt Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never writes code. Requires SkillInstall · skills CLI | 41,140 | MIT | ||
| diagnose Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture fit SkillInstall · skills CLI | 41,140 | MIT | ||
| doublecheck Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversaria SkillInstall · skills CLI | 41,140 | MIT | ||
| eval-driven-dev Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evalua SkillInstall · skills CLI | 41,140 | MIT | ||
| finalize-agent-prompt Finalize prompt file using the role of an AI agent to polish the prompt for the end user. SkillInstall · skills CLI | 41,140 | MIT | ||
| finnish-humanizer Detect and remove AI-generated markers from Finnish text, making it sound like a native Finnish speaker wrote it. Use when asked to "humanize", "natur SkillInstall · skills CLI | 41,140 | MIT | ||
| mentoring-juniors Socratic mentoring for junior developers and AI newcomers. Guides through questions, never answers. Triggers: "help me understand", "explain this code SkillInstall · skills CLI | 41,140 | MIT | ||
| noob-mode Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, SkillInstall · skills CLI | 41,140 | MIT | ||
| andrej-karpathy-perspective Andrej Karpathy的思维框架与表达方式。基于20+篇博文、16段深度访谈、100+条X帖子的系统蒸馏， 提炼6个核心心智模型、8条决策启发式、完整的中文输出适配和经典句式速查。 用途：作为思维顾问，用Karpathy的视角分析AI技术可靠性、学习方法、行业趋势、产品设计。 当用户提到「用 SkillInstall · skills CLI | 38,247 | MIT | ||
| elon-musk-perspective 马斯克的思维操作系统。基于传记、播客、推文、法庭证词、决策记录和外部批评的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用马斯克的视角分析问题、审视决策、拆解成本结构、挑战行业假设。 当用户提到「用马斯克的视角」「马斯克会怎么看」「Musk模式」「马斯克p SkillInstall · skills CLI | 38,247 | MIT | ||
| feynman-perspective 理查德·费曼的思维框架与表达方式。基于40+个一手来源的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用费曼的视角分析问题、审视决策、提供反馈。 当用户提到「用费曼的视角」「费曼会怎么看」「费曼模式」「feynman perspective」「费曼学习法」 SkillInstall · skills CLI | 38,247 | MIT | ||
| huashu-nuwa 女娲造人：输入人名/主题/甚至只是模糊需求，自动深度调研→思维框架提炼→生成可运行的人物Skill。 两种入口：(1)明确人名→直接蒸馏 (2)模糊需求→诊断推荐→再蒸馏。 触发词：「造skill」「蒸馏XX」「女娲」「造人」「XX的思维方式」「做个XX视角」「更新XX的skill」「升级XX的sk SkillInstall · skills CLI | 38,247 | MIT | ||
| ilya-sutskever-perspective Ilya Sutskever的思维框架与表达方式。基于12段一手对话、9篇学术论文、10小时宣誓证词、 27篇推荐阅读清单和14个权威二手来源的深度调研， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用Ilya的视角分析AI技术方向、安全策略、研究品味。 当用户提到 SkillInstall · skills CLI | 38,247 | MIT | ||
| mrbeast-perspective MrBeast（Jimmy Donaldson）的内容创造操作系统。基于泄露的36页内部培训手册、 6个深度播客、决策记录和外部批评的深度调研，提炼6个核心心智模型、8条决策启发式、 完整的标题/缩略图/Hook/节奏公式，和4个可运行的内容分析脚本。 激活后沉浸式扮演MrBeast，直接以「我」的 SkillInstall · skills CLI | 38,247 | MIT | ||
| munger-perspective 芒格的视角：逆向思考、认知偏误、跨学科分析、投资决策审视。说「用芒格的视角」「逆向思考一下」「这有什么认知偏误」「Lollapalooza效应」「能力圈之外」「激励结构是什么」时触发。泛泛的「这个决策靠谱吗」不要触发。 SkillInstall · skills CLI | 38,247 | MIT | ||
| naval-perspective Naval Ravikant的思维操作系统。基于著作、播客、推文、决策记录和外部批评的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 激活后沉浸式扮演Naval，直接以「我」的视角回应问题。 当用户提到「用Naval的视角」「Naval会怎么看」「纳瓦尔模式」「Naval pe SkillInstall · skills CLI | 38,247 | MIT | ||
| paul-graham-perspective Paul Graham的思维框架与表达方式。基于200+篇essays、12个播客/访谈、 Twitter/X分析、7位核心批评者视角和完整人生时间线的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用PG的视角分析创业、写作、产品和人生选择。 当用户提到「 SkillInstall · skills CLI | 38,247 | MIT | ||
| steve-jobs-perspective 乔布斯的视角：产品判断与评审、取舍决策、对人对事的直接反馈。说「用乔布斯的视角」「乔布斯会怎么看」「切换到乔布斯」「让乔布斯评一下」时使用；不在一般性问题上自动触发。 SkillInstall · skills CLI | 38,247 | MIT | ||
| sun-yuchen-perspective 孙宇晨（Justin Sun / 孙割）的思维框架与行为逻辑。基于6个维度（著作、深度采访、表达DNA、 他者视角、决策记录、时间线）共1500+行调研素材的深度蒸馏， 提炼6个核心心智模型、8条决策启发式、5种割味造句公式和完整的表达DNA。 用途：作为思维顾问，用孙宇晨的视角分析营销策略、注意力 SkillInstall · skills CLI | 38,247 | MIT | ||
| taleb-perspective 塔勒布(Nassim Nicholas Taleb)的思维框架与表达方式。基于40+个来源的深度调研， 提炼6个核心心智模型、9条决策启发式和完整的表达DNA。 用途：作为思维顾问，用塔勒布的视角分析问题、审视决策、质疑主流叙事。 当用户提到「用塔勒布的视角」「塔勒布会怎么看」「塔勒布模式」「反脆弱 SkillInstall · skills CLI | 38,247 | MIT | ||
| behavioral-modes AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type. SkillInstall · skills CLI | 33,495 | MIT | ||
| context-window-management Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit SkillInstall · skills CLI | 33,495 | MIT | ||
| mechanistic-interpretability-nnsight Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to ru SkillInstall · skills CLI | 33,495 | MIT | ||
| mechanistic-interpretability-pyvene Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal SkillInstall · skills CLI | 33,495 | MIT | ||
| mechanistic-interpretability-saelens Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable featu SkillInstall · skills CLI | 33,495 | MIT | ||
| mechanistic-interpretability-transformer-lens Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and a SkillInstall · skills CLI | 33,495 | MIT | ||
| planning Create and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a plan", "track progress", "star SkillInstall · skills CLI | 33,495 | MIT | ||
| prompt-caching Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching SkillInstall · skills CLI | 33,495 | MIT | ||
| prompt-engineer Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evalua SkillInstall · skills CLI | 33,495 | MIT | ||
| prompt-engineering-guidance Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with SkillInstall · skills CLI | 33,495 | MIT | ||
| prompt-engineering-instructor Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and SkillInstall · skills CLI | 33,495 | MIT | ||
| prompt-engineering-outlines Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and m SkillInstall · skills CLI | 33,495 | MIT | ||
| prompt-engineering-patterns Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability. SkillInstall · skills CLI | 33,495 | MIT | ||
| prompt-library Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniqu SkillInstall · skills CLI | 33,495 | MIT | ||
| behuman Reply like a real person, direct and warm, without lists or hedging. Use whenever the user says you sound robotic, asks you to be real or talk like a SkillInstall · skills CLI | 29,773 | MIT | ||
| caveman Terse mode: drop filler, articles and pleasantries, keep technical accuracy, about 75% fewer tokens, and stay in it. Load whenever the user asks for f SkillInstall · skills CLI | 29,773 | MIT | ||
| engineering-skills Find which engineering skill fits a task: architecture, frontend, backend, QA, DevOps, security, AI/ML, data, cloud. Use whenever the user is unsure w SkillInstall · skills CLI | 29,773 | MIT | ||
| named-persona-adversarial-review Use when a PR has architectural or UX impact, or automated review feels generic, and you want it reviewed through named engineers' documented views (T SkillInstall · skills CLI | 29,773 | MIT | ||
| senior-architect System architecture decisions with a written rationale: monolith vs microservices, database choice, scaling limits, ADRs, Mermaid diagrams. Load whene SkillInstall · skills CLI | 29,773 | MIT | ||
| senior-data-scientist Design experiments and analyze tabular data: A/B tests, causal inference, feature engineering, model evaluation. Use whenever the user asks how to set SkillInstall · skills CLI | 29,773 | MIT | ||
| senior-fullstack Start a fullstack project or audit a codebase: pick a stack (Next.js, FastAPI, MERN, Django), scaffold it and score code quality. Use whenever the use SkillInstall · skills CLI | 29,773 | MIT | ||
| senior-prompt-engineer Improve prompts and measure LLM quality: fix inconsistent prompts, build eval sets, score RAG retrieval, check agent tool configs. Use whenever the us SkillInstall · skills CLI | 29,773 | MIT | ||
| tech-stack-evaluator Compare frameworks or tech stacks before committing: side-by-side scoring, total cost of ownership, ecosystem health and migration risk. Use whenever SkillInstall · skills CLI | 29,773 | MIT | ||
| zoom-out Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to unders SkillInstall · skills CLI | 27,717 | MIT | ||
| baoyu-translate This skill should be used when the user asks to "translate", "翻译", "精翻", "translate article", "translate to Chinese", "translate to English", "改成中文", SkillInstall · skills CLI | 27,533 | MIT | ||
| clean-user-facing-text Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting prose while preserving SkillInstall · skills CLI | 27,381 | MIT | ||
| remove-ai-marks Remove multi-vendor AI provenance marks: invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B, always offer), and C2PA/EXIF/X SkillInstall · skills CLI | 27,381 | MIT | ||
| skill-inspector Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded sk SkillInstall · skills CLI | 25,921 | Apache-2.0 | ||
| deepeval Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications. PluginAnthropic marketplace | 19,468 | Apache-2.0 | ||
| idea-creator Generate and rank research ideas given a broad direction. Use when user says \"\u627eidea\", \"brainstorm ideas\", \"generate research ideas\", \"what SkillInstall · skills CLI | 19,162 | MIT | ||
| meta-optimize Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired SkillInstall · skills CLI | 19,162 | MIT | ||
| paper-plan Generate a structured paper outline from review conclusions and experiment results. Use when user says \"写大纲\", \"paper outline\", \"plan the paper\", SkillInstall · skills CLI | 19,162 | MIT | ||
| proof-checker Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, SkillInstall · skills CLI | 19,162 | MIT | ||
| proof-writer Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps SkillInstall · skills CLI | 19,162 | MIT | ||
| proof-writer Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps SkillInstall · skills CLI | 19,162 | MIT | ||
| research-refine Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review SkillInstall · skills CLI | 19,162 | MIT | ||
| research-refine Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative Claude review. Use SkillInstall · skills CLI | 19,162 | MIT | ||
| result-to-claim Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates resul SkillInstall · skills CLI | 19,162 | MIT | ||
| result-to-claim Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A secondary Codex agent e SkillInstall · skills CLI | 19,162 | MIT | ||
| think Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reas SkillInstall · skills CLI | 16,462 | MIT | ||
| prompt-master Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI too SkillInstall · skills CLI | 15,938 | MIT | ||
| dspy Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP' SkillInstall · skills CLI | 14,526 | MIT | ||
| evaluating-cosmos-policy Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, ru SkillInstall · skills CLI | 14,526 | MIT | ||
| fine-tuning-openvla-oft Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM con SkillInstall · skills CLI | 14,526 | MIT | ||
| fine-tuning-serving-openpi Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, SkillInstall · skills CLI | 14,526 | MIT | ||
| guidance Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with SkillInstall · skills CLI | 14,526 | MIT | ||
| instructor Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and SkillInstall · skills CLI | 14,526 | MIT | ||
| outlines Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and m SkillInstall · skills CLI | 14,526 | MIT | ||
| tensorboard Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Goog SkillInstall · skills CLI | 14,526 | MIT | ||
| weights-and-biases Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B SkillInstall · skills CLI | 14,526 | MIT | ||
| prompt-engineer Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test sui SkillInstall · skills CLI | 12,355 | MIT | ||
| the-fool Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red SkillInstall · skills CLI | 12,355 | MIT | ||
| hive.error-recovery Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up. SkillInstall · skills CLI | 11,161 | Apache-2.0 | ||
| hive.quality-monitor Periodically self-assess output quality to catch degradation before the judge does. SkillInstall · skills CLI | 11,161 | Apache-2.0 | ||
| content-research-writer 内容创作者、技术写作员在撰写博客、深度文章或技术文档时，使用此技能可开启全流程写作协作。它能帮你研究资料、构建大纲、逐段打磨并自动添加引用，快速优化Hook，让你高效产出高质量内容，告别孤军奋战！ SkillInstall · skills CLI | 9,543 | — | ||
| enhance-prompt Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and struc SkillInstall · skills CLI | 8,771 | Apache-2.0 | ||
| site-md Analyze a project description or site requirements and synthesize a project constitution into SITE.md for the Stitch Build Loop SkillInstall · skills CLI | 8,771 | Apache-2.0 | ||
| tool-calling-tutor Use when a tool-calling agent does not call a tool, sends wrong arguments, loops without stopping, or needs a function schema. Guides a four-branch di SkillInstall · skills CLI | 8,769 | MIT | ||
| story-deslop 网文去AI味。从表达、叙事用笔、故事因果三层诊断并修复文本，保留作者文风与已定剧情。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。 SkillInstall · skills CLI | 8,581 | MIT | ||
| story-import 逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构，兼容 story-long-write / story-short-write 后续写作流程；内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇幅自动分流。触发方式： SkillInstall · skills CLI | 8,581 | MIT | ||
| story-long-analyze 长篇网文拆文。保留黄金三章、逐章摘要、剧情、情绪、节奏、角色、设定和文风接口，以连续章节块完成因果、双时间线、关系与三维节奏分析；兼容旧成果直接使用、按需增强和断点续跑。含可选三层灵感库管道（灵感库、跨书灵感聚合、更新灵感库）。触发方式：/story-long-analyze、/长篇拆文、「帮我拆这 SkillInstall · skills CLI | 8,581 | MIT | ||
| story-long-write 长篇网文规划与写作。支持只讨论结构、只写大纲或指定细纲，明确要求正文后再写章节。触发方式：/story-long-write、/写长篇、「帮我开书」「定设定」「出卷纲」「规划剧情」「写大纲」「补细纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。 SkillInstall · skills CLI | 8,581 | MIT | ||
| story-publish 小说发布准备：调用即生成并保存发布资料，缺失字段留空；按平台整理书名、笔名、分类、标签及所需简介。触发方式：/story-publish、/发布资料、「填写平台建书资料」「建书表单」「起书名/写简介/选标签用于发布」；正文累计约 2 万字、准备上架时也适用。当前适配番茄长篇与短故事（短故事无需简介） SkillInstall · skills CLI | 8,581 | MIT | ||
| story-review 多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下 SkillInstall · skills CLI | 8,581 | MIT | ||
| story-setup 网文写作工具集基础设施部署与检查。为 Claude Code / OpenCode / Codex / Google Antigravity / ZCode / OpenClaw / Reasonix 提供内置适配；Web AI / 通用 Agent 可走 skills + AGENTS.md 文件 SkillInstall · skills CLI | 8,581 | MIT | ||
| story-short-analyze 短篇网文拆文。拆解爆款短篇小说（番茄短篇 / 故事会 / 知乎盐言 / 追妻 / 世情 / 重生 / 虐渣等通俗题材）的故事核、结构、情感线、反转设计、写作手法、共鸣层次。单一全量拆解管道：跑完 Stage 2-6 产出完整拆文报告，落盘到 拆文库/{书名}/，下游 story-short-writ SkillInstall · skills CLI | 8,581 | MIT | ||
| story-short-write 短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。 SkillInstall · skills CLI | 8,581 | MIT | ||
| brainstorming 在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能、修改行为，或筹划任何新东西，无论是软件还是软件之外（一场分享、一门生意、一次装修）。 SkillInstall · skills CLI | 8,535 | MIT | ||
| diagnosing-superpowers 当一次 superpowers 会话出了问题、你的人类伙伴想知道原因时使用——重复劳动、无视计划、磕磕绊绊、结果质量差、某个技能没触发、"太慢了"、"为什么这么贵"、"它到底在干什么"——或者想给 superpowers 维护者整理一份 bug 报告；适用于当前会话，或按 id / 路径指定的过往会 SkillInstall · skills CLI | 8,535 | MIT | ||
| executing-plans 当你要在当前会话里亲自担任实现者执行一份实现计划时使用——你的人类伙伴选择了内联执行，或者没有可用的子智能体工具 SkillInstall · skills CLI | 8,535 | MIT | ||
| finishing-a-development-branch 当实现完成、所有测试通过、需要决定如何集成这份工作时使用 SkillInstall · skills CLI | 8,535 | MIT | ||
| receiving-code-review 收到代码审查反馈后、实施建议之前使用，尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证，而非敷衍附和或盲目执行 SkillInstall · skills CLI | 8,535 | MIT | ||
| requesting-code-review 完成任务、实现重要功能或合并前使用，用于验证工作成果是否符合要求 SkillInstall · skills CLI | 8,535 | MIT | ||
| systematic-debugging 遇到任何 bug、测试失败或异常行为时使用，在提出修复方案之前执行 SkillInstall · skills CLI | 8,535 | MIT | ||
| test-driven-development 在实现任何功能或修复 bug 时使用，在编写实现代码之前 SkillInstall · skills CLI | 8,535 | MIT | ||
| verification-before-completion 在宣称工作完成、已修复或测试通过之前使用，在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功；始终用证据支撑断言 SkillInstall · skills CLI | 8,535 | MIT | ||
| writing-plans 当你有规格说明或需求用于多步骤任务时使用，在动手写代码之前 SkillInstall · skills CLI | 8,535 | MIT | ||
| research-paper-writing Improve academic paper writing quality for ML/CV/NLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation. Use SkillInstall · skills CLI | 8,332 | MIT | ||
| brainstorming Use before implementing a feature, a change in behavior, or a bug fix — however small. Not for questions, checks, or edits that change no behavior (ty SkillInstall · skills CLI | 8,239 | Apache-2.0 | ||
| importing-a-codebase Use when asked to create the initial spec graph for an existing codebase that has source code but no specs. Normally reached via setting-up-a-project. SkillInstall · skills CLI | 8,239 | Apache-2.0 | ||
| setting-up-a-project Use when asked to set up, onboard, initialize, or spec a project with no spec graph, or when invoked by the app's Set-up-project card. Not for ordinar SkillInstall · skills CLI | 8,239 | Apache-2.0 | ||
| spec-graph Use when locating, reading, creating, updating, or validating project specs, or when work is governed by or may alter a documented boundary, contract, SkillInstall · skills CLI | 8,239 | Apache-2.0 | ||
| starting-a-new-project Use when the workspace is empty, has no code, and the user brings a raw project idea. Normally reached via setting-up-a-project; not for an existing p SkillInstall · skills CLI | 8,239 | Apache-2.0 | ||
| todos Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit pla SkillInstall · skills CLI | 8,239 | Apache-2.0 | ||
| writing-specs Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill nam SkillInstall · skills CLI | 8,239 | Apache-2.0 | ||
| goal-prompt Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex. Use when the user asks to create, write, rewrite, improve, compress, cl SkillInstall · skills CLI | 8,179 | CC-BY-SA-4.0 | ||
| writing-lean-proofs Writes and reviews structured Lean 4 proofs and designs Lean libraries following Mathlib conventions. Use when proving theorems in Lean, formalizing m SkillInstall · skills CLI | 8,179 | CC-BY-SA-4.0 | ||
| context-engineering-advisor Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably. SkillInstall · skills CLI | 8,014 | — | ||
| ljg-relationship Relationship analyst combining structural diagnostics (5-layer framework) with psychoanalytic depth (transference, unconscious patterns, resistance). SkillInstall · skills CLI | 7,740 | MIT | ||
| ljg-structure 找出一段信息中母题级别的结构，把抽象关系展开回具体可见的现象，再用风洞检验关键因果与边界。USE WHEN user says '找结构', '母题是什么', '结构风洞', '背后的结构', '不要只做AB测试', or wants the generative mechanism beneath SkillInstall · skills CLI | 7,740 | MIT | ||
| ljg-think 追本之箭——纵向深钻思维工具。给一个观点、现象或问题，像箭一样一路向下钻到不可再分的本质。Use when user says '想透', '追本', '本质是什么', '为什么会这样', '深挖', '钻到底', 'think deep', 'drill down', or wants to tr SkillInstall · skills CLI | 7,740 | MIT | ||
| tune-enemy-ai Build, debug, balance, or test combat enemy AI for playable action games. Use for aggro, target selection, navigation, spacing, attack choices, telegr SkillInstall · skills CLI | 7,464 | MIT | ||
| jev-decision Use Jev to select among available tools, skills or agents, or evaluate outputs against explicit rubrics. Use when the user requests Jev or a bounded d SkillInstall · skills CLI | 7,451 | — | ||
| gepa-optimize-anything Automatically improve any text artifact that can be scored — prompts, programs/code, configs, specs, regex/SQL/schemas, agent scaffolds, or encoded se SkillInstall · skills CLI | 7,427 | MIT | ||
| ai-pricing When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins. Also use when the user mentions 'AI pri SkillInstall · skills CLI | 7,167 | — | ||
| content-to-pipeline When the user wants to turn content into revenue, build a content-led GTM motion, reverse engineer distribution, or repurpose content across platforms SkillInstall · skills CLI | 7,167 | — | ||
| expansion-retention When the user wants to reduce churn, build expansion revenue, automate customer success, or optimize net revenue retention. Also use when the user men SkillInstall · skills CLI | 7,167 | — | ||
| gtm-metrics When the user wants to define GTM metrics, build a metrics dashboard, measure pipeline efficiency, or track AI product performance. Also use when the SkillInstall · skills CLI | 7,167 | — | ||
| positioning-icp When the user wants to define their ideal customer profile, position an AI product, build messaging architecture, or validate product-market fit. Also SkillInstall · skills CLI | 7,167 | — | ||
| sales-motion-design When the user wants to choose between PLG and sales-led, design a sales motion, optimize time-to-first-value, or build a value-before-purchase experie SkillInstall · skills CLI | 7,167 | — | ||
| the-fool Use when challenging ideas, plans, decisions, or proposals. Invoke to play devil's advocate, run a pre-mortem, red team, stress test assumptions, audi SkillInstall · skills CLI | 7,167 | — | ||
| tlc-discover Thinks through new or large projects: turns a vague idea into a design doc with a clear product problem and the technical solution. Use when exploring SkillInstall · skills CLI | 7,167 | — | ||
| tlc-plan Turns a request, ticket, PRD, design or thread into one plan a human approves and a builder can act on without the conversation: asks every gray area SkillInstall · skills CLI | 7,167 | — | ||
| tlc-prd Interviews an idea into a PRD file covering situation, problem, success, boundary, and journey states, and stops before any technical design. Use when SkillInstall · skills CLI | 7,167 | — | ||
| darwin-skill Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt SkillInstall · skills CLI | 6,910 | MIT | ||
| commit-ko AI(Claude 등)가 제안한 한글 커밋 메시지의 사무적·번역투 어휘("~을 수행함", "~을 진행함", "~적 개선을 실시함" 등)를 실제 개발자가 쓰는 자연스러운 한국어 커밋 메시지로 다듬는 스킬. humanize-korean과 달리 산문 문단이 아니라 1~2줄짜 SkillInstall · skills CLI | 6,534 | MIT | ||
| humanize AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 shim 의 route_hint 가 정한 경로(light 1콜 · standard 2콜 · heavy 3+콜)로 실행하고 `--strict`면 heavy 고정. 트리거 — SkillInstall · skills CLI | 6,534 | MIT | ||
| humanize-korean AI(ChatGPT·Claude·Gemini)가 쓴 한글 텍스트를 사람이 쓴 글처럼 진단·윤문·검증한다. 번역투, 기계적 병렬, 관용구, 피동, 접속사, 균일한 리듬 등 10대 카테고리 85개 패턴을 다루며 route_hint에 따라 light·standard·heav SkillInstall · skills CLI | 6,534 | MIT | ||
| humanize-korean AI(ChatGPT·Claude·Gemini)가 쓴 한글 텍스트를 사람이 쓴 글처럼 윤문한다. 번역투·영어 인용 과다·기계적 병렬·관용구·피동 남용·접속사 남발·리듬 균일·이모지/불릿 과다 등 10대 카테고리 70개 AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리 SkillInstall · skills CLI | 6,534 | MIT | ||
| humanize-korean AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 85개 AI 티 패턴을 탐지 SkillInstall · skills CLI | 6,534 | MIT | ||
| humanize-redo 가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능. humanize-korean strict 윤문(Phase B)을 기존 run_id에 재실행해 잔존 finding을 처리한다. 트리거 — "/humanize-redo". SkillInstall · skills CLI | 6,534 | MIT | ||
| humanize-scan 한글 글에 AI 티가 얼마나 있는지 재고, 실제로 고치면 어떻게 되는지 표본으로 보여주는 정찰 스킬. 실측 판별력 상위 6개만 본다. 워크스페이스·진단·게이트·서브에이전트 없이 이 대화 안에서 끝낸다(파일 0개, 서브에이전트 0회). 손볼 게 많다고 나오면 전수 윤문은 SkillInstall · skills CLI | 6,534 | MIT | ||
| grill-me 一个用来打磨计划或设计的持续追问式访谈。 SkillInstall · skills CLI | 5,774 | MIT | ||
| grilling 围绕计划、decision 或 idea 持续追问用户。适用于用户想对自己的思路做压力测试，或使用任何 “grill” 触发措辞时。 SkillInstall · skills CLI | 5,774 | MIT | ||
| loop-me 在这个工作区中，就我想构建的工作流规格访谈我。 SkillInstall · skills CLI | 5,774 | MIT | ||
| teach 在这个工作区中教用户一个新技能或概念。 SkillInstall · skills CLI | 5,774 | MIT | ||
| to-questionnaire 把你无法完整回答的 decision 转成一份交给他人填写的 questionnaire。 SkillInstall · skills CLI | 5,774 | MIT | ||
| wait-what 停一下：刚才那条消息没有说清楚，重新表述一遍。 SkillInstall · skills CLI | 5,774 | MIT | ||
| writing-beats Writing, exploit——把原始素材组装成一段节拍旅程，在某个 beat 依赖一个术语之前先把它 grounded。 SkillInstall · skills CLI | 5,774 | MIT | ||
| writing-fragments Writing, explore：挖掘原始 fragments，暂不施加任何结构。 SkillInstall · skills CLI | 5,774 | MIT | ||
| writing-shape Writing, exploit：把原始素材塑造成文章，一段一段地推进。 SkillInstall · skills CLI | 5,774 | MIT | ||
| Ask Jev Evaluate state with typed choice, score, and probability questions. MCP serverGitHub-verified authorRemoteSign-in needed | 5,294 | MIT | ||
| anti-hallucination ALWAYS activate this skill. Apply these rules to every task regardless of domain. This skill governs how Claude Code verifies information, writes code SkillInstall · skills CLI | 5,013 | — | ||
| bayesian-estimation This skill covers Bayesian estimation and inference in quantitative social science. Use when the user is specifying priors, running MCMC, diagnosing c SkillInstall · skills CLI | 5,013 | — | ||
| causal-inference This skill covers causal inference methods in observational and quasi-experimental settings. Use when the user is implementing, choosing between, or d SkillInstall · skills CLI | 5,013 | — | ||
| causal-inference-mixtape This skill should be used when the user asks to "implement a DiD regression", "write a causal inference pipeline", "set up an event study", "implement SkillInstall · skills CLI | 5,013 | — | ||
| causal-ml This skill covers causal machine learning methods in applied economics and quantitative social science. Use when implementing or choosing between mode SkillInstall · skills CLI | 5,013 | — | ||
| e1 E1-Quantitative Analysis Guide with Code Generation & Sensitivity Analysis VS-Enhanced with Full 5-Phase process: Avoids obvious analyses, explores in SkillInstall · skills CLI | 5,013 | — | ||
| e2 Agent E2 - Qualitative Coding Specialist - Systematic coding and theme development. Covers codebook development, coding strategies, saturation assessm SkillInstall · skills CLI | 5,013 | — | ||
| e3 Agent E3 - Mixed Methods Integration Specialist - Qual-Quant data integration and meta-inference. Covers joint display creation, integration strategie SkillInstall · skills CLI | 5,013 | — | ||
| empirical-playbook This skill covers applied microeconomic empirical methods and research design. Use when the user is selecting an identification strategy, comparing es SkillInstall · skills CLI | 5,013 | — | ||
| estimate Run a structural estimation pipeline — routes to /workflows:work with estimation context from empirical-playbook SkillInstall · skills CLI | 5,013 | — | ||
| f5 Humanization Quality Verifier - Ensures transformation integrity and quality Validates that humanization preserves meaning, citations, and academic st SkillInstall · skills CLI | 5,013 | — | ||
| g1 VS-Enhanced Journal Matcher with Journal Intelligence MCP — Real-time journal data pipeline with checkpoint-based human decisions. Uses OpenAlex + Cro SkillInstall · skills CLI | 5,013 | — | ||
| g2 Publication Specialist - Writing, Review, Pre-registration & Quality Assurance Light VS applied: Avoids template-based writing + audience-specific mes SkillInstall · skills CLI | 5,013 | — | ||
| g5 VS-Enhanced Academic Style Auditor - Academic Writing Quality Analysis Identifies 24+ writing patterns that reduce scholarly quality, adapted from Wik SkillInstall · skills CLI | 5,013 | — | ||
| g6 VS-Enhanced Academic Style Humanizer - Transforms writing patterns to achieve authentic scholarly voice Applies transformations from G5 analysis to cr SkillInstall · skills CLI | 5,013 | — | ||
| game-theory This skill covers game-theoretic methods in structural econometrics and industrial organization. Use when the user is working with strategic interacti SkillInstall · skills CLI | 5,013 | — | ||
| humanize Humanization Pipeline Orchestrator v3.1 - Multi-pass 4-layer transformation pipeline Orchestrates G5 (Auditor), G6 (Humanizer), F5 (Verifier) in seque SkillInstall · skills CLI | 5,013 | — | ||
| i0 Systematic Review Pipeline Orchestrator - Coordinates systematic literature review automation Manages the complete 7-stage PRISMA 2020 pipeline from r SkillInstall · skills CLI | 5,013 | — | ||
| identification-proofs This skill covers formal identification arguments and proofs in structural and reduced-form econometrics. Use when the user needs to prove or formaliz SkillInstall · skills CLI | 5,013 | — | ||
| universal-ma-codebook Universal Meta-Analysis Codebook v2.2 - AI-Human collaboration for meta-analysis data extraction. 4-layer design: Identifiers, Statistics, AI Provenan SkillInstall · skills CLI | 5,013 | — | ||
| x1 Research Guardian - Ethics Advisory & Bias Detection across all research stages Enhanced VS 3-Phase process: Surface-level screening, deep contextual SkillInstall · skills CLI | 5,013 | — | ||
| occams-razor Stop overthinking and answer with what we actually know for sure, how you know, and a confidence %. Use for "occams-razor", or when the user asks what SkillInstall · skills CLI | 4,309 | MIT | ||
| risky-changes Verify assumptions before implementing large or risky changes to APIs, provider data, billing, pricing, quotas, or defaults. Use when a mistake could SkillInstall · skills CLI | 4,309 | MIT | ||
| stop-overthinking Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking. SkillInstall · skills CLI | 4,309 | MIT | ||
| sharpen Make a task deeper, not bigger, then rewrite the prompt. Use for /sharpen. SkillInstall · skills CLI | 4,298 | MIT | ||
| show-me-your-work Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by defa SkillInstall · skills CLI | 4,298 | MIT | ||
| drawdown-circuit-breaker Evaluate account-level drawdown circuit breaker rules from trader-memory-core state and decide whether new trade risk is allowed today. Uses realized SkillInstall · skills CLI | 4,283 | MIT | ||
| agentica-prompts Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity SkillInstall · skills CLI | 3,949 | MIT | ||
| llm-tuning-patterns LLM Tuning Patterns SkillInstall · skills CLI | 3,949 | MIT | ||
| premortem Identify failure modes before they occur using structured risk analysis SkillInstall · skills CLI | 3,949 | MIT | ||
| prove Formal theorem proving with research, testing, and verification phases SkillInstall · skills CLI | 3,949 | MIT | ||
| tldr-overview Get a token-efficient overview of any project using the TLDR stack SkillInstall · skills CLI | 3,949 | MIT | ||
| tldr-router Maps questions to the optimal tldr command. Use this to pick the right layer SkillInstall · skills CLI | 3,949 | MIT | ||
| tldr-stats Show full session token usage, costs, TLDR savings, and hook activity SkillInstall · skills CLI | 3,949 | MIT | ||
| validate-agent Validation agent that validates plan tech choices against current best practices SkillInstall · skills CLI | 3,949 | MIT | ||
| wiring Wiring Verification SkillInstall · skills CLI | 3,949 | MIT | ||
| context-fundamentals This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| evaluating-machine-learning-models Evaluate trained machine learning models with the right metrics and comparison logic. Use for benchmark review, threshold selection, calibration, vali SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| explaining-machine-learning-models Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| math-tools Deterministic mathematical computation using SymPy. Use for ANY math operation requiring exact/verified results - basic arithmetic, algebra (simplify, SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| mathematical-logic-expert Expert in formal logic, model theory, computability, and foundations of mathematics SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| nowait-reasoning-optimizer Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Re SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| performing-causal-analysis Estimate causal effects from existing data. Use when fitting or interpreting DiD, ITS, synthetic control, regression discontinuity, or other treatment SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| writing-plans Use when you have a spec or requirements for a multi-step task, before touching code SkillInstall · skills CLI | 3,816 | Apache-2.0 | ||
| autoresearch Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through m SkillInstall · skills CLI | 3,814 | MIT | ||
| expert-panel Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pag SkillInstall · skills CLI | 3,814 | MIT | ||
| personal-strategic-signal-intelligence Turn an executive or operator's private reading, highlights, notes, social bookmarks, and applied work into source-grounded decision intelligence. Use SkillInstall · skills CLI | 3,814 | MIT | ||
| optimize-agent-prompt Builds and improves Browserbase Agent API demos through an Autobrowse-style outer loop: run a fixed task, collect Agent messages and session logs, sco SkillInstall · skills CLI | 3,757 | — | ||
| hard-predict-future Activate this agent for any future-oriented question that requires deep quantitative analysis, historical precedents, and structured scenario planning SkillInstall · skills CLI | 3,743 | MIT | ||
| rag-evaluation-harness Evaluate retrieval and citation behavior for RAG pipelines from deterministic JSONL fixtures. Use when an agent needs offline Recall@K, reciprocal ran SkillInstall · skills CLI | 3,743 | MIT | ||
| soft-predict-future Activate this skill for ANY future-oriented question. Triggers include: "Will [X]?", "Who will win [X]?", "What happens to [X]?", "Can [X] succeed?", SkillInstall · skills CLI | 3,743 | MIT | ||
| impl-validator Independently check whether an implementation matches its stated goal and return PASS/WARN/FAIL with actionable issues. Use for second-opinion validat SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-narrate Turn a wiki topic into a cited Markdown briefing, plain-language explanation, or progressive lecture. Use this skill for topic-based briefing, explana SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-query Search and synthesize answers from the compiled Obsidian wiki, including cited and multi-hop answers. Use for questions about existing wiki knowledge SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-rebuild Archive and rebuild wiki knowledge from source, or restore a prior archive. Use for full restart/recovery when incremental repair is inappropriate; th SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-setup Initialize or repair an Obsidian wiki vault's required structure and configuration. Use for new-vault setup, .env/config creation, reconfiguration, or SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-stage-commit Review staged wiki writes and promote accepted pages to final locations when WIKI_STAGED_WRITES is enabled. Use for staging approval/commit; rejected SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-status Report wiki ingestion/completeness state, pending source delta, structural insights, or maintenance equilibrium. Use for remaining-work/status questio SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-switch List, create, or switch named Obsidian wiki vault profiles under the global config directory. Use when changing the active vault, checking which vault SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-synthesize Find recurring concept combinations across the wiki that lack an explicit synthesis page, then create cross-cutting synthesis pages. Use for knowledge SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-update Sync knowledge from the current project into the Obsidian wiki. Use when work already in the current project should be distilled into the vault; named SkillInstall · skills CLI | 3,724 | MIT | ||
| five-whys Finds the root cause of a bug, failure or recurring problem by asking "why" until the answer is a cause you can fix. Use when the user asks why someth SkillInstall · skills CLI | 3,699 | — | ||
| onboard Explains this repository's shared Claude Code setup to a new teammate, covering what is committed and shared, what stays personal, and what the team-k SkillInstall · skills CLI | 3,699 | — | ||
| ccf-common Required shared preflight for every CCFA skill after ccf-humanization: apply routing, scope, prerequisites, evidence rules, handoffs, and artifact con SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-experiment-designer Design and interpret CCF experiments: datasets, baselines, metrics, ablations, run requirements, observed feedback, and result-table contents. Use for SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-humanization Required first preflight before every CCFA skill, including research, review, retrieval, experiments, visuals, and maintenance. Keep reasoning and com SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-idea-optimizer Develop and optimize rough CCF research ideas into problems, insights, mechanisms, and evidence plans. Use for 优化idea, 具象化idea, 找方向, 方向探索, and rescue SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-idea-reviewer Assess research ideas for value, novelty, insight, and mechanism. Use for 思路审核, 靠谱吗, 值得做吗, 创新够不够, idea review, scoring, and ranking; no numeric-score SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-integrity-auditor Audit existing CCF claims, numbers, terminology, and citations against supplied or verified evidence. Use for 引用核验, claim审计, 数字一致性, and BibTeX/context SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-literature-monitor Scan recent arXiv/OpenReview papers, venue feeds, labs, and competitors for overlap. Use for 竞品监控, 新论文追踪, 论文跟踪, and recurring novelty watch. Give date SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-literature-searcher Find and verify external literature, prior art, datasets, benchmarks, and citation candidates. Use for 文献检索, 相关工作, benchmark搜索, and research opportuni SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-paper-reviewer Review manuscript claims, evidence, and writing without rewriting. Use for 文章审核, 审稿, 稿件有什么硬伤, 结论站得住吗, 投稿成熟度, writing review, and version comparison. R SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-paper-to-exemplar Distill supplied paper PDFs into writing exemplar cards and register a requested personal library. Use for PDF to writing exemplar, 写作范例, and reusable SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-paper-writer Draft, revise, polish, compress, or presentation-adapt CCF manuscript prose. Use for 写作, 润色论文, research documents to complete papers, 完整初稿, 实验留空, 改写, SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-pipeline-orchestrator Plan or coordinate CCF research stages, goals, gates, artifacts, and ccfa.yaml state. Use for 任务拆解, 流程规划, project status, end-to-end coordination, and SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-project-scaffolder Initialize CCF project folders, LaTeX templates, artifact directories, and ccfa.yaml. Use for 项目初始化, 目录搭建, and paper template setup. Preserve existing SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-rebuttal-writer Write CCF rebuttals, author responses, revision ledgers, response letters, and resubmission plans. Use for 审稿意见回复, rebuttal, revision ledger, and 重投迁移 SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-research-engineer Implement and debug research code, select suitable codebases, reproduce baselines, map mechanisms into model architecture, and optimize training from SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-skill-forger Maintain and audit Codex/CCFA skills, triggers, references, scripts, docs/SVG diagrams, installation dependencies, and release validation. Use for ski SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-submission-checker Check CCF venue rules and submission packages: template, pages, anonymity, PDF build, metadata, and reproducibility. Use for 投稿检查, 会议格式, page limits, SkillInstall · skills CLI | 3,562 | MIT | ||
| ccf-visual-composer Render and redesign scientific figures, visual tables, and method/architecture diagrams from supplied content, including biological data. Use for 绘图美化 SkillInstall · skills CLI | 3,562 | MIT | ||
| li-human Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detectio SkillInstall · skills CLI | 3,545 | MIT | ||
| skill-prompt-convert 在 Skill（SKILL.md）与 Prompt（聊天框指令）两种格式之间相互转换。支持 Skill→Prompt 与 Prompt→Skill 双向转换，保持核心信息零丢失。当用户提到 Skill 转 Prompt、Prompt 转 Skill、格式互转、SKILL.md 转换时使用。 SkillInstall · skills CLI | 3,174 | Apache-2.0 | ||
| critique Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them. SkillInstall · skills CLI | 3,171 | MIT | ||
| gate Run the one-command quality gate and report the real N/N result. Use before claiming any build/review is done. SkillInstall · skills CLI | 3,171 | MIT | ||
| governance Govern how the design system evolves (SemVer for tokens/components, the contribution workflow, deprecation policy, and change communication). Use when SkillInstall · skills CLI | 3,171 | MIT | ||
| grill-me Interrogate the brief before a line is built. Ask only the questions whose answers change the work, and put every unasked decision on the record as a SkillInstall · skills CLI | 3,171 | MIT | ||
| ship Pre-release gate. Run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before taggi SkillInstall · skills CLI | 3,171 | MIT | ||
| ad-creative-builder Use when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| ad-test-designer Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and p SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| attribution-reconciler Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a stan SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| audience-segment-builder Use when the user asks to "build audience segments from my customer list", "make value-based / lookalike seed lists", "set up exclusion / suppression SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| bid-strategy-planner Use when the user asks to "pick a bid strategy", "set a tCPA/tROAS target", or "plan the learning-phase entry"; produces a bid-strategy choice (tCPA / SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| budget-pacing-monitor Use when the user asks to "check pacing", "am I over/under-spending", "is this campaign on track to hit budget", or "why did spend spike/stall mid-fli SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| campaign-architect Use when the user asks to "plan my paid account structure", "pick Search vs PMax", "lay out ad groups / asset groups", or "audit paid-vs-organic canni SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| cold-outbound-sequencer Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make m SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| conversion-value-mapper Use when the user asks to "set up conversion values so tROAS optimizes profit not orders", "map margin onto my purchase value", "build value rules for SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| dynamic-content-personalizer Use when the user asks to "personalize the email", "add merge tags / dynamic content", "set up conditional blocks per segment", or "make first-name an SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| email-creative-builder Use when the user asks to "write the email", "draft subject lines", or "build email creative"; produces the pre-click unit — subject-line variants + p SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| email-quality-auditor Use when the user asks to "audit an email program" or "is this campaign safe to send"; runs a typed 20-item SEND profile with authentication, consent, SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| email-render-builder Use when the user asks to "build the email HTML", "make this email responsive", "fix dark-mode rendering", or "QA the email across clients"; produces SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| email-sequence-designer Use when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| fatigue-frequency-manager Use when the user asks to "is my ad fatiguing", "why is CTR dropping at scale", or "should I rotate creative / widen the audience"; reads frequency, C SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| inbox-placement-monitor Use when the user asks to "track where my emails are actually landing after I send", "read my seed-list inbox vs spam vs promotions results", "trend m SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| landing-experience-checker Use when the user asks to "pre-launch check the landing page", "run a Quality-Score preflight", or "verify ad-to-page message match before launch"; pr SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| newsletter-monetization-planner Use when the user asks to "monetize my newsletter", "build a sponsorship rate card", or "model paid-subscription revenue"; produces a revenue model (p SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| paid-measurement-loop Use when the user asks to "read back" a paid campaign change, "did this ad change work", or "compare ROAS/CPA before and after"; reads ROAS/CPA agains SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| placement-exclusion-manager Use when the user asks to "build my brand-safety exclusion lists", "set placement / topic / content exclusions before launch", "add network and audien SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| preference-frequency-manager Use when the user asks to "build a preference center", "set up a frequency opt-down ladder", "give people a step-down instead of unsubscribe", or "des SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| product-feed-optimizer Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax ass SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| search-term-miner Use when the user asks to "mine my search terms", "find new keywords from converting queries", "build a negative-keyword list", or "cut wasted paid sp SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| send-experiment-designer Use when the user asks to "design an email A/B test", "set up a multivariate subject/CTA test", "run a send-time test", "build a hold-out group", or " SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| subject-line-lab Use when the user asks to "generate subject line variants", "pre-score my subject lines", or "will this subject get truncated / trigger spam filters"; SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| llm-council Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesiz SkillInstall · skills CLI | 3,035 | — | ||
| context-engineering Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partiti SkillInstall · skills CLI | 2,955 | — | ||
| context-optimizer Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget. SkillInstall · skills CLI | 2,955 | — | ||
| cost-tracker Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits. SkillInstall · skills CLI | 2,955 | — | ||
| plan-interrogate Stress-test a plan by walking its decision tree one question at a time. Use when the user wants to pressure-test a design before implementation. SkillInstall · skills CLI | 2,955 | — | ||
| replay-learnings Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patter SkillInstall · skills CLI | 2,955 | — | ||
| thoroughness-scoring Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated op SkillInstall · skills CLI | 2,955 | — | ||
| cortex-eval Evaluate model performance — check for accuracy drops, data drift, and error patterns. Use when asked about "model accuracy dropped", "evaluate the mo SkillInstall · skills CLI | 2,919 | MIT | ||
| explaining-machine-learning-models Build this skill enables AI assistant to provide interpretability and explainability for machine learning models. it is triggered when the user reques SkillInstall · skills CLI | 2,919 | MIT | ||
| lens Analytics and BI engineer — dashboards, metrics design, reporting pipelines, and data storytelling. SkillInstall · skills CLI | 2,919 | MIT | ||
| lens-recon Analytics reconnaissance for takeover — find all analytics tools, inventory what's tracked and dashboarded, assess data freshness and metric definitio SkillInstall · skills CLI | 2,919 | MIT | ||
| lens-report Build a reporting pipeline — scheduled reports with SQL queries, delivery via Slack or email, threshold alerts, and historical comparison. Use when as SkillInstall · skills CLI | 2,919 | MIT | ||
| lumen Product analyst — metrics architecture, funnel analysis, A/B test design, retention, and growth measurement. SkillInstall · skills CLI | 2,919 | MIT | ||
| lumen-abtest A/B test design — produce an experiment spec with hypothesis, primary metric, MDE, sample size, run time, and decision rule. Also determines when NOT SkillInstall · skills CLI | 2,919 | MIT | ||
| lumen-funnel Use when asked to analyze a funnel, find where users drop off, diagnose low conversion or activation rates, design a metrics framework, set up OKRs, o SkillInstall · skills CLI | 2,919 | MIT | ||
| lumen-instrument Instrumentation plan — design event taxonomy, property schema, and tracking plan for analytics tools. Use when asked to "what should we track", "instr SkillInstall · skills CLI | 2,919 | MIT | ||
| lumen-metrics Metrics architecture — produce a complete metrics plan given a product description. North Star, input metrics tree, instrumentation spec, action trigg SkillInstall · skills CLI | 2,919 | MIT | ||
| lumen-recon Analytics reconnaissance — scan existing event tracking, metric definitions, dashboards, and analytics configuration to understand what is currently b SkillInstall · skills CLI | 2,919 | MIT | ||
| pave Platform engineer — developer experience, golden paths, service catalogs, and local dev environments. SkillInstall · skills CLI | 2,919 | MIT | ||
| pave-audit Audit developer experience — measure onboarding time, build speed, deployment friction, and developer satisfaction. Use when asked to "DX audit", "dev SkillInstall · skills CLI | 2,919 | MIT | ||
| pave-catalog Build a service catalog — schema, starter entries, and governance model. Produces what information to capture per service, how it's maintained, and wh SkillInstall · skills CLI | 2,919 | MIT | ||
| pave-contribute Contribute a session learning back to the upstream tonone repo. Scans the conversation, extracts the single most reusable insight, asks one question, SkillInstall · skills CLI | 2,919 | MIT | ||
| pave-env Set up local development environments — devcontainers, Docker Compose, one-command setup, dev/prod parity. Use when asked to "set up dev environment", SkillInstall · skills CLI | 2,919 | MIT | ||
| pave-golden Define a golden path — the opinionated, supported way to do a common developer task (create a new service, set up an environment, deploy a feature). P SkillInstall · skills CLI | 2,919 | MIT | ||
| pave-recon Platform reconnaissance — inventory all developer tooling, environments, build systems, and developer workflows for project takeover. Use when asked t SkillInstall · skills CLI | 2,919 | MIT | ||
| pitch Product marketer — positioning, messaging, value prop, GTM strategy, and launch copy. SkillInstall · skills CLI | 2,919 | MIT | ||
| prism Frontend engineer — UI components, dashboards, design system implementation, and frontend audits. SkillInstall · skills CLI | 2,919 | MIT | ||
| prism-audit Frontend audit — bundle size, dependencies, accessibility, performance, component quality. Use when asked for "frontend review", "performance audit", SkillInstall · skills CLI | 2,919 | MIT | ||
| prism-chart Use when asked to implement a chart, select a visualization type, or build a data display component. Examples: "implement chart for time series", "bes SkillInstall · skills CLI | 2,919 | MIT | ||
| prism-component Implement a reusable, accessible, typed component from a design spec. Use when asked to "create a component", "build a widget", "implement this design SkillInstall · skills CLI | 2,919 | MIT | ||
| prism-dashboard Build an internal dashboard with data tables, filters, detail views, and CRUD. Use when asked to build an "admin panel", "internal dashboard", "back o SkillInstall · skills CLI | 2,919 | MIT | ||
| prism-recon Frontend reconnaissance — map the component tree, routing, state management, build config, and assess quality. Use when asked to "understand this fron SkillInstall · skills CLI | 2,919 | MIT | ||
| prism-stack Use when asked for framework-specific best practices, implementation guidelines for React/Vue/Svelte/Next.js, or stack-specific patterns. Examples: "R SkillInstall · skills CLI | 2,919 | MIT | ||
| prism-ui Implement a complete UI screen or feature from a Form visual spec. Use when asked to "build a page", "implement this screen", "build the frontend for SkillInstall · skills CLI | 2,919 | MIT | ||
| validating-ai-ethics-and-fairness Validate AI/ML models and datasets for bias, fairness, and ethical concerns. Use when auditing AI systems for ethical compliance, fairness assessment, SkillInstall · skills CLI | 2,919 | MIT | ||
| prompt-engineering Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design SkillInstall · skills CLI | 2,838 | Apache-2.0 | ||
| blog-flow FLOW framework integration for bloggers. Evidence-led content workflow using the Find, Optimize, Win loop with stage-specific AI prompts from the FLOW SkillInstall · skills CLI | 2,748 | MIT | ||
| blog-persona Create and manage writing personas with NNGroup 4-dimension tone framework (Funny-Serious, Formal-Casual, Respectful-Irreverent, Enthusiastic-Matter-o SkillInstall · skills CLI | 2,748 | MIT | ||
| blog-style Measure writing-style statistics (sentence length, vocabulary, transitions, phrasing) from 5 to 10 posts you or your client wrote, and produce a voice SkillInstall · skills CLI | 2,748 | MIT | ||
| Verification Before Completion Run verification commands and confirm output before claiming success SkillInstall · skills CLI | 2,244 | — | ||
| agent-anti-false-completion \"用于减少 AI Agent\"没做却说做了\"\"没验证却说完成了\"等假完成行为的可靠性技能。通过任务约束、结果校验和执行规范，帮助 Agent 在复杂任务中保持真实执行、明确验证与可信交付。适用于代码、调试、研究、写作、规划、运维、API 集成、数据分析、部署等所有任务类型。\ SkillInstall · skills CLI | 2,192 | MIT | ||
| ai-decision-authority Use before letting AI or an agent act on a marketing or GTM task without human review, or when writing an AI review policy. Places each workflow in AI SkillInstall · skills CLI | 2,192 | MIT | ||
| ai-drama-prompt-factory AI短剧提示词工厂 - 端到端将小说/故事创意转化为结构化提示词包（角色立绘+场景+道具+分镜图片+视频+音频）的完整流水线。一个入口启动全流程，内部自动按阶段推进：策划→设计→剧本→诊断→提示词组装→API JSON输出。支持小说改编和原创短剧两条路径。触发词：AI短剧、短剧制作、小说转短剧、短剧 SkillInstall · skills CLI | 2,192 | MIT | ||
| ai-learning-planner-cn AI学习计划生成器 v2.1 | AI Learning Planner. 支持个性化路径、进度跟踪、资源推荐、AI导师、学习报告、团队学习。触发词：学习、计划、课程。 SkillInstall · skills CLI | 2,192 | MIT | ||
| ai-prompt-generator 专业 AI 提示词生成工具，帮助用户创建高效、精准的 AI 提示词。内置多种框架和模板，让 AI 输出质量提升 10 倍。 SkillInstall · skills CLI | 2,192 | MIT | ||
| andara-self-improvement Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User correc SkillInstall · skills CLI | 2,192 | MIT | ||
| self-improvement-abc Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User correc SkillInstall · skills CLI | 2,192 | MIT | ||
| research-observability Add file-based observability, tracing, and run analysis to LLM/agent experiments — per-turn transcripts, tool calls and results, reasoning traces, tok SkillInstall · skills CLI | 2,125 | MIT | ||
| llm-application-dev-prompt-optimize Evaluate and improve LLM prompts using examples, structured instructions, and measured comparisons. Use when refining prompt reliability, output quali SkillInstall · skills CLI | 2,009 | MIT | ||
| prompt-engineer Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional SkillInstall · skills CLI | 2,009 | MIT | ||
| prompt-engineering-patterns Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts SkillInstall · skills CLI | 2,009 | MIT | ||
| perf-analyzer Use when synthesizing perf findings into evidence-backed recommendations and decisions. SkillInstall · skills CLI | 1,994 | — | ||
| perf-baseline-manager Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version. SkillInstall · skills CLI | 1,994 | — | ||
| perf-benchmarker Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only f SkillInstall · skills CLI | 1,994 | — | ||
| perf-code-paths Use when mapping code paths, entrypoints, and likely hot files before profiling. SkillInstall · skills CLI | 1,994 | — | ||
| perf-investigation-logger Use when appending structured perf investigation notes and evidence. SkillInstall · skills CLI | 1,994 | — | ||
| perf-profiler Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence. SkillInstall · skills CLI | 1,994 | — | ||
| perf-theory-gatherer Use when generating performance hypotheses backed by git history and code evidence. SkillInstall · skills CLI | 1,994 | — | ||
| perf-theory-tester Use when running controlled perf experiments to validate hypotheses. SkillInstall · skills CLI | 1,994 | — | ||
| debug-like-expert Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous SkillInstall · skills CLI | 1,989 | MIT | ||
| Microsoft Learn MCP Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs. MCP serverVerified domain · microsoft.comRemote● LiveFree to try | 1,986 | CC-BY-4.0 | ||
| skill-optimizer Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, redu SkillInstall · skills CLI | 1,971 | MIT | ||
| mex-statechart Explain complicated existing behavior using checked state diagrams. Use when asked for a state diagram, to diagram the previous explanation, show a bu SkillInstall · skills CLI | 1,796 | MIT | ||
| thinking-bounded-rationality Use when search or investigation could run forever. Set an explicit good-enough threshold first, then stop at the first option that clears it. SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-circle-of-competence Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate. SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-cynefin When the right response mode is unclear, classify the cause-effect domain first; decompose disorder. SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-effectuation Under genuine uncertainty with no reliable forecast, inventory means, cap downside at affordable loss, act for commitments, and let goals emerge from SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-first-principles When a constraint is treated as fixed, separate physics from convention, keep only independently supported primitives, and rebuild the simplest soluti SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-five-whys-plus When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a c SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-jobs-to-be-done Deciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-kepner-tregoe Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence com SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-lindy-effect Use when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then check domain drift before favoring the SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-map-territory When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let te SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-margin-of-safety When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the opt SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-model-combination When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conf SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-model-router When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary). SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-ooda Use under time pressure when the situation is still changing and you must act before certainty — cycle Observe→Orient→Decide→Act on ~70% confidence, t SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-opportunity-cost Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alter SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-pre-mortem Before committing to a plan or launch, assume it already failed and reason backward through concrete causes — convert failure paths into mitigations, SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-probabilistic Use when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeas SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-reversibility Before heavy deliberation, classify the decision as cheap or costly to undo; decide two-way doors fast and stage one-way doors to preserve options. SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-scientific-method When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptiv SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-second-order When a change has effects past the immediate fix—incentives, scale, feedback—trace consequence chains with timing and probability before committing. SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-socratic When a request is vague, assumption-laden, or "obvious," ask the few load-bearing questions that expose hidden requirements before building or committ SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-steel-manning Before rejecting a proposal or reflexively agreeing, build the strongest faithful opposing case, state agreement conditions, then update or reaffirm. SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-systems When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank l SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-theory-of-constraints When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-cons SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-thought-experiment When a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, fix conditions, trace the mechanistic cha SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-triz When two design requirements seem mutually exclusive, name the contradiction, separate conflicting states, then invent a concrete no-compromise resolu SkillInstall · skills CLI | 1,738 | MIT | ||
| thinking-via-negativa Use when the reflex is to add a feature, layer, or process. Prefer removing harmful or nonessential elements first, with an irreversibility guard befo SkillInstall · skills CLI | 1,738 | MIT | ||
| brainstorming Explore user intent, requirements, and design options through collaborative dialogue before implementation. Use before building new features, componen SkillInstall · skills CLI | 1,680 | MIT | ||
| grill-me 针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。 SkillInstall · skills CLI | 1,680 | MIT | ||
| gate-check Find the decisions in a pipeline that do not need the expensive model and propose the gate for each: a rule, a classic classifier, or a small model, w SkillInstall · skills CLI | 1,573 | MIT | ||
| goal-test Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a SkillInstall · skills CLI | 1,573 | MIT | ||
| finetuning This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fi SkillInstall · skills CLI | 1,502 | Apache-2.0 | ||
| first-principles-review Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate own SkillInstall · skills CLI | 1,442 | MIT | ||
| goal-framing Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task bound SkillInstall · skills CLI | 1,442 | MIT | ||
| nopua The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, su SkillInstall · skills CLI | 1,402 | MIT | ||
| nopua-lite NoPUA Lite — core wisdom in ~1.5k tokens. Drives AI with trust and inner motivation instead of fear. Same Daoist philosophy, minimal footprint. For pe SkillInstall · skills CLI | 1,402 | MIT | ||
| nopua-zh The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, su SkillInstall · skills CLI | 1,402 | MIT | ||
| hung-yi-lee Explain machine learning, deep learning, generative AI, LLMs, AI agents, and speech modeling in a Hung-Yi Lee-inspired teaching style. Use this skill SkillInstall · skills CLI | 1,321 | — | ||
| ts-paper Generate a complete, publication-format journal/conference paper (LaTeX → compiled PDF) from whatever the user drops — a one-line idea, a proposal, or SkillInstall · skills CLI | 1,201 | MIT | ||
| ts-paper-cite Stage 2 of the ts-paper suite. Build a complete, REAL refs.bib for a Traitement du Signal paper — using the user's provided references first and Claud SkillInstall · skills CLI | 1,201 | MIT | ||
| ts-paper-data DATA-AWARE mode for the ts-paper suite. Activated by the orchestrator's router ONLY when the input ships REAL measured results (results_mode == "data_ SkillInstall · skills CLI | 1,201 | MIT | ||
| ts-paper-experiment Repair an AI-generated scientific paper draft by diagnosing research logic, completing feasible experiments, rewriting the experiment section, and upd SkillInstall · skills CLI | 1,201 | MIT | ||
| ts-paper-figure Stage 6 of the ts-paper suite. Fill a Traitement du Signal paper's figure placeholders with real diagrams. Claude DESIGNS a concrete, rich figure and SkillInstall · skills CLI | 1,201 | MIT | ||
| ts-paper-latex Stage 7 (final assemble + compile) of the ts-paper suite. Assemble drafted LaTeX section bodies + refs.bib + blueprint into a compilable paper in the SkillInstall · skills CLI | 1,201 | MIT | ||
| ts-paper-plan Stage 1 of the ts-paper suite. Turn a research proposal into a single structured blueprint.json (title, ≤6 keywords, exactly 3 contributions, notation SkillInstall · skills CLI | 1,201 | MIT | ||
| ts-paper-refine Stage 4 of the ts-paper suite. One holistic pass that right-sizes each drafted section toward Traitement du Signal JOURNAL length (not conference page SkillInstall · skills CLI | 1,201 | MIT | ||
| ts-paper-review Adversarial peer-review HARDENING pass for a ts-paper draft — the thing a forward-only drafter/refiner can't do: argue the other side of the paper's c SkillInstall · skills CLI | 1,201 | MIT | ||
| ts-paper-write Stage 3 of the ts-paper suite. Draft every section of a Traitement du Signal paper as LaTeX body files (sections/<id>.tex + abstract.tex) from the blu SkillInstall · skills CLI | 1,201 | MIT | ||
| verification-agent Verify claims, quotations, citations and references against live primary sources, and produce a reproducible audit record instead of an assertion. Use SkillInstall · skills CLI | 1,156 | MIT | ||
| create-custom-grader Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation. SkillInstall · skills CLI | 1,141 | Apache-2.0 | ||
| skillevaluator Run and interpret SkillEvaluator for agent skills. Use for any skill benchmark or eval - validating or scoring a SKILL.md, writing evals.json test cas SkillInstall · skills CLI | 1,141 | Apache-2.0 | ||
| 02-ref-hallucination-arena Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination r SkillInstall · skills CLI | 1,100 | Apache-2.0 | ||
| 03-ref-hallucination-arena Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination r SkillInstall · skills CLI | 1,100 | Apache-2.0 | ||
| align-human Use when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, det SkillInstall · skills CLI | 1,100 | Apache-2.0 | ||
| bootstrap Use when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I ne SkillInstall · skills CLI | 1,100 | Apache-2.0 |
Filters apply to the top 400 of 1,660 tools by stars. Full list for agents: ai-reasoning.json