Agent skills

AI & Agents skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
4,965 found
1,1531,200 · page 25 / 104
cloudflare-workers-aiRun LLMs and AI models on Cloudflare's GPU network with Workers AI. Includes Llama 4, Gemma 3, Mistral 3.1, Flux images, BGE…majiayu000cloudflare-workers-aiRun LLMs and AI models on Cloudflare's global GPU network with Workers AI. Includes Llama, Flux image generation, BGE embeddings…majiayu000clustering-semantic-ideasUse when clustering semantic ideas is required during creativity work, especially when the result must be traceable…casioreview20-glitchcobuilder-heartbeatBehavioral specification for the CoBuilder Heartbeat teammate. Loaded as prompt when spawning the Haiku work-finder agent within…majiayu000writescodanna-codebase-intelligenceUse codanna MCP tools for semantic code search, call graphs, and impact analysis before grep/find.majiayu000code-explorerExplores codebases to find relevant files, trace execution paths, and map architecture with team communication capabilities for…majiayu000code-explorerExplores codebases to find relevant files, trace execution paths, and map architecture with team communication capabilities for…majiayu000code-importRead an existing repository's structure into the project cwd as a normalised snapshot the agent can analyse without re-walking…nexu-iocode-investigateDual-perspective code investigation. Claude explores independently, then Codex explores independently (no feeding), finally…majiayu000writescode-sizeEnforce complexity and size limits on Swift code with SwiftLint threshold rules — cyclomatic complexity, function/type/file…rshankraswritescode-synthesizerSynthesizes exploration findings into unified analysis with deep investigation capabilities and completeness evaluation…majiayu000code-synthesizerSynthesizes exploration findings into unified analysis with deep investigation capabilities (shell commands, git history…majiayu000open-knowledge-pack-codebase-wikiHow to work in a Codebase Wiki project (the `codebase-wiki` starter pack): an agent-authored, source-grounded wiki of the…inkeepsqlite-agent-contextDetect agent capabilities and manage context intelligentlymajiayu000codex-agent-collaborationDelegate coding tasks to Codex AI for implementation, analysis, and alternative solutions. Use when you need a second AI…majiayu000codex-agent作为项目经理操作 OpenAI Codex CLI 完全体。包含:知识库维护(自动跟踪 Codex 最新功能)、任务执行(提示词设计→执行→监控→质量检查→迭代→汇报)、配置管理(feature flags/模型/skills/MCP)。通过 tmux…majiayu000codex-askAsk OpenAI Codex questions about code to understand implementations, architecture, patterns, and debugging. Use when the user…majiayu000writescodexUse when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or…majiayu000codex-cliIntegrate OpenAI Codex CLI into Claude Code for AI collaboration, code generation, and automated development. Use when working…majiayu000codexCodex CLI を read-only sandbox で実行し、OpenAI 側のセカンドオピニオンを得る。majiayu000codexOpenAI Codex CLI(read-only sandbox)を汎用セカンドオピニオンとして実行する。Use when 設計相談、バグ調査、コードレビュー、文章校閲、セカンドオピニオンが必要な場面。キーワード: codex, codexに聞いて…majiayu000codexBridge to the OpenAI Codex CLI for high-reasoning tasks using gpt-5.3-codex.majiayu000codexExecute tasks using the OpenAI Codex CLI (GPT-5.2). This agent MUST run codex exec for every request - it delegates work to…majiayu000codex-law-governorGovern agent behavior through enforcement of the Codex Laws framework.majiayu000codexUse when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or…majiayu000codexRun OpenAI Codex CLI as a subagent for second opinions, code reviews, and questions. Use when you want a different AI model's…majiayu000coding-agentRun Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.majiayu000coding-agentDelegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or…majiayu000coding-agentRun Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.majiayu000coding-agentRun Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.majiayu000coding-agent-docsStay current with how OpenCode, OpenAI Codex, and Claude Code implement extensibility features (skills, slash commands…majiayu000coding-agentRun Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.majiayu000coding-agentDelegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or…majiayu000coding-agentRun Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.majiayu000coding-agentRun Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.majiayu000coding-agentRun Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.majiayu000coding-agentRun Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.majiayu000coding-prompt-optimizerコーディング用プロンプトを最適化・添削するスキル。 以下の状況で使用: (1) ユーザーが「このプロンプトを改善して」「プロンプトを最適化して」と依頼した時 (2) ユーザーが明示的に「/coding-prompt-optimizer」を実行した時 (3)…majiayu000coequalizersQuotient redundant skill paths via coequalizers, preserving GF(3) conservationmajiayu000comfyuiComfyUI node-based Stable Diffusion interface. GPU-accelerated image generation with custom node support and CivitAI model…majiayu000commitCreate git commits with user approval and no Claude attributionparcadeicomms-research-partner科研伙伴助手。当用户想要讨论论文、学习知识点、头脑风暴研究想法、搜索学术文献、探讨数学建模、或进行学术交流时使用此 skill。触发短语包括:"讨论论文"、"研究想法"、"头脑风暴"、"搜文献"、"帮我理解"、"一起研究"、"科研问题"等。majiayu000company-contact-finderFind decision-makers at a specific company using Apollo, Crustdata, Fiber, and PDL people search via Gooseworks MCP. Given a…gooseworks-aicompany-researchConduct comprehensive company research and due diligence. Analyze business model, competitive landscape, management, and market…majiayu000company-researchFull research pipeline with subagent coordination and memorymajiayu000competitive-analysisCompetitive intelligence with positioning analysis, battlecards, and market monitoring. Use for competitor tracking…majiayu000competitive-landscapeThis skill should be used when the user asks to "analyze competitors", "assess competitive landscape", "identify…majiayu000competitive-landscapeThis skill should be used when the user asks to "analyze competitors", "assess competitive landscape", "identify…majiayu000
← Prev25 / 104Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going