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
865912 · page 19 / 104
agf-wiring-multi-llm-sdkUse when wiring up or switching between China-domestic LLM providers (DeepSeek, Doubao/Volc Ark, Qwen/DashScope, MiniMax).…majiayu000agile-v-coreFoundational values, directives, and context engineering rules for all Agile V agents. Load this skill first in any Agile V…majiayu000agnxi-search-skillAdvanced search using Agnxi AI for specialized knowledge retrieval.majiayu000ai-agent-builderBuild AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patternsmajiayu000ai-agents-architectExpert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent…majiayu000ai-agents-architectExpert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent…majiayu000ai-agents-architectExpert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent…majiayu000ai-agents-architectExpert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent…majiayu000ai-context-optimizerAIコーディング支援ツールのコンテキストファイル(CLAUDE.md等)を最適化するスキル。 以下の状況で使用: (1) ユーザーが「CLAUDE.mdを改善して」「コンテキストファイルを最適化して」と依頼した時 (2)…majiayu000ai-economist-skillA unified tool for central bank policy analysis and real-time GDP nowcasting for the US and Canada.majiayu000ai-engineerBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI…majiayu000ai-engineerProduction-grade AI engineering for LLM applications, RAG systems, and agent architectures. Use when building AI features…majiayu000ai-engineerBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI…majiayu000writesai-engineer-expertExpert-level AI implementation, deployment, LLM integration, and production AI systemsmajiayu000writesai-engineerBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI…majiayu000ai-engineerExpert in building comprehensive AI systems, integrating LLMs, RAG architectures, and autonomous agents into production…majiayu000ai-engineerBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI…majiayu000koan-ai-integrationChat endpoints, embeddings, RAG workflows, vector searchmajiayu000ai-llm-inferenceOperational patterns for LLM inference: latency budgeting, tail-latency control, caching, batching/scheduling…majiayu000ai-llm-skills-guideGuide for AI Agents and LLM development skills including RAG, multi-agent systems, prompt engineering, memory systems, and…majiayu000ai-ml-technologiesMaster AI, machine learning, LLMs, prompt engineering, and blockchain development. Use when building AI applications, working…majiayu000ai-mdConvert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens…majiayu000ai-ml-expertAI and ML expert including PyTorch, LangChain, LLM integration, and scientific computingmajiayu000ai-model-cloudbaseComplete guide for calling AI models with CloudBase - covers JS/Node SDK and WeChat Mini Program. Text generation, streaming, and…majiayu000ai-modelsLatest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicatemajiayu000ai-news-aggregator获取最新的AI行业新闻,进行智能总结和筛选,最多展示10条最重要的新闻资讯。当用户需要了解AI行业最新动态时使用此skill。majiayu000ai-output-validationEnsures all AI-generated output fields have proper validation. Auto-activates on "AI 輸出", "LLM", "Gemini", "GPT", "truncate"…majiayu000writesai-productEvery product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.…majiayu000ai-prompt-engineerAI engineering skill for prompt optimization, context inference, and intelligent command routing across different models and use…majiayu000writesai-prompt-engineeringOperational prompt engineering for production LLM apps: structured outputs (JSON/schema), deterministic extractors, RAG…majiayu000ai-promptUse when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiveness.majiayu000ai-ragComplete RAG and search engineering skill. Covers chunking strategies, hybrid retrieval (BM25 + vector), cross-encoder reranking…majiayu000ai-sdk-agentsExpert guidance for building AI agents with ToolLoopAgent (AI SDK v6+). Use when creating agents, configuring…majiayu000ai-sdkAnswer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like…majiayu000ai-setupConfigure AI model options - budget cloud models (save 80%+) and offline mode (use Dex without internet)majiayu000ai-specialist提供 AI 应用开发、MCP 服务器工程、提示词工程与智能体框架集成能力。当需要构建或优化基于大模型的功能、工作流或平台集成时使用。majiayu000ai-statusCheck your AI model configuration - see what's set up, current model, credits remainingmajiayu000ai-tuningOptimize AI assistant configurations for maximum effectiveness. USE THIS SKILL when user says "improve CLAUDE.md", "better…majiayu000writesaiUse when working with AI agent protocols, standards, and interoperability specifications. Covers MCP, A2A, ACP, Agent Skills…majiayu000aico-pm-competitor-analysisResearch and analyze competitors with STRUCTURED output: feature comparison matrix, strengths/weaknesses analysis, and actionable…majiayu000aim-best-practices-researcherResearch current best practices for any technology, pattern, or coding standard. Use when asking about best practices…majiayu000aim-parzival-bootstrapLoad Parzival cross-session memory from Qdrantmajiayu000writesaim-searchSearch memory system with advanced filtering and intent detectionmajiayu000writesaios-cerebrumAIOS Agent Operating System and Cerebrum SDK for building, deploying, and orchestrating AI agentsmajiayu000aitask-refresh-code-modelsResearch latest AI code agent models via web and update models_*.json configuration files.majiayu000aitask-refresh-code-modelsResearch latest AI code agent models via web and update models_*.json configuration files.majiayu000aitask-refresh-code-modelsResearch latest AI code agent models via web and update models_*.json configuration files.majiayu000deep-thinkerStructured reasoning for complex problems using Sequential Thinking MCP. Break down problems into stages, track thought…majiayu000
← Prev19 / 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