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
1,2011,248 · page 26 / 104
competitive-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…majiayu000compiling-context-packUse when compiling context pack is required during kernel work, especially when the result must be traceable, independently…casioreview20-glitchcompress-promptCompresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action…majiayu000compressing-project-artifactsUse when compressing project artifacts is required during meta work, especially when the result must be traceable, independently…casioreview20-glitchcomputer-use-agentsBuild AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text.…majiayu000Computer Vision SkillSpecialized skill for robot vision including feature detection, tracking, and camera calibrationa5c-aiwritesComputer Vision SkillSpecialized skill for robot vision including feature detection, tracking, and camera calibrationmajiayu000writesConcurrency PrimitivesExpert skill for implementing language-level concurrency support including threads, channels, and synchronizationa5c-aiwritescondensed-anima-qcCondensed ANIMA on quantum-classical and classical-quantum networks. All skill compositions materialized as s-expressions across…majiayu000configuring-block-policyGuide users through creating and managing .satk/block-policy.json for controlling which blocks the agent can use, which are…matlabconfusion-matrix-generatorInspect classifier errors with confusion matrices after predictions already exist. Use for per-class error analysis, threshold…majiayu000writesconsciousness-councilRun a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the…majiayu000consciousness-councilRun a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the…K-Dense-AIwritesconsciousness-councilRun a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the…LeonChaoXwritesconsensus-mechanismsMulti-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation…a5c-aiwritesconsole-performanceConsole optimization skill for memory constraints and TCRs.a5c-aiwritesconstitutional-ai-alignmentA framework for aligning AI agents to be helpful, harmless, and honest using a principles-based critique loop. Use this when you…majiayu000constitutional-ai-promptsConstitutional AI and safety guardrail prompts for aligned LLM behaviora5c-aiwritesconstructConstruct 3 visual programming skill for rapid prototyping and 2D game development.a5c-aiwritesconstructing-idea-genomesUse when constructing idea genomes is required during creativity work, especially when the result must be traceable…casioreview20-glitchconsultationClaude(スマホ・PC)への相談スキル。実装中に判断が必要になった時、技術選定が必要な時、設計相談が必要な時に使用。majiayu000hosted-agentsThis skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed…majiayu000context-finderAuto-spawn context-finder agent for search tasks. Use when user says "find", "search", "where is", "look for", "trace", "what…majiayu000context-gathererPhase 0.1 — Automatic codebase scan before PRD generation. Extracts key terms from the user prompt, searches the codebase for…majiayu000writescontextual-retrievalAnthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid…majiayu000continual-learningGuide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up…majiayu000continuity-kernelOpenClaw continuity kernel for fail-open llm_input injection, deterministic runtime contracts, and shadow-mode eval receipts.majiayu000continuous-learningPattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.a5c-aiwritescontrolling-ai-costUse when controlling ai cost is required during ai-products product work, especially when the result must be traceable…casioreview20-glitchcontrolling-code-complexityUse when controlling code complexity is required during implementation work, especially when the result must be traceable…casioreview20-glitchconvex-agentBuild AI agents with persistent threads, tool calling, and streaming on Convex. Use when implementing chat interfaces, AI…majiayu000Convex Agents ContextCustomizes what information the LLM receives for each generation. Use this to control message history, implement RAG context…majiayu000Convex Agents FilesHandles file uploads, image attachments, and media processing in agent conversations. Use this when agents analyze images…majiayu000Convex Agents FundamentalsSets up and configures Convex agents for chat-based AI interactions. Use this when initializing agent instances, creating…majiayu000Convex Agents MessagesSends, saves, retrieves, and manages messages within agent conversations. Use this when handling user messages, displaying…majiayu000Convex Agents StreamingStreams agent responses in real-time to clients without blocking. Use this for responsive UIs, long-running generations, and…majiayu000convo-analysisAnalyze conversation flows for behavioral patterns. Use this skill when debugging AI compliance issues, reviewing human request…majiayu000convoy-managementCreate, track, and land convoys of related beads as primary work orders in the Gas Town multi-agent orchestration framework.a5c-aiwritescopilotkitCopilotKit integration patterns for providers, runtime wiring, `useCoAgent`, `useCopilotAction`, `useLangGraphInterrupt`, shared…majiayu000coreProvide visibility into the "Black Box" of agent execution by tracking cost (tokens) and efficiency (time/loops).majiayu000coremlIntegrate and optimize Core ML models in iOS apps for on-device machine learning inference. Covers model loading (.mlmodelc…majiayu000cortex-promptBuild a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval criteria. Use…jeremylongshorewritescost-aware-llm-pipelineUse when building an LLM-powered app that needs cost control via model routing, budget tracking, retry, and prompt caching.majiayu000cost-latency-optimizerReduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provides cost…majiayu000create-agentClaude Code 커스텀 에이전트를 만들고 실행할 때 사용하는 스킬. 사용자가 "에이전트 만들어", "Claude agent 생성", "--agents 설정"을 요청하면 활성화됩니다.majiayu000writescreate-agentCreate and validate domain agents. USE WHEN create agent, new agent, agent structure, validate agent, check agent, domain agent.…majiayu000create-agentCreates a new LearningAgent with directory structure, core-knowledge.md, and Claude Code agent file. Guides the user through…majiayu000
← Prev26 / 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