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
1,0571,104 · page 23 / 104
bmorphism-starsbmorphism's GitHub stars (2155 repos) and created repos - a curated index of applied category theory, MCP servers, and xenomodern…majiayu000boltzStructure prediction using Boltz-1/Boltz-2, an open biomolecular structure predictor. Use this skill when: (1) Predicting protein…majiayu000book-biographyBibliographic research agent for analyzing books and manuscripts. Builds comprehensive "book biographies" showing production…majiayu000cognitive-architecturesPatterns from SOAR, ACT-R, and LIDA for advanced agent cognitive cyclesmajiayu000self-improvementEvolutionary mechanisms for the agent to rewrite its own prompts (Neuroplasticity).majiayu000episodic-consolidationConsolidate short-term events into long-term 'Semantic' memory.majiayu000breadth-chart-analystThis skill should be used when analyzing market breadth charts, specifically the S&P 500 Breadth Index (200-Day MA based) and the…majiayu000breaking-hidden-assumptionsUse when breaking hidden assumptions is required during creativity work, especially when the result must be traceable…casioreview20-glitchbrugesGeophysical equations and rock physics calculations for seismic analysis. Use when Claude needs to: (1) Calculate AVO responses…majiayu000bspBSP geometry skill for Unreal brushes and CSG.a5c-aiwritesbug-hunt-swarmParallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures.…sickn33build-agentBuilds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration. Use when creating a…majiayu000building-agent-toolsGuide for creating effective tools for AI agents. Use when building MCP tools, agent APIs, or any tool interface that agents will…majiayu000building-agentsExpert at creating and modifying Claude Code agents (subagents). Auto-invokes when the user wants to create, update, modify…majiayu000writesbuilding-agents-constructionStep-by-step guide for building goal-driven agents. Creates package structure, defines goals, adds nodes, connects edges, and…majiayu000building-ai-agent-on-cloudflareBuilds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool…majiayu000building-evidence-backed-personasUse when building evidence backed personas is required during ux work, especially when the result must be traceable…casioreview20-glitchbuilding-langgraph-agentsLangGraph development for stateful multi-agent applications, cyclic workflows, conditional routing, human-in-the-loop patterns…majiayu000building-neural-networksExecute this skill allows AI assistant to construct and configure neural network architectures using the neural-network-builder…majiayu000writesbuilding-rag-systemsBuild production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document…majiayu000building-rag-systemsBuild production RAG systems with LangChain orchestration and Qdrant vector store. Covers 8 RAG architectures (Simple, HyDE…majiayu000building-with-agent-memoryBuild persistent memory systems for AI agents using Mem0, claude-mem, or custom implementations. Use when adding conversation…majiayu000bulk-rna-seq-differential-expression-with-omicverseGuide Claude through omicverse's bulk RNA-seq DEG pipeline, from gene ID mapping and DESeq2 normalization to statistical testing…FreedomIntelligencebulk-rna-seq-deseq2-analysis-with-omicverseWalk Claude through PyDESeq2-based differential expression, including ID mapping, DE testing, fold-change thresholding, and…FreedomIntelligencestring-protein-interaction-analysis-with-omicverseHelp Claude query STRING for protein interactions, build PPI graphs with pyPPI, and render styled network figures for bulk gene…FreedomIntelligencebulk-wgcna-analysis-with-omicverseAssist Claude in running PyWGCNA through omicverse—preprocessing expression matrices, constructing co-expression modules…FreedomIntelligencecache-cost-trackingLLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or…majiayu000Calibration Tools SkillSensor and robot calibration using specialized robotics calibration toolsa5c-aiwritescatalysis-electrochemThis skill group covers computational catalysis and electrochemistry workflows corresponding to VASPKIT menu 05 (tasks 501-509).…majiayu000causal-tracingCausal mediation analysis to identify which model components mediate specific behaviors. Use when investigating how information…majiayu000caveman-statsShow real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI…JuliusBrusseecaveman-statsShow real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI…stevesoluncc-configuring-mcpUse when optimizing MCP token usage, understanding Tool Search thresholds, or deciding MCP vs skills for token efficiency. For…majiayu000cc-cost-engineeringAI Agent 成本工程 — 基於 Claude Code 的成本追蹤、prompt cache 最佳化、token 預算控制逆向分析。Use when: 優化 token 消耗、設計成本控制機制、分析 cache 效率、選擇模型配置。majiayu000cc-harness-patternsHarness Engineering 設計模式 — 基於 Claude Code 原始碼逆向分析的 12 條可遷移原則。Use when: 設計 agent 系統架構、實作 tool orchestration、設計 context 管理策略、建構…majiayu000cc-prompt-craftSystem Prompt 工程 — 基於 Claude Code 914 行系統提示詞的逆向分析。Use when: 撰寫 system prompt、設計 prompt 動態組裝、最佳化 prompt cache 效率、撰寫安全指令。majiayu000cc-tasksReference for Claude Code Tasks — tool parameters, status lifecycle, dependency management, and conventionsmajiayu000cellagentdescription: LLM-driven multi-agent framework for automated single-cell analysis.'majiayu000ceo-speech-agentCEO statement tone shift analyzer for /ceo-analysis page. Analyzes CEO quotes from SEC filings, earnings calls to detect tone…majiayu000certifying-platform-adaptersUse when certifying platform adapters is required during meta work, especially when the result must be traceable, independently…casioreview20-glitchcfn-agent-toolingAgent development tools - generation and validation. Use when creating new agent templates from scaffolding, or validating and…majiayu000cfn-expert-updateUpdate CFN system expert agent with relevant git commits and project changesmajiayu000change-managementFramework for rolling out organizational changes without chaos. Covers the ADKAR model adapted for startups, communication…alirezarezvanicharacter-physicsCharacter controller skill for movement physics and platformer mechanics.a5c-aiwriteschatQuick single voice exchange. Speaks a prompt, captures one response via TTS. No persistent session needed.majiayu000chat-formatFormat prompts for different LLM providers with chat templates and HNSW-powered context retrievalmajiayu000writespersonal-context-agentExtract personal facts about a user from AI chat transcripts and structure into themed markdown files. Use when (1) Processing…majiayu000checkpoint-promotionGate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training…wshobson
← Prev23 / 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