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
1,7771,824 · page 38 / 104
managing-pluginsCreates, packs, bundles, and manages Claude Code plugins with manifest generation, directory structure, marketplace…majiayu000managing-project-stateUse when managing project state is required during kernel work, especially when the result must be traceable, independently…casioreview20-glitchmanaging-slash-commandsCreates, analyzes, updates, and improves slash commands including YAML frontmatter, argument handling, and command authoring…majiayu000managing-software-dependenciesUse when managing software dependencies is required during implementation work, especially when the result must be traceable…casioreview20-glitchmanufacturer-agentWeb-augmented agent for creating manufacturer skills and comprehensive tests. Use when adding or improving support for a…majiayu000Manus AI Agent IntegrationUse this skill when delegating complex autonomous tasks to Manus AI - an AI agent that can browse the web, execute code, generate…majiayu000writesmapping-acceptance-contractsUse when mapping acceptance contracts is required during planning work, especially when the result must be traceable…casioreview20-glitchmapping-business-modelUse when mapping business model is required during product work, especially when the result must be traceable, independently…casioreview20-glitchmapping-existing-solutionsUse when mapping existing solutions is required during research work, especially when the result must be traceable, independently…casioreview20-glitchmapping-jobs-to-be-doneUse when mapping jobs to be done is required during research work, especially when the result must be traceable, independently…casioreview20-glitchmapping-user-journeysUse when mapping user journeys is required during ux work, especially when the result must be traceable, independently…casioreview20-glitchmarket-sizing-analysisThis skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate…majiayu000market-sizing-analysisThis skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate…majiayu000matchmakingMatchmaking skill for ELO/MMR and skill-based matching.a5c-aiwritesmath-and-combinatoricsReference patterns for mathematical and combinatorial problem-solving. Covers modular arithmetic, prime sieves, GCD/LCM, binomial…majiayu000mathematical-modelingReal-world problem formulation, mathematical abstraction, and applied mathematics for translating between practical problems and…majiayu000mathematical-theorem-proverImplement comprehensive mathematical theorem proving capabilities with SFT+GRPO training, MCP/A2A agent integration, and imatrix…majiayu000maya-integrationMaya to engine pipeline skill for FBX export and rigging workflows.a5c-aiwritesmcmc-sampling-stanGuide for performing Markov Chain Monte Carlo (MCMC) sampling using RStan or PyStan. This skill should be used when implementing…majiayu000mcp-app-verificationComprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text…a5c-aiwritesmcp-capability-declaratorGenerate MCP capability declarations from tool and resource inventory with proper versioning and feature flags.a5c-aiwritesmcp-create-declarative-agentSkill converted from mcp-create-declarative-agent.prompt.mdmajiayu000mcp-error-code-mapperMap application errors to MCP error codes with proper messages, error types, and recovery suggestions.a5c-aiwritesmcp-inspector-integrationSet up MCP Inspector for debugging and testing MCP servers with request logging, response inspection, and protocol validation.a5c-aiwritesmcp-tool-schema-generatorGenerate JSON Schema definitions for MCP tool input parameters. Creates well-documented, AI-consumable schemas with proper types…a5c-aiwritesmcp-transport-sse-setupConfigure HTTP/SSE transport for web-based MCP servers with proper endpoints, authentication, and CORS.a5c-aiwritesmcp-transport-websocket-setupConfigure WebSocket transport for bidirectional MCP communication with connection management and reconnection handling.a5c-aiwritesrun-benchmarkRun an MCP evaluation using mcpbr on SWE-bench or other datasets.majiayu000measuring-developer-experienceUse when measuring developer experience is required during developer-tools product work, especially when the result must be…casioreview20-glitchmeasuring-saas-activationUse when measuring saas activation is required during saas product work, especially when the result must be traceable…casioreview20-glitchmechanical-propertiesThis skill group covers calculations of mechanical properties of crystalline materials. Two main approaches are available:'majiayu000medcomInvoke MEDCOM for military medical advisory, ACGME interpretation, and domain expertise. Advisory-only agent that surfaces…majiayu000medical-research-literature-reader-proA medical-research-native literature reading skill for users with clinical, bioinformatics, translational, and basic experimental…majiayu000mem0-integrationMem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and…a5c-aiwritesmemlab-analysisExpert skill for JavaScript memory leak detection using Facebook MemLab. Configure MemLab scenarios, execute memory leak…a5c-aiwritesmemory-analysisEmbedded memory analysis, optimization, and leak detectiona5c-aiwritesmemory-curateUse this skill on a weekly cadence and at every change archive to keep the project's tiered memory (MEMORY.md index + per-topic…charliehzmmemory-documentaryGenerate evidence-based documentary reports by searching across all 4 memory systems (Claude-Mem, Forgetful, Serena, DeepWiki)…majiayu000memory-forensicsMaster memory forensics techniques including memory acquisition, process analysis, and artifact extraction using Volatility and…wshobsonmemory-leak-detectorDetect memory leaks in desktop applications through heap analysis and object trackinga5c-aiwritesmemorySwift 6.2 InlineArray and Span types for zero-overhead memory access, fixed-size collections, and safe pointer alternatives. Use…rshankrasmemory-safety-patternsCross-language patterns for memory-safe programming including RAII, ownership, smart pointers, and resource management.sickn33memory-summarizationConversation summarization for memory compression and context managementa5c-aiwritesmemory-systemsThis skill should be used when the user asks to "implement agent memory", "persist state across sessions", "build knowledge…majiayu000mental-model-libraryUse when a problem spans multiple disciplines or when single-domain thinking has produced stale analysis—applies Munger's…majiayu000merge-agentMerge Agent with exclusive write access to main branch. Performs final merge after all approvals. Use this skill ONLY for merging…majiayu000merge-queueProcess the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify…a5c-aiwritesmeta-analyst-agentAI self-improvement analyst. Tracks AI agent mistakes, analyzes failure patterns, and proposes system improvements. Implements…majiayu000
← Prev38 / 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