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
2,0172,064 · page 43 / 104
破产文书生成基于《破产程序法律文书样式》中的165份文书模板(106份法院文书+59份管理人文书),按需生成各类破产程序文书。本Skill作为破产文书的统一生成工具,供其他破产Skill调用。当用户发送客户编号并提及"破产文书"/"生成XX通知"/"生成XX报告"/"生成…pa1nrui1财产调查与管理R1(管理人)专属Skill,覆盖破产程序中的财产全面调查、可撤销/无效行为追回、财产管理方案编制。当用户发送客户编号并提及"财产调查"、"财产清查"、"可撤销行为"、"追回财产"、"财产管理方案"等指令时触发使用。pa1nrui1债权申报与审查破产债权管理全流程Skill,覆盖债权申报、审查、编制债权表全流程。适用于管理人(R1)、债权人代理(R2)、债务人代理(R3)三种角色。当用户发送客户编号并提及"债权申报"、"债权审查"、"编制债权表"、"申报债权"等指令时触发使用。pa1nrui1packaging-developer-binariesUse when packaging developer binaries is required during developer-tools product work, especially when the result must be…casioreview20-glitchpackaging-release-evidenceUse when packaging release evidence is required during operations work, especially when the result must be traceable…casioreview20-glitchpacket-captureExpert skill for packet capture and analysis using libpcap/Wireshark. Execute tcpdump/tshark commands, write BPF filter…a5c-aiwritesParser GeneratorExpert skill for parser generation and implementation using LL, LR, LALR, PEG, and Pratt parsing techniquesa5c-aiwritesparticle-systemsParticle system skill for emitters and GPU particles.a5c-aiwritespatrol-monitoringContinuous monitoring using Deacon/Witness patterns for agent health checks, stuck detection, and automated recovery.a5c-aiwritespattern-matchingExpert skill for implementing pattern matching including exhaustiveness checking, decision tree compilation, and efficient match…a5c-aiwritespave-catalogBuild a service catalog — schema, starter entries, and governance model. Produces what information to capture per service, how…jeremylongshorewritespbr-renderingPhysically-based rendering skill for BRDF models and material workflows.a5c-aiwritespendView latest reply from AI provider (gemini/codex/opencode/droid/claude).majiayu000pendView latest reply from AI provider (gemini/codex/opencode/droid/claude).majiayu000perfAnalyze Elixir/Phoenix performance — N+1 queries, assign bloat, ecto optimization, genserver bottlenecks. Use when slowness…oliver-kriskaperforcePerforce skill for game projects, streams, and shelving.a5c-aiwritesperformance-profilerProfile application performance including CPU, memory, and flame graph generationa5c-aiwritesperforming-regression-analysisBuild and diagnose regression models when the main question is regression itself. Use for model specification, coefficient…majiayu000writesperigon-agentPointers for Copilot/agents to apply Perigon conventionsmajiayu000perplexity-routingRouting guide for selecting the correct Perplexity tool. Reference before spawning any Perplexity agent.majiayu000persistent-memoryObservation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and…a5c-aiwritespersona-detectionIntelligent project persona identification using priority chain detection with LLM and heuristic fallbackmajiayu000petropyPetrophysical analysis and formation evaluation from well logs. Calculate porosity, water saturation, permeability, and…majiayu000phaserPhaser.js 2D game development skill for web games, arcade physics, and web deployment.a5c-aiwritesphi-ain-gauntletFull-corpus reasoning gauntlet. 12 cognitive tools run consecutively on all 105 framework skill files. Produces golden spiral…majiayu000phoenix-arize-setupArize Phoenix observability platform setup for LLM debugging and evaluationa5c-aiwritesphoenix-arize-setupArize Phoenix observability platform setup for LLM debugging and evaluationmajiayu000writesphoenix-evalsBuild and run evaluators for AI/LLM applications using Phoenix.majiayu000arize-phoenixOpen-source AI observability platform for tracing, evaluating, and improving LLM applications with OpenTelemetry integrationmajiayu000phoenix-tracingOpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating…majiayu000photonPhoton PUN/Fusion skill for rooms and real-time communication.a5c-aiwritesphx-perfAnalyze Elixir/Phoenix performance — N+1 queries, assign bloat, ecto optimization, genserver bottlenecks. Use when slowness…oliver-kriskaphx-recallRecall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done…oliver-kriskaphysician-feedback-agentEvaluate NGM products and services through the lens of synthesized longevity physician personas. Provides multi-perspective…majiayu000writesphysics-enginePhysics engine integration skill for rigid body dynamics and collision detection.a5c-aiwritespineconeImplements vector search with Pinecone for semantic similarity and RAG applications. Use when building embeddings-based search…majiayu000place-and-routeExpert skill for FPGA place and route optimization and physical implementationa5c-aiwritesplagiarism-checkerScans lyrics for phrases that may match existing songs using web search and LLM knowledge. Use before release to check for…majiayu000planning-agentPlanning agent that creates implementation plans and handoffs from conversation contextparcadeiplanning-enterprise-rolloutUse when planning enterprise rollout is required during enterprise product work, especially when the result must be traceable…casioreview20-glitchplanning-performance-budgetsUse when planning performance budgets is required during architecture work, especially when the result must be traceable…casioreview20-glitchplanning-product-experimentsUse when planning product experiments is required during product work, especially when the result must be traceable…casioreview20-glitchplaystation-sdkPlayStation SDK skill for trophies and submission.a5c-aiwritespm-agentPortfolio Manager and final arbiter. Synthesizes all agent votes, applies Constitution validation, resolves conflicts, and makes…majiayu000Point Cloud Processing SkillSpecialized skill for 3D point cloud processing and analysis using PCL and Open3Da5c-aiwritesPoint Cloud Processing SkillSpecialized skill for 3D point cloud processing and analysis using PCL and Open3Dmajiayu000writespolicyengine-github-agent-skillGuidance for working with the PolicyEngine GitHub agent botmajiayu000policyengine-microsimulationALWAYS USE THIS SKILL for PolicyEngine microsimulation, population-level analysis, winners/losers calculations. Use this skill's…majiayu000
← Prev43 / 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