Agent skills

Other 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
21,420 found
2,4492,496 · page 52 / 447
ask-userPattern for effectively interacting with users to gather information or get decisions. Use when you need user input.majiayu000asking-notesQuery your Second Brain with keyword search. Use when asked to "ask my notes", "what do I know about", "query my knowledge"…majiayu000writesasking-questionsGuidance for asking clarifying questions when user requests are ambiguous, have multiple valid approaches, or require critical…majiayu000assembly-indexLee Cronin's Assembly Theory for molecular complexity measurement andmajiayu000risk-assessment設計・計画段階で自律的にリスクアセスメントを行うメタスキルです。 行動する前に自問自答し、浅い解決策を避け、根本的な問題を特定します。majiayu000assistant-behavior-rulesAI assistant behavior rules including response formatting and interaction patternsmajiayu000asunto-osakeyhtioAsunto-osakeyhtiön hallinto ja osakkaan asema Suomessa asunto-osakeyhtiölain (1599/2009) mukaan. Käytä tätä skilliä, kun käyttäjä…akunikkolaasuntokauppaAsunto-osakkeiden kauppa Suomessa asuntokauppalain (843/1994) mukaan. Käytä tätä skilliä, kun käyttäjä valmistelee tai tarkistaa…akunikkolaasymptotic-theoryM-estimation, influence functions, and semiparametric efficiency theory for causal inferencebrycewang-stanfordasync-python-patternsComprehensive guidance for implementing asynchronous Python applications using asyncio, concurrent programming patterns, and…sickn33async-python-patternsMaster Python asyncio, concurrent programming, and async/await patterns for high-performance applications. Use when building…wshobsonatcoder-clientInterface with AtCoder for Japanese competitive programming contestsa5c-aiwritesattributeEstablish cause-effect relationships between events or states. Use when analyzing root causes, mapping dependencies, tracing…majiayu000attribution-patchingGradient-based approximation to activation patching for scalable circuit analysis. Use when activation patching is too slow or…majiayu000authorship-credit-genUse when determining author order on research manuscripts, assigning CRediT contributor roles for transparency, documenting…majiayu000writesauto-anton-abyzov-specweaveStart autonomous execution with stop hook feedback loop. Works until all tasks complete or max iterations reached. Use when you…majiayu000auto-improvement(ePost) Use when reviewing session performance, analyzing improvement trends, or understanding the metrics-capture-detection…majiayu000auto-repair-estimate-decoderDecode an auto repair estimate — what each line actually is, which items are urgent vs upsell, and the questions that separate a…mohitagw15856autonomous-builderRun headless implementation from idea to artifact. Use when user says 'build in background', 'autonomous', 'headless', or wants…majiayu000writesautonomous-operationUse when starting any work session - establishes autonomous operation mode, overriding token limits and time pressure to work…majiayu000autonomous-operationUse when starting any work session - establishes autonomous operation mode, overriding token limits and time pressure to work…majiayu000writesautopilotFull autonomous execution from idea to working codemajiayu000autopilotFull autonomous execution from idea to working codemajiayu000autopilotFull autonomous execution from idea to working codemajiayu000autopilotFull autonomous execution from idea to working codemajiayu000autoresearchRun a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault…AgriciDanielax-scorecardSignal 정량 평가 — Scorecard JSON (100점 만점, 5개 차원)majiayu000axiom-foundation-models-diagUse when debugging Foundation Models issues — context exceeded, guardrail violations, slow generation, availability problems…majiayu000axiom-foundation-models-diagUse when debugging Foundation Models issues — context exceeded, guardrail violations, slow generation, availability problems…majiayu000axiom-foundation-models-refReference — Complete Foundation Models framework guide covering LanguageModelSession, @Generable, @Guide, Tool protocol…majiayu000axiom-foundation-models-refReference — Complete Foundation Models framework guide covering LanguageModelSession, @Generable, @Guide, Tool protocol…majiayu000axiom-ios-aiUse when implementing ANY Apple Intelligence or on-device AI feature. Covers Foundation Models, @Generable, LanguageModelSession…majiayu000axiom-ios-aiUse when implementing ANY Apple Intelligence or on-device AI feature. Covers Foundation Models, @Generable, LanguageModelSession…majiayu000axiom-ios-visionUse when implementing ANY computer vision feature - image analysis, object detection, pose detection, person segmentation…majiayu000axiom-visionsubject segmentation, VNGenerateForegroundInstanceMaskRequest, isolate object from hand, VisionKit subject lifting, image…majiayu000axiosPromise-based HTTP client for making requests from browser and Node.jsmajiayu000b2c-scapi-schemasUsing the b2c CLI to browse and retrieve SCAPI schema specificationsmajiayu000background-processingGenerates background processing infrastructure with BGTaskScheduler, background refresh, background downloads, and silent push…rshankraswritesbacklink-analyzerUse when analyzing backlink profiles, link authority, toxic links, link-building opportunities, or competitor link gaps. 外链分析/反向链接majiayu000backsolve-miner-vs-metal-ratio-with-fundamentals從網路自動抓取礦業公司財務報表與營運揭露(產量、成本、資本支出),回算「礦業股/金屬本體比率」的基本面解釋與區間門檻(如 1.2/1.7),並輸出可重現的估值拆解(成本因子 / 槓桿因子 / 倍數因子 / 稀釋因子)。majiayu000BackstopJS Visual TestingBackstopJS visual regression testing for self-hosted visual comparisona5c-aiwritesbacktest-expertExpert guidance for systematic backtesting of trading strategies on Indian markets (NSE/BSE). Use when developing strategies…majiayu000backtest-expertExpert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating…majiayu000backtest백테스트를 실행하고 전략 성과를 분석합니다. 날짜 범위와 초기 자본을 지정할 수 있습니다.majiayu000Backtesting AnalysisComprehensive guidance for interpreting backtest results and detecting overfitting (project)majiayu000backtesting-frameworksBuild robust, production-grade backtesting systems that avoid common pitfalls and produce reliable strategy performance estimates.sickn33backtesting-frameworksBuild robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and…wshobsonbaoyu-wechat-summarySummarizes WeChat group chat highlights into a structured digest using the local wx-cli binary…majiayu000
← Prev52 / 447Next →
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