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 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
21,420 found
4,6574,704 · page 98 / 447
Simplification CascadesFind one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Zmajiayu000simplification-principlesApply simplification principles (Occam's Razor) when debugging complex issues, evaluating competing theories, or simplifying…majiayu000simulate-elite-expertsSimulate high-stakes reasoning by modeling how top experts in the relevant domain would think, disagree, and converge on a…majiayu000single-cell-multi-omics-integrationQuick-reference sheet for OmicVerse tutorials spanning MOFA, GLUE pairing, SIMBA integration, TOSICA transfer, and StaVIA…FreedomIntelligencesingle-trajectory-analysisGuide to reproducing OmicVerse trajectory workflows spanning PAGA, Palantir, VIA, velocity coupling, and fate scoring notebooks.FreedomIntelligenceskd-infoАнализ структуры схемы компоновки данных 1С (СКД) — наборы, поля, параметры, варианты. Используй для понимания отчёта — источник…majiayu000writesskep基于当前仓库进行证据驱动的方案审视:先自主探索并阅读相关代码、配置、文档与测试,再提出有依据的质疑,评估优点、缺点、风险、可行性与预期效果,并通过讨论推进决策。用于需要判断当前方案是否可行、效果是否达标、是否应调整技术路线或实现策略时。majiayu000skeumorphismReal-world mimicry with textured surfaces, 3D effects, and familiar physical metaphors for intuitive digital interfaces.bergsideGREP-EXA-RESEARCHResearch libraries, APIs, and patterns using searchGitHub and Exa tools. Finds real-world implementations and saves structured…majiayu000writesdeep-analysisExecute high-density analysis on complex ideas/tasks. Move from 'Vague' to 'Verified' by producing: constraints -> core modules…majiayu000OSINTOpen source intelligence gathering. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate.majiayu000numpyN-dimensional array computing library providing array types, vectorized operations, linear algebra, FFT, random sampling, and…majiayu000skin-health-analyzer-huifer-wellally-health-0ec3b985分析皮肤健康数据、识别皮肤问题模式、评估皮肤健康状况、提供个性化皮肤健康建议。支持与营养、慢性病、用药等其他健康数据的关联分析。majiayu000sleep-analyzer分析睡眠数据、识别睡眠模式、评估睡眠质量,并提供个性化睡眠改善建议。支持与其他健康数据的关联分析。majiayu000writessleep-analyzer分析睡眠数据、识别睡眠模式、评估睡眠质量,并提供个性化睡眠改善建议。支持与其他健康数据的关联分析。majiayu000writessleep-analyzer分析睡眠数据、识别睡眠模式、评估睡眠质量,并提供个性化睡眠改善建议。支持与其他健康数据的关联分析。majiayu000writesslim-executive-summaryGenerate comprehensive executive summaries from workspace communication files using AI analysis with automatic context discoverymajiayu000slippageSlippage estimation, optimization, and protection for trade executionmajiayu000slo-implementationDefine and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting. Use…wshobsonsmart-interviewReset to smart interview depth (default). Use when user says '/smart-interview' or wants to reset interview mode.majiayu000smart-sourcingSelects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when deciding whether a…majiayu000snap-yaml-generatorGenerate snapcraft.yaml with confinement settings for Ubuntu Snap packagesa5c-aiwritesx-topic-intelligence当需要在 X/Twitter 上围绕某个主题收集热门帖子、趋势讨论、KOL 内容、钩子写法、回复驱动内容或社媒情报数据集时使用。适用于内容调研、舆情研究、话题扫描、社媒竞品观察和内容机会分析等场景,优先快速模式,深入采集时再做多轮 DOM 抓取。majiayu000society-of-mindIntelligence emerges from many simple agents (Minsky)majiayu000socketioSocket.io rooms, namespaces, adapters, middleware, and real-time patterns.a5c-aiwritessocratic-tutorGuide users through learning by asking questions, giving progressive hints, and helping them reason step by step instead of…mingchen666sofa-scoreCalculate SOFA (Sequential Organ Failure Assessment) score for ICU patients in MIMIC-IV. Use for sepsis severity assessment…majiayu000soliton-detectionTopological soliton detection and agency bridge with anyonic fusion algebra for concept compositionmajiayu000solution-comparatorCompare multiple solutions for correctness and performancea5c-aiwritessolution-explainerGenerate clear explanations of algorithm solutionsa5c-aiwritessophia-rsi-enhancedRSI-Enhanced Sophia Singularity with full integration: 21 Dokkōdō precepts, Five Rings (element+morpheme variants)…majiayu000sopimuksen-tarkistusSopimuksen lausekekohtainen riskiarvio Suomen oikeuden mukaan ja luokittelu (VIHREÄ / KELTAINEN / PUNAINEN). Käytä tätä skilliä…akunikkolaSoulEmbody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.majiayu000hopeCognitive operating system for structured thinking with confidence tracking. Use when starting complex tasks, making decisions…majiayu000soulEmbody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.majiayu000source-analysisPrimary and secondary source analysis for historical reasoning. Covers source classification, sourcing (author/context/purpose)…majiayu000source-credibility-analyzer/============================================================================/majiayu000source-researchSearch and cite primary sources from Source Library. Use when asked what historical authors wrote, to find quotes from old texts…majiayu000spaciousGenerous whitespace, consistent padding, and grid-based layouts for clean, readable, and breathing interfaces.bergsidespacyspaCy NLP library with pipelines. Use for text processing.majiayu000spark-prairie-fire触发:当你从零起步、资源极少、需要先找到最小可行切入口并建立稳定根据地时调用;常见信号包括 bootstrap、MVP、pilot、first foothold、小团队起步。HughYaubio-spatial-transcriptomics-spatial-deconvolutionEstimate cell type composition in spatial transcriptomics spots using reference-based deconvolution. Use cell2location, RCTD…majiayu000spawn-investigatorInvestigate a codebase question using an isolated subagent. Use when you need to read many files without bloating the main…majiayu000SpcImplement SPC charting, process capability analysis, and control chart interpretation. Covers control chart selection, capability…majiayu000speak-enterprise-rbacConfigure Speak for schools and organizations: SSO, teacher/student roles, class management, and usage reporting. Use when…jeremylongshorewritesspeak-webhooks-eventsHandle Speak lesson completion events, progress webhooks, and achievement notifications. Use when implementing webhooks events…jeremylongshorewritesspecialization-researcherResearch specialization domains, compile references, analyze best practices, and gather comprehensive knowledge for new…majiayu000writesspecification-generationConvert requirements into structured technical specifications with architecture decisionsa5c-aiwrites
← Prev98 / 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