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
3,1693,216 · page 67 / 447
evernote-multi-env-setupConfigure multi-environment setup for Evernote integrations. Use when setting up dev, staging, and production environments, or…jeremylongshorewritesevernote-observabilityImplement observability for Evernote integrations. Use when setting up monitoring, logging, tracing, or alerting for Evernote…jeremylongshorewritesevidence-scout指定薬剤・適応・国・データベース特性に基づき、PubMed/Web検索で先行RWD研究・RCT・ガイドラインを調査し、 エビデンスランドスケープを要約する。JMDC/MDV等クレームDBとの差別化観点を必ず含める。majiayu000evo-domain-researchConduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]majiayu000evo-os-root-cause-analysisAnalyzes a bug-fix commit or PR and produces a structured Root Cause Analysis report covering what went wrong, why, and what…majiayu000evo-technical-researchConduct technical research on technologies and architecture. Use when the user says "create a technical research report on…majiayu000exa-searchUse Exa for web/code/company research (web_search_exa / get_code_context_exa / company_research_exa), with parameters and…majiayu000Exa Semantic ResearchConceptual and semantic web search; cite sourcesmajiayu000exa-web-searchExa.ai semantic web search: neural search, crawl, contents extraction, highlights, date filteringmajiayu000exam-simulatorCreate realistic mock exams from user-provided materials, syllabi, exam scopes, or searched public information. Supports exam…mingchen666examensvorbereitung-fragenExamensvorbereitungs-Fragen für 1. und 2. Staatsexamen erstellen: Anwendungsfall Student will Examenswissen durch gezielte…majiayu000excalidrawUse when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture…softaworksexpansion-signal-spotterMonitor existing customer accounts for upsell and cross-sell signals: team growth on LinkedIn, new job postings, product usage…gooseworks-aioptimization.experiment_analysisAnalyze completed experiments and craft executive-ready summaries with insights and recommendations.majiayu000experiment-configuration-with-hydra-yamlYou are a coding standards expert specializing in experiment configuration with hydra yaml.majiayu000experiment-failure-analysisSystematically analyze experiment failures and optimization setbacks to identify root causes and define validation plans before…majiayu000experiment-queueSSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race…majiayu000writesexperiment-queueSSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race…majiayu000writesexperiment-trackerManages ML experiment tracking with MLflow, Weights & Biases, or SpecWeave's built-in tracking. Activates for "track…majiayu000experimental-plannerUse when theoretical calculations need experimental validation, protocols must be designed with clear hypotheses and success…majiayu000expert-panel-deliberationMulti-expert evaluation pattern for structured analysis and decision-making. PROACTIVELY activate for: (1) Analyze with expert…majiayu000expertise-manager/============================================================================/majiayu000explain-allierays-agentic-loopExplain what code does line by line so you can understand and learn from it.majiayu000explainUse when explaining code, concepts, patterns, or architecture: engineer-grade technical explanations with 3-tier depth control…majiayu000explain-architectureExplain the system architecture or a specific part of the codebasemajiayu000explain-codeExplains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when asked…majiayu000explain-codeExplain how code works in detail. Use when trying to understand unfamiliar code, complex logic, or system architecture.majiayu000explainExplain a file, function, or system — architectural walkthrough using query toolsmajiayu000explain-like-seniorSenior-level code explanations with deep technical insights and contextmajiayu000explainExplain what a piece of code does — a specific file, class, or method in close detail, or a user-facing flow as a concise system…majiayu000explainerUse when explaining code, technical concepts, or implementation decisions. Provides structured approach to creating clear…majiayu000writesexplaining-codeExplains code clearly and thoroughly. Use when asked to explain, clarify, or teach about code snippets, functions, or concepts.majiayu000explaining-codeExplains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user…majiayu000explorationCodebase exploration techniques for rapid discovery, architecture analysis, pattern detection, and dependency mapping.majiayu000explorationCode exploration strategies for understanding unfamiliar codebases. Use when exploring unknown code, debugging, or analyzing…majiayu000explorationCode exploration strategies for understanding unfamiliar codebases. Use when exploring unknown code, debugging, or analyzing…majiayu000exploratory-autoresearchUse when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A…gaasherexploring-graphAnalyze the knowledge graph for insights. Use when asked to "analyze connections", "graph report", "show hubs", "find orphans"…majiayu000extract-algorithmParse and document algorithm pseudocode from research papers. Use when preparing for implementation.majiayu000extract-dependenciesAnalyze imports and identify all module dependencies. Use when mapping project structure.majiayu000extract-physical-ai-formulasExtract and explain formulas used in Physical AI and Humanoid Robotics from text, lecture notes, or papers. Use when user asks to…majiayu000f-threadFusion/Comparison Thread for architecture decisions. Use when: - User says "compare approaches", "which is better" - User asks to…majiayu000fa-slot-creator在 Fantastic-admin 框架中创建插槽,向布局的任意位置注入自定义内容。当用户提到以下任何需求时必须使用此技能:在头部/侧边栏/工具栏/标签栏加东西、logo…fantastic-adminfa-store-generator为 Fantastic-admin 框架生成 Pinia Store 模块。当用户提到以下任何需求时必须使用此技能:多个页面需要共享数据、全局状态管理、数据需要持久化(刷新后还在)、登录状态/用户信息需要缓存、购物车/通知/权限等全局数据、需要在组件外访问状态…fantastic-adminfabric-aiGuides pattern selection through decomposition, exploration, and diverse approach generationmajiayu000faf-wizardDone-for-you .faf generator. One-click AI context for any project - new, legacy, or famous. Auto-detects stack, scores readiness…majiayu000failure-mode-analysisIdentify potential failure modes and assess system vulnerabilities for pilot workflows and integrations. Use when anticipating…majiayu000Failure Modes AnalysisComprehensive guide to identifying, analyzing, and documenting failure modes in distributed systemsmajiayu000
← Prev67 / 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