Agent skills

Skills for cursor

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
6,852 found
2,9292,976 · page 62 / 143
ai-native-cliDesign spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling…sickn33ai-native-uiWeb and App implementation guide for AI Native UI. Trigger when user wants conversational interfaces, adaptive layouts, and…sickn33ai-product-canvasStructure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating…mohitagw15856ai-regression-testingRegression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated…mturacai-roi-auditAudit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes. Use when a CFO…mohitagw15856ai-seoWhen the user wants to build programmatic SEO with AI, create competitor alternative pages, optimize for AI Overviews, or scale…tech-leads-clubai-traffic-trackingWhen the user wants to track AI search traffic in GA4 or GSC. Also use when the user mentions "AI traffic," "ChatGPT referral,"…kostja94ai-ugc-adsWhen the user wants to create UGC ad campaigns, recruit UGC creators, generate AI UGC content, or scale with user-generated…tech-leads-clubai-usage-policyWrite an AI usage policy people can actually follow — approved tools, data rules, disclosure duties, and review obligations, in…mohitagw15856ai-wrapper-productExpert in building products that wrap AI APIs (OpenAI, Anthropic, etc. ) into focused tools people will pay for. Not just…sickn33aims-audit/cs:aims-audit <scope> — ISO/IEC 42001 AIMS internal-audit 6-question forcing interrogation. Use before certification stage 1…alirezarezvaniair-qualityCheck live air quality anywhere with zero API keys — Open-Meteo's air-quality API via curl, decoded from raw PM2.5 and AQI…mohitagw15856airtable-automationAutomate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current…sickn33aivoov-automationAutomate Aivoov tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQakf-trust-metadataThe AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds…sickn33alchemy-automationAutomate Alchemy tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQalexTurns requirements into a precise, dependency-aware implementation plan.sickn33algodocs-automationAutomate Algodocs tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQalgolia-automationAutomate Algolia tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQalgolia-searchExpert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuningsickn33algorithmic-artCreate generative art using p5.js with seeded randomness so every render is reproducible. Useful for procedural posters…nexu-ioall-hands-deckBuild an all-hands that lands with everyone from intern to VP — the mixed-altitude structure (the story for all, the numbers for…mohitagw15856all-images-ai-automationAutomate All Images AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQalpha-vantage-automationAutomate Alpha Vantage tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQalpha-vantageAccess 20+ years of global financial data: equities, options, forex, crypto, commodities, economic indicators, and 50+ technical…sickn33alternatives-page-generatorWhen the user wants to create, optimize, or audit alternatives or comparison content (page or blog article). Also use when the…kostja94altoviz-automationAutomate Altoviz tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQalttext-ai-automationAutomate Alttext AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQamara-automationAutomate Amara tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQamazon-alexaIntegracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como…sickn33amazon-automationAutomate Amazon tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQambee-automationAutomate Ambee tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQambient-weather-automationAutomate Ambient Weather tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQambiguity-resolverStructure vague opportunities and unclear briefs into actionable one-page problem statements. Use when asked to clarify a vague…mohitagw15856amcards-automationAutomate Amcards tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQamplitude-automationAutomate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first…sickn33analyst-relations-briefPrepare for an industry analyst briefing (Gartner, Forrester, IDC and similar). Use when asked to prep an analyst briefing, write…mohitagw15856analytics-productAnalytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.sickn33analytics-trackingDesign, audit, and improve analytics tracking systems that produce reliable, decision-ready data.sickn33analyzing-projectsAnalyzes codebases to understand structure, tech stack, patterns, and conventions. Use when onboarding to a new project…CloudAI-Xanchor-browser-automationAutomate Anchor Browser tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQandrej-karpathyBehavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…sickn33android-clean-architectureClean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases…mturacandroid-jetpack-compose-expertExpert guidance for building modern Android UIs with Jetpack Compose, covering state management, navigation, performance, and…sickn33android-ui-journey-testingXML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.sickn33angular-migrationMaster AngularJS to Angular migration, including hybrid apps, component conversion, dependency injection changes, and routing…sickn33announcement-cardWrite a short, punchy announcement designed to be shared as an image or social card. Use when asked to announce a launch…mohitagw15856anomaly-scanDetect marketing anomalies. Use when: traffic drops, cost spikes, conversion changes, deliverability issues, budget overruns.indranilbanerjee
← Prev62 / 143Next →
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