Agent skills

Skills for cursor

6,852 skills that declare support for cursor. The SKILL.md format is shared, so most of these work in the other agents too — the declaration only says where the author tested it.

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
6,852 found
6,2896,336 · page 132 / 143
startup-business-analyst-financial-projectionsCreate detailed 3-5 year financial model with revenue, costs, cash flow, and scenarios 'sickn33startup-business-analyst-market-opportunityGenerate comprehensive market opportunity analysis with TAM/SAM/SOM calculations 'sickn33startup-financial-modelingBuild comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario…sickn33startup-idea-validatorPressure-test a startup idea the way a sharp investor or co-founder would — problem, market, wedge, moat, why-now, and the…mohitagw15856startup-metrics-frameworkTrack, calculate, and optimize key performance metrics for SaaS, marketplace, consumer, and B2B startups from seed through Series…wshobsonstartups-page-generatorWhen the user wants to create, optimize, or audit a startups, education, or special program page. Also use when the user mentions…kostja94statement-of-workWrite a tight Statement of Work (SOW) that prevents scope creep and payment disputes. Use when asked to write a SOW, a scope of…mohitagw15856statsmodelsStatsmodels is Python's premier library for statistical modeling, providing tools for estimation, inference, and diagnostics…sickn33statusShow a unified status snapshot of the active brand: profile, active engagements with current part, recent insights, recent…indranilbanerjeewritesstatus-page-generatorWhen the user wants to create, optimize, or structure a status page. Also use when the user mentions "status page,"…kostja94status-report-pipelineBuild the pipeline that turns team updates into the rollup report without the Friday scramble — the collection format that…mohitagw15856statuscake-automationAutomate Statuscake tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsteve-jobsAgente que simula Steve Jobs — cofundador da Apple, CEO da Pixar, fundador da NeXT, o maior designer de produtos tecnologicos da…sickn33stitch-loopIterative design-to-code feedback loop. Critique → adjust → ship cycle for tightening visual fidelity between brief and built UI.nexu-iostitch-loopTeaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop patternsickn33writesstock-snapshotFetch a stock quote snapshot with keyless curl — Yahoo Finance's public chart endpoint, read with the discipline unofficial…mohitagw15856stoic-setback-debriefRecover from a professional setback — a failed launch, brutal feedback, a public mistake, a lost deal, a layoff — using the…mohitagw15856storeganise-automationAutomate Storeganise tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQstorerocket-automationAutomate Storerocket tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQstormglass-io-automationAutomate Stormglass IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQstory-pitchPitch a news or feature story to an editor — the angle, why now, and how you'll report it. Use when a reporter or freelancer…mohitagw15856strategic-compactSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary…mturacstrategic-narrative-generatorGenerate the strategic story connecting a product roadmap to company goals in a form non-technical stakeholders can repeat. Use…mohitagw15856strategy-memoWrite a strategy memo that commits to a bet and says what you won't do. Use when asked to write a strategy memo, articulate a…mohitagw15856strava-automationAutomate Strava tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQstreamtime-automationAutomate Streamtime tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQstripe-automationAutomate Stripe tasks via Rube MCP (Composio): customers, charges, subscriptions, invoices, products, refunds. Always search…sickn33stripe-integration-expertProduction-grade Stripe integrations: subscriptions with trials and proration, one-time payments, usage-based billing, checkout…alirezarezvanistripe-integrationMaster Stripe payment processing integration for robust, PCI-compliant payment flows including checkout, subscriptions, webhooks…sickn33stripe-projectsUse when the user wants to provision infrastructure or third-party services using Stripe Projects. Triggers: "I need a database"…fcakyonstructured-code-reviewPerforms a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and…rohitg00student-feedbackWrite constructive, specific feedback on student work that motivates and tells the student exactly how to improve. Use when asked…mohitagw15856style-fingerprintStudy 3-5 documents the user actually shipped and distil a compact style card — so every skill writes in their voice, not the…mohitagw15856styleseed-design-reviewReviews UI/frontend code and tells you exactly why it "looks AI-generated" — then how to fix it. Use it when a…bitjarustyleseed-design-reviewReviews UI/frontend code and tells you exactly why it "looks AI-generated" — then how to fix it. Use it when a…sickn33subagent-creatorGuide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent…tech-leads-clubsubagent-orchestrationDecompose work across parallel subagents properly — task slicing that avoids collisions, briefs that stand alone, and result…mohitagw15856subcontractor-scorecardScore a subcontractor's performance across schedule reliability, quality, safety, paperwork, and change-order behaviour with…mohitagw15856submit-programResearch an affiliate program and create a verified listing for openaffiliate.dev. Use this skill when the user asks anything…Affitorsubstack-notes-scraperScrapes a Substack Notes page and exports engagement data to a formatted .xlsx file. Use when asked to download, analyse, or…mohitagw15856subtitle-captionWrite or translate subtitles/captions that respect reading speed and timing rules. Use when asked to write subtitles, captions…mohitagw15856summarize-anythingTurn a long article, email thread, document, or transcript into a tight summary you can act on — the gist, the key points, and…mohitagw15856sun-and-moonGet sunrise, sunset, golden hour, day length, and moon phase for any location with zero API keys — sunrise-sunset.org and…mohitagw15856sun-tzu-strategy-briefPrepare for a specific contest — a competitive deal, a negotiation, a market entry, a turf fight — using the actual planning…mohitagw15856supabase-automationAutomate Supabase database queries, table management, project administration, storage, edge functions, and SQL execution via Rube…sickn33supadata-automationAutomate Supadata tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsuperchat-automationAutomate Superchat tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsupplier-scorecardBuild a quarterly supplier performance scorecard with a weighted grade and a clear escalate/develop/exit call. Use when asked to…mohitagw15856
← Prev132 / 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