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
5,0895,136 · page 107 / 143
mcp-server-specDesign an MCP server for a product — the tool surface, auth model, and safety boundaries that make it genuinely usable by AI…mohitagw15856mcp-tool-developerBuild Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing…sickn33mdpr-skillReview MDPR Markdown presentation workflows with semantic hints, visual checks, and deterministic renderer boundaries.sickn33meal-prep-osTurn what's actually in the fridge and 90 minutes on Sunday into a week that mostly feeds itself — a cook-once-eat-thrice batch…mohitagw15856mechanic-quote-decoderRead a garage quote or invoice like someone who can't be padded — which line items connect to your actual symptom, which are…mohitagw15856media-kit-page-generatorWhen the user wants to create, optimize, or audit media kit or press page. Also use when the user mentions "media kit," "press…kostja94media-pitchWrite a media pitch or press outreach email for any story or announcement. Use when asked to write a media pitch, journalist…mohitagw15856media-planCreate a paid media plan. Use when: building media buy schedules, cross-channel budget allocation, or creative rotation calendars.indranilbanerjeemedical-records-requestRequest your medical records and actually get them — what to ask for, the request letter that can't be shuffled aside, the…mohitagw15856medium-postsWhen the user wants to write, publish, republish, or optimize posts on Medium.com (canonical tags, distribution, Medium SEO).…kostja94meeting-action-extractorPull the action items and decisions out of meeting notes or a transcript — each with an owner, a due date, and enough context to…mohitagw15856meeting-analyzerAnalyzes meeting transcripts and recordings to surface behavioral patterns, communication anti-patterns, and actionable coaching…alirezarezvanimeeting-cost-meterPrice meetings in money and focus — the attendee-hours × loaded-rate math, the recurring multiplier that turns a weekly…mohitagw15856meeting-follow-up-pipelineTurn a completed meeting into a debrief, decisions, action items, ready-to-send follow-up drafts, and proposed writebacks. Use…zapiermeeting-groundingConvert a raw multi-speaker meeting transcript into structured meeting notes for downstream follow-up, with optional topic-level…gaotiexinqumeeting-prep-livePrepare the user for a REAL upcoming meeting by pulling the actual Calendar event, its attendees, the linked Drive docs, and the…mohitagw15856meeting-prep-packArrive at a meeting armed in fifteen minutes — the prep pack: what this meeting decides, your position with its reasons, the…mohitagw15856meeting-room-etiquetteSet the shared-space norms that end the small daily frictions — meeting room booking discipline (the ghost-booking cure)…mohitagw15856melo-automationAutomate Melo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmem-automationAutomate Mem tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmem0-automationAutomate Mem0 tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmemberspot-automationAutomate Memberspot tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmemberstack-automationAutomate Memberstack tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmembervault-automationAutomate Membervault tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmemory-forensicsComprehensive techniques for acquiring, analyzing, and extracting artifacts from memory dumps for incident response and malware…sickn33memoryPersistent, token-efficient project memory. When ON, maintains a `.shob/memory/` folder of structured `.md` files so the full…shobcodermental-health-analyzer分析心理健康数据、识别心理模式、评估心理健康状况、提供个性化心理健康建议。支持与睡眠、运动、营养等其他健康数据的关联分析。sickn33writesmenu-cost-engineerCost a menu item to a plate cost and food-cost percentage, then price it for a target margin. Use when asked to cost a dish…mohitagw15856mercury-mcpCheatsheet for the Mercury (proton) MCP tools. Use when connected to the Mercury MCP server to look up which mercury_* tool to…sickn33mermaid-expertCreate Mermaid diagrams for flowcharts, sequences, ERDs, and architectures. Masters syntax for all diagram types and styling.sickn33mesh-memorySelf-hosted semantic memory for AI agents via MCP. Save worklogs, decisions, and notes, then recall them across sessions by…sickn33message-for-the-momentWrite the short message you freeze on — a thank-you, condolence, congratulations, apology, or a graceful 'no' to an invite —…mohitagw15856message-testTest message variants on synthetic audiences. Use when: predicting response rates, sentiment, or objections before live tests.indranilbanerjeemessages-opsEvidence-first live messaging workflow for ecc. Use when the user wants to read texts or DMs, recover a recent one-time code…mturacmessaging-frameworkBuild a messaging framework (message house) that the whole company can use consistently. Use when asked to create messaging, a…mohitagw15856meta-adsWhen the user wants to set up, optimize, or manage Meta (Facebook/Instagram) Ads. Also use when the user mentions "Meta Ads,"…kostja94metaads-automationAutomate Metaads tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpage-metadataWhen the user wants to optimize meta tags other than title, description, Open Graph, or Twitter Cards. Also use when the user…kostja94metaphor-automationAutomate Metaphor tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmetasploit-framework⚠️ AUTHORIZED USE ONLY > This skill is for educational purposes or authorized security assessments only. > You must have…sickn33metric-gaslighting-detectorFind out how a dashboard, KPI report, or metrics slide is lying to you — before you repeat its story in a bigger room. Use when…mohitagw15856metric-semantic-layerDefine a metric in a semantic layer so it means one thing everywhere. Use when asked to define a metric, build a semantic layer /…mohitagw15856metric-tree-builderDecompose a north-star metric into a driver tree — the inputs and sub-inputs that actually move it — so a team knows which levers…mohitagw15856mezmo-automationAutomate Mezmo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmicro-retirement-plannerPlan a deliberate career break — 3 to 12 months off between chapters — with honest runway math, the re-entry story rehearsed…mohitagw15856micro-saas-launcherExpert in launching small, focused SaaS products fast - the indie hacker approach to building profitable software. Covers idea…sickn33microcopy-writerWrite the small UI text that guides users — buttons, labels, tooltips, CTAs, confirmations. Use when asked to write microcopy…mohitagw15856microservices-decompositionDesign a microservices decomposition for a monolith or new system, defining service boundaries, ownership, communication…mohitagw15856
← Prev107 / 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