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
5,3775,424 · page 113 / 143
ontoly-software-graphUse Ontoly's deterministic Software Graph, MCP server, and agent skills for architecture review, request tracing, impact…sickn33open-dynamic-workflowsPlan, orchestrate, and adversarially verify parallel AI coding agents with a dynamic multi-agent workflow engine.sickn33open-graphWhen the user wants to add or optimize Open Graph metadata for social sharing. Also use when the user mentions "Open Graph,"…kostja94open-house-planPlan and promote an open house that draws buyers and generates leads. Use when asked to plan an open house, market an open house…mohitagw15856open-sea-automationAutomate Open Sea tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQopen-source-strategyWhen the user wants open source strategy, OSS commercialization, or open source growth. Also use when the user mentions "open…kostja94openapi-spec-generatorGenerate complete, production-ready OpenAPI 3.x and Swagger 2.0 specifications from natural language descriptions, code, or…sickn33opencage-automationAutomate Opencage tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQopengraph-io-automationAutomate Opengraph IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQopenperplex-automationAutomate Openperplex tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQopenrouter-automationAutomate Openrouter tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQopensource-pipelineOpen-source pipeline: fork, sanitize, and package private projects for safe public release. Chains 3 agents (forker, sanitizer…mturacopenweather-api-automationAutomate Openweather API tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQops-inspectorAIOps-style one-click inspection skill for CloudBase resources. Use this skill when users need to diagnose errors, check resource…TencentCloudBaseoptim-agentGuide agent-driven parameter optimization for configurable systems with measurable objectives. Use for HPO, inference tuning…sickn33optimizing-performanceAnalyzes and optimizes application performance across frontend, backend, and database layers. Use when diagnosing slowness…CloudAI-Xoptimoroute-automationAutomate Optimoroute tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQoptions-flow-analyzerReal vs lottery call separation for options P/C ratio analysis — prevents signal inversion from deep OTM noisesickn33oral-health-analyzer分析口腔健康数据、识别口腔问题模式、评估口腔健康状况、提供个性化口腔健康建议。支持与营养、慢性病、用药等其他健康数据的关联分析。sickn33orchestrate-reviewUse when user asks to \"deep review the code\", \"thorough code review\", \"multi-pass review\", or when orchestrating the Phase…agent-shorchestrateWire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and…rohitg00org-chartTurn a team or reporting structure into a clean org chart. Use when asked to draw an org chart, show reporting lines, visualize…mohitagw15856os-scriptingOperating system and shell scripting troubleshooting workflow for Linux, macOS, and Windows. Covers bash scripting, system…sickn33osterwalder-canvas-architectIterative consultant agent for building and validating logically consistent 9-block Business Model Canvases.sickn33out-of-office-designerDesign an out-of-office that actually protects the time off — the auto-reply that routes instead of apologizes, the coverage map…mohitagw15856outline-before-proseOutline documents before drafting them — the argument skeleton that gets alignment cheaply, the one-line-per-section discipline…mohitagw15856outlook-automationAutomate Outlook tasks via Rube MCP (Composio): emails, calendar, contacts, folders, attachments. Always search tools first for…sickn33outlook-calendar-automationAutomate Outlook Calendar tasks via Rube MCP (Composio): create events, manage attendees, find meeting times, and handle…sickn33outreach-messageWrite cold outreach and networking messages that actually get replies. Use when asked to write a cold message to a…mohitagw15856oversized-skillA skill whose body deliberately exceeds the 500-line recommendation.first-flukeowl-protocol-automationAutomate Owl Protocol tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpackage-healthCheck a package's health before you depend on it — npm and PyPI registry APIs via keyless curl: downloads, release recency…mohitagw15856page-croAnalyze and optimize individual pages for conversion performance.sickn33page-seo-analysisAnalyze SEO for a single page. Use when: auditing on-page signals, schema, content quality, E-E-A-T, or AI search readiness.indranilbanerjeepage-x-automationAutomate Page X tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpagerduty-automationAutomate PagerDuty tasks via Rube MCP (Composio): manage incidents, services, schedules, escalation policies, and on-call…sickn33pagespeed-enhancerScan, audit, and fix web performance issues across all four Lighthouse/PageSpeed Insights pillars — Performance, Accessibility…sickn33paid-acquisition-planPlan a paid acquisition / performance marketing program with unit economics that work. Use when asked to plan paid media…mohitagw15856paid-ads-strategyWhen the user wants to plan paid ads strategy, allocate ad budget, or choose paid channels. Also use when the user mentions "paid…kostja94paid-adsYou are an expert performance marketer with direct access to ad platform accounts. Your goal is to help create, optimize, and…sickn33pakistan-payments-stackDesign and implement production-grade Pakistani payment integrations (JazzCash, Easypaisa, bank/PSP rails, optional Raast) for…sickn33PandaDoc AutomationAutomate document workflows with PandaDoc -- create documents from files, manage contacts, organize folders, set up webhooks…ComposioHQpaper-search-usageThis skill should be used when user asks to "search for papers", "find research papers", "search arXiv", "search PubMed", "find…fcakyonparadym-automationAutomate Paradym tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQparallel-agentsMulti-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when…sickn33parallel-automationAutomate Parallel tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQparallel-executionPatterns for parallel subagent execution using Task tool with run_in_background. Use when coordinating multiple independent…CloudAI-Xparallel-investigationCoordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system…rohitg00
← Prev113 / 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