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
5,8575,904 · page 123 / 143
review-responseRespond to online reviews. Use when: drafting replies for Google, Yelp, G2, or building review response templates.indranilbanerjeereview-responseWrite the right reply to a customer review — positive, negative, or mixed. Use when asked to respond to a review, reply to a…mohitagw15856review-workPost-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle…code-yeongyurevolt-automationAutomate Revolt tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrexTranslates user intent into a precise, unambiguous specification and requirements.sickn33rfc-writerWrite an engineering RFC (Request for Comments) for a technical decision, architectural change, or significant implementation…mohitagw15856rfp-responseWrite a compliant, competitive response to an RFP/RFQ/ITT (government or enterprise procurement). Use when responding to a…mohitagw15856rfp-scoring-matrixBuild a weighted RFP evaluation matrix and defensible award recommendation. Use when asked to score RFP responses, compare vendor…mohitagw15856rfp-writerWrite a clear Request for Proposal that gets comparable, high-quality vendor bids. Use when asked to write an RFP, a request for…mohitagw15856riffkitRiff a winning TikTok into your own short video — study a proven video's emotion formula and regenerate it with your product…sickn33RingCentral AutomationRingCentral automation via Rube MCP -- toolkit not currently available in Composio; no RING_CENTRAL_ tools foundComposioHQring_central-automationAutomate RingCentral tasks via Rube MCP (Composio): calls, messages, meetings, and unified communications. Always search tools…ComposioHQrippling-automationAutomate Rippling tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrisk-managerMonitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements…sickn33risk-registerBuild and maintain a project or product risk register. Use when asked to create a risk register, identify project risks, build a…mohitagw15856ritekit-automationAutomate Ritekit tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQriverpodUse when setting up providers, combining requests, managing state disposal, passing arguments, performing side effects, or…evancarkvst-automationAutomate Rkvst tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrma-failure-analysisTurn field returns into a structured failure-analysis report — RMA triage taxonomy (NTF vs real failures), Pareto by verified…mohitagw15856roadmap-presentationCreate structured roadmap presentations calibrated to any audience. Use when asked to build a product roadmap, present roadmap to…mohitagw15856robius-app-architectureTokio, async, submit_async_request, 异步, 架构, SignalToUI, Cx::post_action, worker task, app structure, MatchEvent, handle_startupsickn33robius-event-actioncustom action, MatchEvent, post_action, cx.widget_action, handle_actions, DefaultNone, widget action, event handling, 事件处理, 自定义动作sickn33robius-matrix-integrationMatrix SDK, sliding sync, MatrixRequest, timeline, matrix-sdk, matrix client, robrix, matrix room, Matrix 集成, 聊天客户端sickn33robius-state-managementAppState, persistence, theme switch, 状态管理, 状态持久化, 主题切换sickn33robius-widget-patternsapply_over, TextOrImage, modal, 可复用, 模态, collapsible, drag drop, reusable widget, widget design, pageflip, 组件设计, 组件模式sickn33robot-framework-skillGenerates Robot Framework tests in keyword-driven syntax with Python. Supports SeleniumLibrary, RequestsLibrary, and custom…sickn33robots-txtWhen the user wants to configure, audit, or optimize robots.txt. Also use when the user mentions "robots.txt," "crawler rules,"…kostja94rocketlane-automationAutomate Rocketlane tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQroi-calculatorCalculate marketing ROI. Use when: measuring campaign ROAS, CAC, CPL, LTV, or multi-channel attribution returns.indranilbanerjeerole-redesign-for-aiRedesign a job role that AI now does a large part of — deliberately, instead of quietly expecting the same headcount to absorb…mohitagw15856rollback-planWrite a concrete rollback plan for a risky change (deploy, migration, feature-flag flip, config rollout) so the reverse is one…mohitagw15856roommate-agreementWrite the flat's constitution before the first passive-aggressive note — money, chores, guests, noise, food, and the exit plan…mohitagw15856root-cause-analysisPerforms systematic root cause analysis to identify the true source of bugs, errors, and unexpected behavior through structured…rohitg00rootly-automationAutomate Rootly tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrosette-text-analytics-automationAutomate Rosette Text Analytics tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQroute4me-automationAutomate Route4me tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrouterbase-model-gatewayIntegrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.sickn33rss-digestFetch and digest any RSS or Atom feed with zero API keys — curl plus disciplined parsing into a ranked, deduplicated briefing…mohitagw15856rubric-builderCreate a clear grading rubric with criteria and performance-level descriptors that make scoring fair, fast, and consistent. Use…mohitagw15856ruby-proWrite idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem…sickn33rubyLanguage-specific super-code guidelines for ruby.sickn33rulesUse when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or…code-yeongyurules-lawyerSettle a board game rules dispute like a fair judge — reconstruct the situation, rule from the rulebook text (pasted or known)…mohitagw15856run-deep-sweRun reproducible DeepSWE coding-agent benchmark evaluations through OpenRouter and mini-swe-agent.sickn33runapi-cliGenerate AI images, videos, and music/audio from agents using the RunAPI CLI.sickn33runway-plannerTurn burn and cash into a clear runway picture and a raise decision — months left, default-alive vs default-dead, and what to cut…mohitagw15856rust-patternsIdiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant…mturacrust-proMaster Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming.sickn33
← Prev123 / 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