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
6,3376,384 · page 133 / 143
supply-chain-risk-auditorIdentifies dependencies at heightened risk of exploitation or takeover. Use when assessing supply chain attack surface…sickn33writessupport-macroWrite reusable support macros / canned responses that sound human, not robotic. Use when asked to write a support macro, a canned…mohitagw15856support-runbookWrite a support runbook for handling a recurring issue type consistently. Use when asked to write a support runbook, a…mohitagw15856supportbee-automationAutomate Supportbee tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsupportivekoala-automationAutomate Supportivekoala tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsurvey-design-basicsDesign a survey that measures instead of leads — neutral question wording, answer scales that don't smuggle conclusions, the…mohitagw15856SurveyMonkey AutomationAutomate SurveyMonkey survey creation, response collection, collector management, and survey discovery through natural language…ComposioHQsurvey_monkey-automationAutomate SurveyMonkey tasks via Rube MCP (Composio): surveys, responses, collectors, and survey analytics. Always search tools…ComposioHQsveltekitBuild full-stack web applications with SvelteKit — file-based routing, SSR, SSG, API routes, and form actions in one framework.sickn33svix-automationAutomate Svix tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQswift-actor-persistenceThread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.mturacswift-concurrency-6-2Swift 6.2 Approachable Concurrency — single-threaded by default, @concurrent for explicit background offloading, isolated…mturacswift-protocol-di-testingProtocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused…mturacswiftLanguage-specific super-code guidelines for swift.sickn33swiftui-designSwiftUI 前端设计 skill — anti AI-slop rules, design direction advisor, brand asset protocol, and five-dimension review. Works with…nexu-ioswiftui-patternsSwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and…mturacswiss-designWeb and App implementation guide for Swiss Design (International Typographic Style). Trigger when user wants strict grid systems…sickn33switch-brandSwitch active brand profile. Use when: changing brand context in multi-client or agency workflows.indranilbanerjeesycophancy-challengerFlip Claude’s default from validation to adversarial critique. Use when you are about to make a high-stakes decision, commit to a…mohitagw15856sympla-automationAutomate Sympla tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsympySymPy is a Python library for symbolic mathematics that enables exact computation using mathematical symbols rather than…sickn33sync-docsSync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after…agent-shsync-memoryBatch sync session learnings to memory. Use when: persisting campaign insights and performance history across sessions.indranilbanerjeesynthetic-user-researchUse AI personas for early-stage research signal — with hard guardrails on what synthetic methods can and cannot validate. Use…mohitagw15856synthflow-ai-automationAutomate Synthflow AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsynthwaveWeb and App implementation guide for Synthwave. Trigger when user wants 80s-inspired neon, dark backgrounds, outrun grids, and…sickn33system-design-interviewStructure a complete system design answer for interview questions or real architecture sessions. Use when asked to design a…mohitagw15856systems-programming-rust-projectYou are a Rust project architecture expert specializing in scaffolding production-ready Rust applications. Generate complete…sickn33tab-accordionWhen the user wants to add or optimize tab or accordion components for content organization. Also use when the user mentions "tab…kostja94tabletop-negotiatorPractice the table-talk that wins negotiation board games — play out a Catan-style trade, a Diplomacy-style alliance, or a…mohitagw15856taggun-automationAutomate Taggun tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtailwind-patternsTailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.sickn33taisly-social-media-postingUse Taisly Agent Kit to prepare and publish approved short-form video posts across TikTok, Instagram Reels, YouTube Shorts, X…sickn33talenthr-automationAutomate Talenthr tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtalivia-agent-kitSet up and verify Talivia revenue analytics through MCP, with explicit confirmation for website changes and payment attribution.sickn33tally-automationAutomate Tally tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtanstack-query-expertExpert in TanStack Query (React Query) — asynchronous state management. Covers data fetching, stale time configuration…sickn33tapfiliate-automationAutomate Tapfiliate tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtapform-automationAutomate Tapform tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtask-decompositionBreaks down complex software, writing, or research tasks into small, atomic, independently completable units with dependency…rohitg00task-triage-matrixTriage an overwhelming task list into what actually gets done — the urgent/important sort applied honestly (with the two…mohitagw15856tavily-automationAutomate Tavily tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtavily-usageThis skill should be used when user asks to "search the web", "fetch content from URL", "extract page content", "use Tavily…fcakyontavily-webWeb search, content extraction, crawling, and research capabilities using Tavily API. Use when you need to search the web for…sickn33tax-planning-checklistGenerate a structured tax planning checklist and review framework for any individual or business context. Use when asked to…mohitagw15856taxjar-automationAutomate Taxjar tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtcm-constitution-analyzer分析中医体质数据、识别体质类型、评估体质特征,并提供个性化养生建议。支持与营养、运动、睡眠等健康数据的关联分析。sickn33writestdd-orchestratorMaster TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive…sickn33
← Prev133 / 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