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
5,4735,520 · page 115 / 143
performance-optimizationOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when…addyosmaniperformance-optimizationOptimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when…sickn33performance-reportGenerate performance reports. Use when: tracking KPIs, trend analysis, anomaly detection, and actionable recommendations.indranilbanerjeeperformance-testing-review-ai-reviewYou are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and…sickn33performance-testing-review-multi-agent-reviewUse when working with performance testing review multi agent reviewsickn33perigon-automationAutomate Perigon tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQperl-patternsModern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.mturacperl-securityComprehensive Perl security covering taint mode, input validation, safe process execution, DBI parameterized queries, web…mturacperl-testingPerl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.mturacpermission-tunerAnalyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are…rohitg00perplexityai-automationAutomate Perplexityai tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpersistiq-automationAutomate Persistiq tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmira-tan-perspectiveThe design-judgment lens of Mira Tan (a FICTIONAL product-design mentor), distilled from an invented corpus into 4 mental models…AIScientists-Devpersonal-bioWrite a professional bio in the three lengths you actually need. Use when asked to write a bio, an 'about me', a speaker/author…mohitagw15856personal-tool-builderExpert in building custom tools that solve your own problems first. The best products often start as personal tools - scratch…sickn33personal-wip-limitsCap your work-in-progress so things finish — the personal WIP limit (3 active outcomes, defended), the finish-before-start rule…mohitagw15856persuasion-briefBuild the case to win someone over to a decision, idea, or change. Use when asked to persuade someone, build a case for an idea…mohitagw15856pexels-automationAutomate Pexels tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQPhantomBuster AutomationAutomate lead generation, web scraping, and social media data extraction workflows through PhantomBuster's cloud platform via…ComposioHQphase-gated-debuggingUse when debugging any bug. Enforces a 5-phase protocol where code edits are blocked until root cause is confirmed. Prevents…sickn33photo-library-rescueRescue a photo library drowning in duplicates, screenshots, and 40,000 unsorted items — the triage order that shrinks first…mohitagw15856photopea-embedded-editorEmbed Photopea in web apps using photopea.js. Covers embedding, file I/O, scripting, exporting, layers, text, filters, and the…sickn33php-proWrite idiomatic PHP code with generators, iterators, SPL data structures, and modern OOP features. Use PROACTIVELY for…sickn33phpLanguage-specific super-code guidelines for php.sickn33pi-custom-modelRegister custom Pi Agent model slugs so saved OpenRouter variants resolve correctly.sickn33pi-web-searchGive Pi Agents a safe web-search and fetch workflow using the installed pi-web-access package.sickn33piggy-automationAutomate Piggy tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpilot-protocolGive an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocolsickn33piloterr-automationAutomate Piloterr tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpilvio-automationAutomate Pilvio tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpingdom-automationAutomate Pingdom tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpinterest-postsWhen the user wants to create Pinterest Pins, optimize Pin descriptions, or grow Pinterest presence. Also use when the user…kostja94pip-responderRespond to a performance improvement plan strategically — decode what the PIP really is, decide fight-vs-land-softly with clear…mohitagw15856pip-writerWrite a Performance Improvement Plan a manager can defend and an employee can actually act on — specific concerns, measurable…mohitagw15856pipedrive-automationAutomate Pipedrive CRM operations including deals, contacts, organizations, activities, notes, and pipeline management via Rube…sickn33pipeline-crm-automationAutomate Pipeline CRM tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpipeline-updateUpdate CRM pipeline. Use when: changing deal stages, values, notes, tracking velocity, or managing deal progression.indranilbanerjeepitch-packagerPackage a finished piece of work (spec, prototype, implementation notes) into a single document that gets reviewers to…Neeeophyteepitch-vs-teachKnow which talk you're giving — the pitch (drive one decision) vs. the teach (build understanding) — because mixing their…mohitagw15856pivot-analysis-plannerPlan pivot-table analysis that answers the actual question — the question-to-layout mapping (rows, values, filters chosen on…mohitagw15856pixelbin-mediaGenerate and edit images and videos with an 85+ API portfolio and build visually appealing website pages via Pixelbin.nexu-ioplacekey-automationAutomate Placekey tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplacid-automationAutomate Placid tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplaid-fintechExpert patterns for Plaid API integration including Link token flows, transactions sync, identity verification, Auth for ACH…sickn33plain-automationAutomate Plain tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplain-language-rewriteRewrite jargon-dense text into plain language without losing precision — the translation pass that keeps every fact and…mohitagw15856plan-design-reviewSenior Designer review: rates each design dimension 0-10, explains what a 10 looks like, and flags AI Slop signals. Useful as a…nexu-ioplan-interrogateStress-test a plan by walking its decision tree one question at a time. Use when the user wants to pressure-test a design before…rohitg00
← Prev115 / 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