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
5,9536,000 · page 125 / 143
ggetgget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and…mturacliterature-reviewSystematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning…mturacscholar-evaluationStructured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation…mturacscientific-writingThis is the core skill for the deep research and writing tool—combining AI-driven deep research with well-formatted written…sickn33scikit-learnMachine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines.sickn33scope-creep-responseHandle scope creep on client work without torching the relationship — classify the ask against the agreement, respond with the…mohitagw15856scoring-checksAdd a new deterministic scoring check in src/scoring/checks/ that evaluates config quality. Follows the Check[] return pattern…caliber-ai-orgscrape-do-automationAutomate Scrape Do tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQscrapegraph-ai-automationAutomate Scrapegraph AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQscrapfly-automationAutomate Scrapfly tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQscrapingant-automationAutomate Scrapingant tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQscrapingbee-automationAutomate Scrapingbee tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQscreen-reader-testingTest web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility…wshobsonscreenshot-fyi-automationAutomate Screenshot Fyi tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQscreenshotCapture desktop, app windows, or pixel regions across OS platforms. Useful for marketing screenshots, design reviews, and bug…nexu-ioscreenshot-teardownTear down a competitor's product from screenshots of its actual UI — onboarding, pricing page, core flows. Use when given…mohitagw15856screenshotone-automationAutomate Screenshotone tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQscreenshots-marketingGenerate marketing screenshots with Playwright. Useful for landing-page hero shots, App Store screenshots, and changelog visuals.nexu-ioscreenshotsGenerate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product Hunt…sickn33screenstudio-altOpen-source headless Screen Studio alternative: auto speed-up of idle, auto-zoom on click clusters, keystroke overlay chips…sickn33scroll-experienceExpert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and…sickn33seabornSeaborn is a Python visualization library for creating publication-quality statistical graphics. Use this skill for…sickn33search-firstResearch-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the…mturacsearch-knowledgeSearch stored brand knowledge. Use when: recalling past learnings, voice guidelines, or competitor insights via semantic search.indranilbanerjeesearch-specialistExpert web researcher using advanced search techniques andsickn33seat-geek-automationAutomate Seat Geek tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsecond-opinion-requestGet a second medical opinion without torching the first relationship — when it's warranted, how to raise it with the current…mohitagw15856secrets-managementSecure secrets management practices for CI/CD pipelines using Vault, AWS Secrets Manager, and other tools.sickn33secrets-managementImplement secure secrets management for CI/CD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when…wshobsonsecurity-and-hardeningHardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use…addyosmanisecurity-and-hardeningHardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use…sickn33security-auditComprehensive security auditing workflow covering web application testing, API security, penetration testing, vulnerability…sickn33security-auditorExpert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks.sickn33security-bluebook-builderBuild a minimal but real security policy for sensitive apps. The output is a single, coherent Blue Book document using…sickn33security-bounty-hunterHunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify…mturacsecurity-checklistReference document for monopoly security-checklist.sickn33security-deposit-recoveryGet your security deposit back — the move-out documentation that wins disputes before they start, the itemized-deduction…mohitagw15856security-incident-responseRun or document a security incident response — contain, eradicate, recover, and learn. Use when responding to a…mohitagw15856security-patternsImplements authentication, authorization, encryption, secrets management, and security hardening patterns. Use when designing…CloudAI-Xsecurity-questionnaire-autofillDraft answers to a vendor security questionnaire (SIG, CAIQ, or a custom sheet) from your real controls — fast, consistent, and…mohitagw15856security-researchTeam Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in parallel…code-yeongyusecurity-reviewReview a design, PR, or feature for security issues before it ships. Use when asked to do a security review, security-review a…mohitagw15856security-scanScan your OpenAI Codex configuration (.codex/ directory) for security vulnerabilities, misconfigurations, and injection risks…mturacsecurity-scanning-security-hardeningCoordinate multi-layer security scanning and hardening across application, infrastructure, and compliance controls.sickn33security-scanning-security-sastStatic Application Security Testing (SAST) for code vulnerability analysis across multiple languages and frameworks 'sickn33security-threat-modelWrite a STRIDE-based threat model for a service or feature. Use when asked to produce a threat model, document security risks…mohitagw15856securitytrails-automationAutomate Securitytrails tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsegment-audienceCreate audience segments. Use when: building or updating CRM or email platform segments for campaign targeting.indranilbanerjee
← Prev125 / 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