Agent skills

Skills for codex

9,699 skills that declare support for codex. 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
9,699 found
8,2098,256 · page 172 / 203
postman-openapi-converterConvert OpenAPI 3.x or Swagger 2.0 specs (YAML or JSON) into complete, import-ready Postman Collection v2.1 JSON files. Use this…sickn33postmark-automationAutomate Postmark email delivery tasks via Rube MCP (Composio): send templated emails, manage templates, monitor delivery stats…sickn33postmortem-writingComprehensive guide to writing effective, blameless postmortems that drive organizational learning and prevent incident…sickn33power-analysis-calculatorSkill for statistical power analysis and sample size calculationa5c-aiwritespower-consumption-testingMeasure and validate power consumption in embedded systems across sleep modes, active states, and peripheral usage.a5c-aiwritespower-sample-size-calculatorStatistical power analysis and sample size determinationa5c-aiwritespowershell-windowsPowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.sickn33pptx-generatorCreate and edit PowerPoint presentations from scratch with PptxGenJS — MiniMax's production-tested deck pipeline.nexu-iopptxRead, generate, and adjust PowerPoint slides, layouts, and templates. Useful for executive decks, training material, and product…nexu-iopqc-evaluatorPost-quantum cryptography evaluation skill for quantum-safe migrationa5c-aiwritespr-analyticsPR measurement and reporting automation following Barcelona Principles with comprehensive analytics and visualization capabilitiesa5c-aiwritespr-feedback-quality-gateSafely track pull request feedback, resolve review comments or merge conflicts, validate fixes, and use a read-only cross-review…nexu-iopr-merge-championOptimize pull requests for quick approval and merging by ensuring clean diffs, comprehensive self-reviews, and structured…sickn33pr-pitchCreate media pitch packages. Use when: building pitch templates, media lists, outreach strategy, or journalist-request-platform…indranilbanerjeepr-review-ci-fixAutomated PR review and CI auto-fix for GitHub and GitLab using the Composio CLI. Pulls diffs, fetches failing job logs, posts…composio-communitypr-review-expertUse when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of…alirezarezvanipr-writerCreate pull requests following Sentry's engineering practices.sickn33prd-to-specConvert an approved PRD into a phase-gated implementation SPEC. User-facing entry point that dispatches to the prd-to-spec…a5c-aiprd-to-specTransform a PRD into a technical SPEC document — architecture, API design, data model, error handling, and implementation…smallnestpre-mortem-facilitatorPre-mortem analysis skill for prospective hindsight and failure mode identificationa5c-aiwritespre-publish-reviewNuclear-grade 16-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release…code-yeongyupre-ship-gateA ship gate that runs before any production deploy: checks the silent failure modes that make a deploy 'succeed' while prod stays…sickn33precedent-transaction-analyzerM&A precedent transaction analysis skill with deal sourcing and premium analysisa5c-aiwritesprecoro-automationAutomate Precoro tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpredictive-maintenance-schedulerPredictive maintenance scheduling skill using telematics data and historical patterns to maximize fleet uptimea5c-aiwritespremium-3d-websiteGuidelines for building premium 3D websites, focusing on custom WebGL shaders, post-processing, physics-based interactions…sickn33prepare-releasePrepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release…CherryHQprerender-automationAutomate Prerender tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpress-release-distributionWire service integration and press release distribution managementa5c-aiwritespressure-vesselSkill for pressure vessel design and analysis per ASME BPVCa5c-aiwritespricing-strategyDesign pricing, packaging, and monetization strategies based on value, customer willingness to pay, and growth objectives.sickn33pricing-testTest pricing strategies with synthetic data. Use when: simulating willingness to pay, price sensitivity, or optimal price points.indranilbanerjeeprimary-source-evaluationAuthenticate, date, and critically assess historical documents for provenance, reliability, and bias with systematic source…a5c-aiwritesprintautopilot-automationAutomate Printautopilot tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQprisma-automationAutomate Prisma tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQprisma-expertYou are an expert in Prisma ORM with deep knowledge of schema design, migrations, query optimization, relations modeling, and…sickn33prisma-patternsPrisma ORM patterns for TypeScript backends — schema design, query optimization, transactions, pagination, and critical traps…mturacPrismic AutomationAutomate headless CMS operations in Prismic -- query documents, search content, retrieve custom types, and manage repository refs…ComposioHQprivacy-maskMask, redact, anonymize and censor sensitive information (PII) in screenshots and images — phone numbers, emails, IDs, API keys…sickn33privilege-escalation-methodsProvide comprehensive techniques for escalating privileges from a low-privileged user to root/administrator access on compromised…sickn33pro-workflowComplete AI coding workflow system. Orchestration patterns, 18 hook events, 8 agents, cross-agent support, reference guides, and…rohitg00probabilistic-analysis-toolkitAnalyze randomized algorithms with probability theory tools and concentration inequalitiesa5c-aiwritesprocess-analyzerAnalyze processes, identify workflows, define boundaries and scope, and map process requirements for specialization creation.a5c-aiprocess-builderScaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase…a5c-aiprocess-capability-calculatorProcess capability analysis skill with Cp, Cpk, Pp, Ppk calculations and specification compliance assessment.a5c-aiwritesprocess-economics-estimatorProcess economics estimation skill for capital costs, operating costs, and profitability analysisa5c-aiwritesprocess-fmea-generatorProcess Failure Mode and Effects Analysis (PFMEA) skill for manufacturing risk assessmenta5c-aiwritesprocess-generatorGenerate process JS files following Babysitter SDK patterns including task definitions, quality gates, breakpoints, and proper io…a5c-aiwrites
← Prev172 / 203Next →
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