Skip to content

Agent skills for Codex

3,289 agent skills for Codex, out of 3,419 agent skills listed. Popular ones include Rea analysis optimization, Rea changelog update and Rea ci tests audit. Codex reads the SKILL.md folder format, so each skill here can be copied into ~/.agents/skills. Each one lists what it can run and the steps to install it.
  1. Guides an agent on naming, visibility and menu placement for VS Code extension commands

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  2. Guides localization of VS Code extension settings, commands, walkthroughs and strings

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  3. Inspects a running website for layout, responsive, accessibility and consistency issues

    • Open source
    • 41.3K GitHub stars
    • Design and media
  4. Guides an agent through exposing a web app's user actions as WebMCP tools, verified

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  5. Makes the agent list the files it needs to see before answering a question

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  6. Lets your agent find and inspect Windows desktop API types from a local WinMD cache

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  7. Guides an agent through migrating UWP code to WinUI 3 and Windows App SDK APIs

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  8. Sets up a workshop folder structure for agent desks, locally or as a private GitHub repo

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  9. Guides an agent through Xquik X API integrations for tweet search, lookups and exports

    • Open source
    • 41.3K GitHub stars
    • Web search and scraping
  10. Routes GitHub Agentic Workflows requests to the matching gh-aw design, debug or upgrade

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  11. Guides reviewers through pull requests to awesome-copilot for fit, value and provenance

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  12. Scaffolds and registers canvas extensions and plugin manifests in awesome-copilot

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  13. Maps a codebase into seven evidence-based docs covering stack, structure, and risks

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  14. Runs an AI-readiness scan on a repo and builds a static HTML scoring dashboard

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  15. Guides an agent to create, pick, and apply AgentRC scoring policies

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  16. Turns ad campaign exports into cut, scale and test decisions with budget reallocation

    • Open source
    • 41.3K GitHub stars
    • Marketing and SEO
  17. Adds explanatory comments to a code file so it works as a learning resource

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  18. Guides building Illustrator panels, C++ plug-ins, MCP servers and command-line automation

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  19. Lets your agent write, debug and optimize Adobe Illustrator ExtendScript automation

    • Open source
    • 41.3K GitHub stars
    • Design and media
  20. Designs AI agent architectures from requirements or audits existing agents for flaws

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  21. Adds policy checks, intent screening, trust scores and audit logs to AI agents

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  22. Audits an AI agent codebase against the OWASP ASI Top 10 agentic security risks

    • Open source
    • 41.3K GitHub stars
    • Security
  23. Builds a minimal, vetted set of agent skills for a multi-step goal, with install checks

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  24. Hash and verify AI agent plugin files to detect tampering and untracked changes

    • Open source
    • 41.3K GitHub stars
    • Security
  25. Guides agents through self-critique, reflection loops and LLM-as-judge evaluation

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  26. Reviews a prompt for safety, bias, security and effectiveness, then suggests a rewrite

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  27. Sets up a lightweight producer, dev and QA agent team for planning and building projects

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  28. Lets Codex generate or edit raster images like photos, sprites and cutouts

    • Open source
    • 28.8K GitHub stars
    • Design and media