Skip to content

Agent skills

Agent skills are folders of instructions and scripts that teach Claude Code, Codex, Cursor and other agents a task. Each one lists what it can run and how to install it.
  1. Optimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence

    • Open source
    • 465K GitHub stars
  2. Prepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Ple

    • Open source
    • 465K GitHub stars
    • Developer tools
  3. Audit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigation

    • Open source
    • 465K GitHub stars
  4. Audit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.

    • Open source
    • 465K GitHub stars
    • Design and media
  5. Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (Agent

    • Open source
    • 465K GitHub stars
  6. Ask which skill or flow fits your situation

    • Open source
    • 326K GitHub stars
  7. Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's docu

    • Open source
    • 326K GitHub stars
    • Developer tools
  8. Shared vocabulary for designing deep modules

    • Open source
    • 326K GitHub stars
    • Design and media
  9. Build and sharpen a project's domain model

    • Open source
    • 326K GitHub stars
  10. A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

    • Open source
    • 326K GitHub stars
  11. Implement a piece of work based on a spec or set of tickets.

    • Open source
    • 326K GitHub stars
  12. Implement the result of /to-spec and /to-tickets in code.

    • Open source
    • 326K GitHub stars
  13. Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

    • Open source
    • 326K GitHub stars
  14. Build a throwaway prototype to answer a design question

    • Open source
    • 326K GitHub stars
  15. Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo

    • Open source
    • 326K GitHub stars
  16. Conduct a retrospective on a coding session.

    • Open source
    • 326K GitHub stars
  17. Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout

    • Open source
    • 326K GitHub stars
  18. Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

    • Open source
    • 41.3K GitHub stars
  19. Review pull requests for repository fit, meaningful value, trustworthy provenance, differentiation, and maintainability in awesome-copilot.

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  20. Create or register a canvas extension in the awesome-copilot repository

    • Open source
    • 41.3K GitHub stars
  21. Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  22. Help the user pick, write, or apply an AgentRC policy

    • Open source
    • 41.3K GitHub stars
  23. Use this skill when the user shares ad campaign performance data and asks what to cut, scale, or test

    • Open source
    • 41.3K GitHub stars
    • Marketing and SEO
  24. Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.

    • Open source
    • 41.3K GitHub stars
  25. Build, debug, package, and document Adobe Illustrator integrations: CEP extension panels, C++ SDK plug-ins (.aip), the coming UXP plugins, M

    • Open source
    • 41.3K GitHub stars
  26. Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX)

    • Open source
    • 41.3K GitHub stars
  27. Design AI agent architectures through requirements discovery, or audit and diagnose architectural flaws in existing agents

    • Open source
    • 41.3K GitHub stars
  28. Patterns and techniques for adding governance, safety, and trust controls to AI agent systems

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  29. Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks

    • Open source
    • 41.3K GitHub stars
    • Security