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.

Showing 2,071–2,100 of 3,289

  1. Identify the assumptions the current thinking relies on.

    • Open source
    • 120 GitHub stars
  2. Identify meaningful directions for exploring the current thinking.

    • Open source
    • 120 GitHub stars
  3. Find strong counterarguments, counterexamples, or failure cases for the current thinking.

    • Open source
    • 120 GitHub stars
  4. Create a resumable checkpoint of our current thinking.

    • Open source
    • 120 GitHub stars
  5. Ask the single most important clarification question before answering.

    • Open source
    • 120 GitHub stars
  6. Compare competing ideas or interpretations in the current thinking.

    • Open source
    • 120 GitHub stars
  7. Reduce the current thinking to its smallest useful representation.

    • Open source
    • 120 GitHub stars
  8. Turn my request into a clear delegation for a capable agent.

    • Open source
    • 120 GitHub stars
  9. Identify how our thinking changed over the conversation.

    • Open source
    • 120 GitHub stars
  10. Use this skill to generate well-branded interfaces and assets for Honeycomb (shared AI agent memory, a Legion Code × Activeloop product), ei

    • Open source
    • 118 GitHub stars
    • Design and media
  11. Use before starting non-trivial work that Honeycomb may already have prior context for (a past decision, a stated convention, where somethin

    • Open source
    • 118 GitHub stars
    • Knowledge and memory
  12. Honeycomb persistent shared memory for the OpenClaw harness — auto-capture and recall across sessions via the local Honeycomb daemon.

    • Open source
    • 118 GitHub stars
  13. Guide for using the dhub CLI — the AI skill manager for data science agents

    • Open source
    • 116 GitHub stars
  14. Guide for creating effective skills for Claude Code agents

    • Open source
    • 116 GitHub stars
  15. Z.AI CLI providing: - Vision: image/video analysis, OCR, UI-to-code, error diagnosis (GLM-4.6V) - Search: real-time web search with domain/r

    • Open source
    • 111 GitHub stars
    • Files and documents
  16. Explore code structure, architecture, files, directories, and component relationships using the OpenTrace knowledge graph

    • Open source
    • 111 GitHub stars
  17. Run the full OpenTrace knowledge-graph pipeline over a folder or repo — index, clustering, highlight surfacing, and the markdown / graphml /

    • Open source
    • 111 GitHub stars
    • Files and documents
  18. Build, package, and verify DesktopManager NuGet, PowerShell module, and CLI/MCP artefacts through the repo-standard PowerForge entrypoints

    • Open source
    • 108 GitHub stars
  19. Operate and validate Windows desktop state through DesktopManager using MCP first and CLI second

    • Open source
    • 108 GitHub stars
  20. Inspect Windows desktop applications and verify requested UI workflows with DesktopManager MCP, screenshots, and window or control evidence

    • Open source
    • 108 GitHub stars
  21. Distill a top-level principle into knowledge/rules.md

    • Open source
    • 107 GitHub stars
  22. Enforces coding best practices: deep-read before modify, LSP-first navigation, TDD red-green-refactor, minimal changes, self-review, verific

    • Open source
    • 107 GitHub stars
  23. Fetch current library/framework documentation via Context7

    • Open source
    • 107 GitHub stars
    • Databases
  24. Systematic debugging: reproduce → hypothesize → verify → fix

    • Open source
    • 107 GitHub stars
  25. Branch completion workflow: verify tests → present 4 options (merge/PR/keep/discard) → execute → cleanup worktree

    • Open source
    • 107 GitHub stars
  26. Capture knowledge into episodes.md

    • Open source
    • 107 GitHub stars
  27. Generate professional PDF documents with correct CJK (Chinese/Japanese/Korean) rendering

    • Open source
    • 107 GitHub stars
    • Files and documents
  28. Full plan lifecycle: deep understanding → write plan with TDD checklist → parallel review → Ralph Loop execution

    • Open source
    • 107 GitHub stars
  29. Multi-level research: built-in knowledge → web search → Tavily deep research API

    • Open source
    • 107 GitHub stars
    • Web search and scraping