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.

Showing 2,521–2,550 of 3,419

  1. Synthesize the important ideas in the current thinking into one coherent model.

    • Open source
    • 120 GitHub stars
  2. Reconstruct how our thinking evolved through meaningful phases.

    • Open source
    • 120 GitHub stars
  3. Transfer the current insight to other problems, domains, or situations.

    • Open source
    • 120 GitHub stars
  4. Map what is known, unknown, implicit, or potentially missing about a problem.

    • Open source
    • 120 GitHub stars
  5. Verify the important claims in the current thinking against the available evidence.

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

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

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

    • Open source
    • 107 GitHub stars
  9. 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
  10. Fetch current library/framework documentation via Context7

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

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

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

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

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

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

    • Open source
    • 107 GitHub stars
    • Web search and scraping
  17. Code and plan review with multi-angle dispatch

    • Open source
    • 107 GitHub stars
  18. Agent self-learning: promote recurring episodes to rules, capture complex corrections

    • Open source
    • 107 GitHub stars
  19. Create high-quality, production-ready skills from scratch

    • Open source
    • 107 GitHub stars
  20. Google Stitch design-to-code workflow with design system management

    • Open source
    • 107 GitHub stars
  21. Evidence before claims — run verification commands before any completion/success statement

    • Open source
    • 107 GitHub stars
  22. Extract and summarize YouTube video content via subtitle extraction

    • Open source
    • 107 GitHub stars
    • Design and media
  23. Summarizes a session as a cartoon comic book.

    • Open source
    • 88 GitHub stars
  24. Lists decisions done during the session.

    • Open source
    • 88 GitHub stars
  25. Plain English Expository Prose, with few words.

    • Open source
    • 88 GitHub stars
  26. Locates where a feature, behavior, symbol, or concept is implemented in the codebase.

    • Open source
    • 88 GitHub stars
  27. Build polished product launch videos in Remotion from brief → storyboard → render → multi-agent review → iterate

    • Open source
    • 86 GitHub stars
    • Design and media
  28. YouTube Marketing MCP — 21-command suite for YouTube creators

    • Open source
    • 85 GitHub stars
    • Design and media
  29. Org-agenda-like transient views for ASI skill orchestration via nbb/squint + Emacs hydra

    • Open source
    • 72 GitHub stars
  30. Connect and stream from OpenBCI Cyton/Daisy via USB dongle, including first-time radio channel pairing

    • Open source
    • 72 GitHub stars