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 3,301–3,330 of 3,352

  1. Use when deciding between two approaches and you need a structured tradeoff comparison

    • Open source
    • 14 GitHub stars
  2. Use when you want to browse available skills or find the right pipeline for a workflow

    • Open source
    • 14 GitHub stars
  3. Use when prior output is too verbose and needs condensing

    • Open source
    • 14 GitHub stars
  4. Use when you have a goal but don't know which skill fits

    • Open source
    • 14 GitHub stars
  5. Use when prior findings are too sparse for action

    • Open source
    • 14 GitHub stars
  6. Use when you need to remove irrelevant items from a collection

    • Open source
    • 14 GitHub stars
  7. Use when you need to research a topic before analyzing it

    • Open source
    • 14 GitHub stars
  8. Use when multiple agents or skills produced separate findings that need combining into one list

    • Open source
    • 14 GitHub stars
  9. Use when you have items to execute and need to know the right order

    • Open source
    • 14 GitHub stars
  10. Use when you have items and need to know which matter most

    • Open source
    • 14 GitHub stars
  11. Use when you've decided on an approach and need to see the structure before implementing

    • Open source
    • 14 GitHub stars
  12. Use when items need reformatting without changing the collection (e.g., as ticket titles, test cases, or for a different audience)

    • Open source
    • 14 GitHub stars
  13. Use when prior findings contain claims that need fact-checking against code, docs, or reality

    • Open source
    • 14 GitHub stars
  14. Use when you need to research, analyze, compare, plan, or structure thinking and aren't sure which primitive to reach for

    • Open source
    • 14 GitHub stars
  15. Use when an agent's performance is uneven and you want systematic improvement

    • Open source
    • 14 GitHub stars
  16. Use when starting a project, forming a team for long-horizon work, or upgrading from ad-hoc agent dispatch

    • Open source
    • 14 GitHub stars
  17. Use when learnings feel bloated, before sprints, after /retro, or when rules need a health check

    • Open source
    • 14 GitHub stars
  18. Use after /curate or /retro when learnings have accumulated and you want to graduate durable patterns to project rules

    • Open source
    • 14 GitHub stars
  19. Use at the end of a work session, after completing an epic, or when you want to capture what worked and what didn't

    • Open source
    • 14 GitHub stars
  20. Use when you have an assembled team and work ready to dispatch

    • Open source
    • 14 GitHub stars
  21. Use when a team exists but current status is unknown — backlog changed, context switch happened, or session just started

    • Open source
    • 14 GitHub stars
  22. Use when you have a goal and want the team to plan it collaboratively — not explore (blossom) or brainstorm (meeting)

    • Open source
    • 14 GitHub stars
  23. Use after sprints, before major work phases, or on regular cadence

    • Open source
    • 14 GitHub stars
  24. Use when you're unsure what to work on next

    • Open source
    • 14 GitHub stars
  25. Use when a goal is vague and you need to explore before planning

    • Open source
    • 14 GitHub stars
  26. Use when starting a new project or adding Claude Code support to an existing one

    • Open source
    • 14 GitHub stars
  27. Use when you've found a defect and need to file it

    • Open source
    • 14 GitHub stars
  28. Use after /diagnose-agent when you have a struggle profile and need training challenges

    • Open source
    • 14 GitHub stars
  29. Use after /challenge-gen when challenges are ready to execute

    • Open source
    • 14 GitHub stars
  30. Use when torn between architectural approaches or when you suspect hidden trade-offs

    • Open source
    • 14 GitHub stars