Skip to content

Instruction-only agent skills

2,929 instruction-only agent skills, out of 3,419 agent skills listed. Popular ones include Rea analysis optimization, Rea changelog update and Rea ci tests audit. These skills contain instructions and reference files but no scripts, so they run no code of their own. Each one lists the tools it asks for and how to install it in Claude Code, Codex, Cursor and other agents.

Showing 2,851–2,880 of 2,889

  1. Use when prior findings contain claims that need fact-checking against code, docs, or reality

    • Open source
    • 14 GitHub stars
  2. 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
  3. Use when an agent's performance is uneven and you want systematic improvement

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

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

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

    • Open source
    • 14 GitHub stars
  7. 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
  8. Use when you have an assembled team and work ready to dispatch

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

    • Open source
    • 14 GitHub stars
  10. 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
  11. Use after sprints, before major work phases, or on regular cadence

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

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

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

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

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

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

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

    • Open source
    • 14 GitHub stars
  19. Use when the backlog feels unwieldy — after a blossom run, before a sprint, or when you suspect duplicates or stale tasks

    • Open source
    • 14 GitHub stars
  20. Use when code is ready to ship and you want a structured deployment with readiness checks and rollback criteria

    • Open source
    • 14 GitHub stars
  21. Use when an agent's performance is uneven and you want to understand where it excels or struggles

    • Open source
    • 14 GitHub stars
  22. Use when a term is ambiguous or project-specific and needs a canonical definition

    • Open source
    • 14 GitHub stars
  23. Use after major skill edits or when definitions feel inconsistent

    • Open source
    • 14 GitHub stars
  24. Use when you have a plan document and want autonomous implementation until it's done

    • Open source
    • 14 GitHub stars
  25. Use when reviewing a skill/agent/rule and you need to understand why it looks the way it does

    • Open source
    • 14 GitHub stars
  26. Use after a human jam session to turn agreements into code

    • Open source
    • 14 GitHub stars
  27. Use when you need deep understanding of a focused area — not broad exploration

    • Open source
    • 14 GitHub stars
  28. Capture the orchestrator's mental model for a structured session transition

    • Open source
    • 14 GitHub stars
  29. Use after parallel bounded-context implementation to verify contracts still hold

    • Open source
    • 14 GitHub stars
  30. Use when you need multiple perspectives on a topic — brainstorming, requirements clarification, or pressure-testing an idea before committin

    • Open source
    • 14 GitHub stars