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 2,761–2,790 of 2,878

  1. Show all scheduled OneBrain entries (skills + CLI commands) with cron/at expressions and installed-on-disk status.

    • Open source
    • 31 GitHub stars
  2. Interactive wizard to schedule a OneBrain skill to run ONCE at a specific datetime, then auto-uninstall

    • Open source
    • 31 GitHub stars
  3. General vault retrieval — answers both "what" and "why" questions across MEMORY.md, memory/, session logs, project trackers, and vault notes

    • Open source
    • 31 GitHub stars
    • Knowledge and memory
  4. Fetch a URL and create a structured summary note saved to the resources folder

    • Open source
    • 31 GitHub stars
  5. Create or update the live task dashboard (TASKS.md) in Obsidian

    • Open source
    • 31 GitHub stars
    • Productivity
  6. Update OneBrain system files from GitHub to the latest version

    • Open source
    • 31 GitHub stars
    • Knowledge and memory
  7. Weekly reflection : review the past week's sessions, surface patterns, and plan ahead

    • Open source
    • 31 GitHub stars
  8. Wrap up and save the current session summary to the session log

    • Open source
    • 31 GitHub stars
  9. Analiza textos aplicando pensamiento crítico — el marco de los 8 elementos del pensamiento y los estándares intelectuales universales de Ric

    • Open source
    • 30 GitHub stars
  10. One-time setup and health check for fable-baton

    • Open source
    • 30 GitHub stars
  11. Forges weak Claude Code prompts into structured, credit-saving, framework-aware prompts

    • Open source
    • 30 GitHub stars
    • AI models and LLM tooling
  12. MANDATORY estimation protocol

    • Open source
    • 28 GitHub stars
  13. MANDATORY planning protocol

    • Open source
    • 28 GitHub stars
    • Productivity
  14. MANDATORY prompt-design protocol

    • Open source
    • 28 GitHub stars
    • AI models and LLM tooling
  15. MANDATORY scoping protocol

    • Open source
    • 28 GitHub stars
  16. Reasoning router — invoke before starting any non-trivial task: designing a system or feature, debugging a failure, architecture decisions,

    • Open source
    • 28 GitHub stars