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 991–1,020 of 2,929

  1. Multi-agent workflow patterns: parallel dispatch, pipelines, QC gates, retries.

    • Open source
    • 155 GitHub stars
  2. NL artifact anti-patterns: vague quantifiers, bare prohibitions, oversized skills.

    • Open source
    • 155 GitHub stars
  3. The 50 NL programming rules (R01-R50) for skills, agents, commands, hooks, prompts.

    • Open source
    • 155 GitHub stars
  4. 100-point NL artifact rubric: penalty tables per artifact type, calibration cases.

    • Open source
    • 155 GitHub stars
  5. Plugin security risks: hooks, scripts, MCP configs, supply chain, prompt injection.

    • Open source
    • 155 GitHub stars
    • Security
  6. NLPM noun/verb registry (R51): pick the canonical term, detect vocabulary drift.

    • Open source
    • 155 GitHub stars
  7. How to write Claude Code agents: example blocks, model choice, least-privilege tools.

    • Open source
    • 155 GitHub stars
  8. How to write Claude Code hooks: events, matchers, blocking vs advisory, paths.

    • Open source
    • 155 GitHub stars
  9. How to design plugins: architecture, artifact choice, manifests, marketplaces.

    • Open source
    • 155 GitHub stars
  10. How to write LLM system prompts: role, structured output, injection resistance.

    • Open source
    • 155 GitHub stars
    • AI models and LLM tooling
  11. How to write .claude/rules/ files: golden format, enforceability, budget, scope.

    • Open source
    • 155 GitHub stars
  12. How to write SKILL.md files that trigger reliably, for any tool (open spec).

    • Open source
    • 155 GitHub stars
  13. Join and operate on tiny.place (the agent-to-agent social network): create a self-custodied wallet, fund it via MoonPay, buy/renew/transfer

    • Open source
    • 146 GitHub stars
  14. Use when an agent or harness needs to drive the full tiny.place network from the command line — register an @handle identity, search the ope

    • Open source
    • 146 GitHub stars
  15. Reduce the current thinking to its smallest useful representation.

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

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

    • Open source
    • 120 GitHub stars
  18. Find a general useful pattern or principle behind the current thinking.

    • Open source
    • 120 GitHub stars
  19. Turn the current response into a clear, immediately executable next action.

    • Open source
    • 120 GitHub stars
  20. Reconnect a drifting discussion to the original intent.

    • Open source
    • 120 GitHub stars
  21. Identify the assumptions the current thinking relies on.

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

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

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

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

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

    • Open source
    • 120 GitHub stars
  27. 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
  28. Honeycomb persistent shared memory for the OpenClaw harness — auto-capture and recall across sessions via the local Honeycomb daemon.

    • Open source
    • 118 GitHub stars
  29. 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
  30. Explore code structure, architecture, files, directories, and component relationships using the OpenTrace knowledge graph

    • Open source
    • 111 GitHub stars