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 1,201–1,230 of 1,400

  1. Claude Code artifact schemas: plugin.json, frontmatter, hooks, settings, tools.

    • Open source
    • 155 GitHub stars
  2. Codex CLI artifact schemas: config.toml, .codex-plugin, skills, hooks, AGENTS.md.

    • Open source
    • 155 GitHub stars
  3. Multi-agent workflow patterns: parallel dispatch, pipelines, QC gates, retries.

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

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

    • Open source
    • 155 GitHub stars
  6. 100-point NL artifact rubric: penalty tables per artifact type, calibration cases.

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

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

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

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

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

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

    • Open source
    • 155 GitHub stars
  13. How to write .claude/rules/ files: golden format, enforceability, budget, scope.

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

    • Open source
    • 155 GitHub stars
  15. Capture what this conversation worked out into DocBrain, so the whole organization can find it later and DocBrain can tell when it stops bei

    • Open source
    • 33 GitHub stars
  16. This skill should be used when the user asks about 'wt', 'worktree', 'worktrees', 'wt create', 'wt checkout', 'wt list', 'wt remove', 'wt pr

    • Open source
    • 64 GitHub stars
  17. Use this skill to generate well-branded interfaces and assets for Honeycomb (shared AI agent memory, a Legion Code × Activeloop product), ei

    • Open source
    • 118 GitHub stars
  18. 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
  19. Honeycomb persistent shared memory for the OpenClaw harness — auto-capture and recall across sessions via the local Honeycomb daemon.

    • Open source
    • 118 GitHub stars
  20. Help users safely install and use DigestSEO mcp-geo for measured AI-search brand visibility, citations, competitive comparisons, and evidenc

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

    • Open source
    • 111 GitHub stars
  22. Run the full OpenTrace knowledge-graph pipeline over a folder or repo — index, clustering, highlight surfacing, and the markdown / graphml /

    • Open source
    • 111 GitHub stars
  23. Use when the user wants to check, understand, or harden the security of their Mac, or asks whether their laptop is secure and what to fix

    • Open source
    • 82 GitHub stars
  24. Audit PHP engine deserialization surface (unserialize, session decoders, WDDX, phar metadata, custom ce->unserialize handlers, Serializable

    • Open source
    • 85 GitHub stars
  25. Solve coding, debugging, research, analysis, planning, and other agentic work with the smallest verified solution, adaptive effort, minimal

    • Open source
    • 73 GitHub stars
  26. Process academic PDFs into structured Obsidian literature notes and 9-node critical-thinking canvases

    • Open source
    • 66 GitHub stars
  27. OCPP protocol reference for EV charging infrastructure development

    • Open source
    • 32 GitHub stars
  28. This skill should be used when a PDF made with bidi2pdf (CLI, Ruby API or bidi2pdf-rails) is blank, half empty, unstyled, missing images or

    • Open source
    • 58 GitHub stars
  29. This skill should be used when pages of a web site or app need screenshots for a design, UX or accessibility review - at phone and desktop w

    • Open source
    • 58 GitHub stars
  30. This skill should be used when a PDF needs more than one render call - waiting for an element, clicking something open, running a script, sw

    • Open source
    • 58 GitHub stars