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 1,171–1,200 of 1,400

  1. Use when the user wants an autonomous ML research loop that pressure-tests competing ideas before spending compute — several research subage

    • Open source
    • 183 GitHub stars
  2. Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI

    • Open source
    • 552 GitHub stars
  3. Turn a concept, feature description, blog post, or pitch into a single beautiful, on-brand illustration by matching it to a real unDraw illu

    • Open source
    • 552 GitHub stars
  4. Use whenever a task needs an API key, token, password, or other secret — before asking the user for a value, before writing any .env or hard

    • Open source
    • 87 GitHub stars
  5. Make a showreel-grade product film (landing-page loop, launch video, promo, demo reel, social cut) in code with Remotion, built on the produ

    • Open source
    • 425 GitHub stars
  6. Structured roundtable discussion framework with a truth-seeking moderator who invites representative figures for dialectical debate on any t

    • Open source
    • 297 GitHub stars
  7. Build, package, and verify DesktopManager NuGet, PowerShell module, and CLI/MCP artefacts through the repo-standard PowerForge entrypoints

    • Open source
    • 108 GitHub stars
  8. Operate and validate Windows desktop state through DesktopManager using MCP first and CLI second

    • Open source
    • 108 GitHub stars
  9. Inspect Windows desktop applications and verify requested UI workflows with DesktopManager MCP, screenshots, and window or control evidence

    • Open source
    • 108 GitHub stars
  10. 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
  11. Rebuilds an AI-generated (or any) flat motion design video as clean, editable code: inline SVG shapes animated by one GSAP timeline, seekabl

    • Open source
    • 355 GitHub stars
  12. Universal NL conventions: SKILL.md open spec, AGENTS.md, vague quantifiers, naming.

    • Open source
    • 155 GitHub stars
  13. Antigravity and Gemini CLI artifact schemas: .gemini/ paths, extensions, hooks.

    • Open source
    • 155 GitHub stars
  14. Claude Code artifact schemas: plugin.json, frontmatter, hooks, settings, tools.

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

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

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

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

    • Open source
    • 155 GitHub stars
  19. 100-point NL artifact rubric: penalty tables per artifact type, calibration cases.

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

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

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

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

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

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

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

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

    • Open source
    • 155 GitHub stars
  28. Universal NL conventions: SKILL.md open spec, AGENTS.md, vague quantifiers, naming.

    • Open source
    • 155 GitHub stars
  29. Antigravity and Gemini CLI artifact schemas: .gemini/ paths, extensions, hooks.

    • Open source
    • 155 GitHub stars