addyosmani/agent-skills: Trending on GitHub

addyosmani/agent-skills: Trending on GitHub

In the world of software development, AI coding agents have become increasingly popular for their ability to automate repetitive tasks and speed up the development process. However, these agents often default to the shortest path, which can lead to skipping essential steps such as writing specs, testing, and security reviews. This is where Agent Skills come in – a set of production-grade engineering skills for AI coding agents that encode the workflows, quality gates, and best practices used by senior engineers.

What are Agent Skills?

Agent Skills are structured workflows that agents follow to ensure that the same discipline and best practices used by senior engineers are applied to production code. Each skill encodes hard-won engineering judgment, including when to write a spec, what to test, how to review, and when to ship. These skills are not generic prompts, but rather opinionated, process-driven workflows that separate production-quality work from prototype-quality work.

Key Features of Agent Skills

1. Process, not prose: Skills are workflows agents follow, not reference docs they read. Each has steps, checkpoints, and exit criteria.
2. Anti-rationalization: Every skill includes a table of common excuses agents use to skip steps (e.g., "I'll add tests later") with documented counter-arguments.
3. Verification is non-negotiable: Every skill ends with evidence requirements - tests passing, build output, runtime data. "Seems right" is never sufficient.
4. Progressive disclosure: The SKILL.md is the entry point. Supporting references load only when needed, keeping token usage minimal.

Project Structure

The Agent Skills project is organized into the following directories:

• skills/: 23 skills (22 lifecycle + 1 meta)
• agents/: 3 specialist personas
• references/: 4 supplementary checklists
• hooks/: Session lifecycle hooks
• .claude/commands/: 7 slash commands (Claude Code)
• .gemini/commands/: 7 slash commands (Gemini CLI)
• docs/: Setup guides per tool

Why Agent Skills?

AI coding agents default to the shortest path, which often means skipping specs, tests, security reviews, and the practices that make software reliable. Agent Skills gives agents structured workflows that enforce the same discipline senior engineers bring to production code. Each skill encodes hard-won engineering judgment, including when to write a spec, what to test, how to review, and when to ship.

Contributing

Skills should be specific (actionable steps, not vague advice), verifiable (clear exit criteria with evidence requirements), battle-tested (based on real workflows), and minimal (only what's needed to guide the agent). See docs/skill-anatomy.md for the format specification and CONTRIBUTING.md for guidelines.

License

MIT - use these skills in your projects, teams, and tools.

Requirements

1. MINIMUM 800 words - comprehensive coverage
2. Use clear section headings (##) to organize content
3. Write in an engaging, journalistic style
4. Include technical details but make them accessible
5. Provide practical insights and implications
6. Use markdown formatting for structure
7. NO fluff or filler - every sentence should add value
8. Focus on "why this matters" and real-world applications
9. Include specific examples where relevant
10. End with forward-looking thoughts or implications

By following these guidelines and contributing to the Agent Skills project, you can help ensure that AI coding agents are used responsibly and effectively to produce high-quality software.

Source: https://github.com/addyosmani/agent-skills