$ show addyosmani/agent-skills
The agent-skills repository provides a framework for enhancing AI coding agents with structured engineering workflows called 'skills'. Each skill encodes senior engineer best practices across the software development lifecycle (Define → Plan → Build → Verify → Review → Ship) through opinionated, process-driven guidelines. Skills are invoked automatically based on context or via slash commands and integrate with multiple AI agent tools (Claude Code, Gemini CLI, Antigravity, Codex, etc.) through tool-specific adapters. The system includes a meta-skill for dynamic skill routing, reusable agent personas for specialized tasks, and validation infrastructure to ensure consistency and prevent drift. It is designed to prevent agents from skipping critical steps by mandating concrete evidence (tests, build output) rather than relying on subjective assessments.
The LLM identified 3 files worth highlighting for reuse:
A self-contained Node.js script that validates the structure of skill files (SKILL.md) by checking for required YAML frontmatter and sections (Overview, When to Use, Process, Common Rationalizations, Red Flags, Verification). It ensures consistency across all skills and prevents drift in skill anatomy, making it reusable in any project that adopts a similar skill-based framework.
A bash hook that prevents AI agents from modifying code marked with SIMPLIFY-IGNORE comments during code simplification tasks. It demonstrates a non-obvious pattern for protecting critical code sections from unintended agent modifications, and can be extracted as a standalone hook mechanism for any AI agent extensibility system.
A markdown file defining a reusable AI agent persona for code review, structuring the review along five axes (correctness, readability, architecture, security, performance). This prompt template encapsulates expert knowledge in a portable format and can be used in any AI agent system to define specialized reviewer roles without modification.