Agent Rules

If you're working with AI coding assistants across a team or maintaining multiple repos, this generates and maintains AGENTS.md files that follow the agents.md convention. It's basically structured onboarding docs for AI, not humans. The skill includes scripts to detect your project stack (Go, PHP, TypeScript, Python), extract commands from build configs and CI files, and generate either thin or verbose documentation with verification built in. The philosophy is pointer-based rather than duplicative, and it won't fabricate anything it can't verify. Useful when you want your AI agents to understand project conventions, build commands, and architecture rules without hunting through README files or guessing at undocumented patterns.

Install to Claude Code

npx -y skills add netresearch/agent-rules-skill --skill agent-rules --agent claude-code