Optimizes and manages CLAUDE.md and AGENTS.md files to streamline AI coding agent behavior and project context.
This skill provides a standardized framework for managing AI agent instruction files like CLAUDE.md and AGENTS.md. It implements advanced patterns such as progressive disclosure and minimal root files to prevent token bloat while ensuring Claude has exactly the context it needs for specific tasks. Whether you are initializing a new project, refactoring a 'ball of mud' instruction file, or syncing multi-tool configurations in a monorepo, this skill ensures your AI interactions remain efficient, accurate, and scalable by describing capabilities rather than fragile file paths.
Características Principales
01Automated creation and initialization of CLAUDE.md and AGENTS.md files
02Implementation of progressive disclosure patterns for multi-layered documentation
03Synchronization tools to keep multiple AI agent configuration files in sync
04Monorepo support with nested package-level instruction strategies
050 GitHub stars
06Audit and refactor workflows to eliminate instruction bloat and redundant rules
Casos de Uso
01Setting up a new repository with standardized AI agent guidelines and build commands
02Managing complex monorepos where different packages require unique context without duplicating global rules
03Cleaning up a massive CLAUDE.md file that has become too expensive or confusing for the agent
