Refactors and prunes project context files to maximize model compliance and minimize token waste.
This skill automates the optimization of CLAUDE.md files based on research-backed best practices to prevent instruction degradation. By applying the principle of progressive disclosure, it relocates verbose technical specifications into a dedicated agent_docs directory while maintaining a lean, high-leverage core instruction set (60-150 lines). This ensures Claude Code remains focused on critical project rules and architecture, improving the reliability of implementation tasks and reducing token overhead in every conversation.
Características Principales
01Organizes project context into structured WHAT, WHY, and HOW dimensions
02Implements 'Progressive Disclosure' by migrating detailed specs to an agent_docs/ folder
03Prioritizes critical rules at the top to exploit LLM attention distribution biases
04Prunes instruction count to the high-compliance sweet spot of 60-150 lines
050 GitHub stars
06Identifies and removes redundant style/linting rules better handled by external tools
Casos de Uso
01Refactoring verbose /init output into a focused, high-leverage project context
02Improving rule compliance in projects where the AI has started ignoring instructions
03Organizing complex monorepo documentation for better agent navigation
