What problem does it solve? AI coding agents produce inconsistent output, hallucinate APIs, and ignore project conventions when they receive too little context or lose focus when flooded with too much. This Skill provides a structured methodology for curating exactly what an agent sees at each stage of a session. ## Core Features & Use Cases - Five-Level Context Hierarchy: Organizes context from persistent rules files (CLAUDE.md, .cursorrules, AGENTS.md) down through specs, source files, error output, and conversation history. - Context Packing Strategies: Provides templates like the Brain Dump, Selective Include, and Hierarchical Summary for loading focused, task-relevant context under 2,000 lines. - Confusion Management: Defines explicit patterns for surfacing spec conflicts, missing requirements, and inline planning instead of silently guessing. - Use Case: When starting a new feature in a large codebase, use this Skill to write a rules file covering tech stack, commands, and conventions, then load only the relevant spec section and source files so the agent follows existing patterns instead of inventing new ones. ## Quick Start Ask the agent to create a CLAUDE.md rules file for your project covering the tech stack, build commands, code conventions, and boundaries before starting the next coding task.
