What problem does it solve? AI coding agents produce inconsistent output when they lack the right context: they hallucinate APIs, ignore project conventions, and degrade over long sessions. This Skill provides a structured method for curating what the agent sees, when it sees it, and how it is structured. ## 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 the Brain Dump, Selective Include, and Hierarchical Summary patterns for loading focused context per task. - Confusion Management: Defines explicit patterns for surfacing conflicting specs, missing requirements, and ambiguity instead of guessing. - Use Case: When starting a new project for AI-assisted development, use this Skill to write a CLAUDE.md covering tech stack, commands, conventions, and boundaries, then load only task-relevant files per session. ## Quick Start Set up a CLAUDE.md rules file for my project covering the tech stack, build commands, code conventions, and boundaries so the agent follows our patterns.
