context-engineering

What problem does it solve? AI coding agents hallucinate APIs, ignore project conventions, and degrade in quality when they receive too little context, too much context, or stale context. This Skill provides a systematic method for curating what the agent sees at each stage of a session. ## Core Features & Use Cases - Five-Level Context Hierarchy: Structures context from persistent rules files (CLAUDE.md, .cursorrules, AGENTS.md) down to per-iteration error output and conversation history. - Context Packing Strategies: Provides templates like the Brain Dump, Selective Include, and Hierarchical Summary for loading only task-relevant files and specs. - Confusion Management: Defines patterns for surfacing spec conflicts, missing requirements, and inline plans instead of silently guessing. - Use Case: When starting a new feature, you create a CLAUDE.md with your 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 this project covering the tech stack, build commands, code conventions, and boundaries before starting the next task.