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 structured method for curating exactly what the 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, copilot-instructions.md) down to per-iteration error output and conversation history. - Context Packing Strategies: Provides the Brain Dump, Selective Include, and Hierarchical Summary patterns for loading task-relevant files, specs, and examples without flooding the agent. - Confusion Management: Defines explicit patterns for surfacing spec-versus-code conflicts and missing requirements instead of silently guessing. - Use Case: When starting a new feature, you load only the relevant spec section, the files to modify, one existing pattern example, and project conventions — keeping context under 2,000 focused lines so the agent follows your codebase style instead of inventing its own. ## Quick Start Ask the agent to create a project rules file covering the tech stack, commands, conventions, and boundaries, then load only the files relevant to the current task.
