What problem does it solve? AI coding agents produce poor output when given too little context (hallucinated APIs, ignored conventions) or too much context (lost focus, degraded attention). This Skill provides a structured methodology for deliberately managing what an agent sees, when it sees it, and how it is structured across a session. ## Core Features & Use Cases - Five-Level Context Hierarchy: Organizes context from persistent rules files (CLAUDE.md, .cursorrules, AGENTS.md) down to transient conversation history, with templates for each level. - Context Budget Management: Defines a 75% capacity trimming threshold, prioritization tables for what to cut versus protect, and compression strategies to prevent abrupt quality drops in long sessions. - Confusion Management Patterns: Provides explicit formats for surfacing spec conflicts, missing requirements, and inline plans instead of silently guessing. - Use Case: When starting a new project for AI-assisted development, use this Skill to write a rules file covering tech stack, commands, conventions, and boundaries so every subsequent agent session follows project patterns instead of inventing them. ## Quick Start Ask the agent to set up a context rules file and context loading strategy for your project using the context-engineering skill.
