What problem does it solve? AI coding agents produce inconsistent or hallucinated output when they lack the right project context, and they lose focus when flooded with irrelevant information. This Skill provides a systematic method for curating what an agent sees — rules files, specs, source files, and error output — so output follows project conventions instead of inventing APIs. ## Core Features & Use Cases - Context Hierarchy Framework: Structures context into five levels from persistent rules files (CLAUDE.md, .cursorrules, AGENTS.md) down to transient conversation history, with templates for each level. - Context Packing Strategies: Provides the Brain Dump, Selective Include, and Hierarchical Summary patterns for loading exactly the right files per task. - Confusion Management: Defines explicit patterns for surfacing spec conflicts and missing requirements instead of silently guessing, plus an inline planning pattern for multi-step tasks. - Use Case: When an agent keeps ignoring your project's naming conventions and inventing nonexistent utility functions, use this Skill to write a rules file covering tech stack, commands, conventions, and boundaries, then load only task-relevant source 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.
