What problem does it solve? AI assistants start every session without knowledge of your project's design direction, leading to inconsistent UI decisions. This Skill runs a one-time setup that captures your brand, users, and aesthetic preferences and persists them for all future sessions. ## Core Features & Use Cases - Codebase Exploration: Scans README, package.json, components, brand assets, and CSS variables to infer existing design patterns before asking questions. - Targeted UX Questioning: Asks only about users, brand personality, aesthetic direction, and accessibility needs that cannot be inferred from the code. - Persistent Design Context: Writes a structured Design Context section (users, brand personality, aesthetic direction, design principles) into CLAUDE.md, updating it without duplication. - Use Case: A developer starting a new web app runs this once so every subsequent AI-assisted design task follows the same established brand and accessibility guidelines. ## Quick Start Ask the AI to run the teach-impeccable setup to establish design guidelines for this project.