What problem does it solve? AI-generated frontend code tends to converge on generic, recognizable aesthetics—default fonts, gradient text, side-stripe cards, and templated layouts. This Skill enforces a structured design process with explicit anti-pattern bans and project-specific design context so interfaces look intentionally designed rather than machine-generated. ## Core Features & Use Cases - Design Context Setup (teach mode): Scans the codebase, asks targeted UX questions, and writes a persistent Design Context file (.impeccable.md) capturing audience, brand personality, and aesthetic direction. - Guided Feature Building (craft mode): Shapes a design brief, loads relevant reference guides (typography, color, spatial, motion, interaction, responsive, UX writing), builds the feature, and iterates visually against quality checks. - Design System Extraction (extract mode): Identifies repeated components, hard-coded values, and patterns used 3+ times, then consolidates them into reusable components and design tokens. - Use Case: When asked to build a landing page or dashboard, the Skill first gathers brand context, selects non-default fonts via a structured procedure, builds an OKLCH-based palette, and applies explicit bans on AI design tells like gradient text and border-left accent stripes. ## Quick Start Ask the assistant to run /impeccable teach to set up design context for the project, then use /impeccable craft followed by a feature description to build a polished interface.