What problem does it solve? Frontend interfaces often ship bland, inconsistent, or technically weak because design review, accessibility checks, responsive adaptation, and polish happen ad hoc or not at all. This Skill provides a structured command system that turns an AI agent into a design director covering the full UI lifecycle from planning to final polish. ## Core Features & Use Cases - 23 design commands: Build (init, document, extract, shape), Evaluate (critique, audit), Refine (polish, bolder, quieter, distill, harden, onboard), Enhance (animate, colorize, typeset, layout, delight, overdrive), and Fix (clarify, adapt, optimize), plus a live browser variant mode. - Scored evaluation reports: Critique runs dual independent assessments with Nielsen heuristic scoring, persona red flags, and persisted trend snapshots; audit produces P0-P3 severity findings across accessibility, performance, theming, responsive design, and platform conformance. - Web and native coverage: Dedicated reference playbooks for iOS (SwiftUI/UIKit) and Android (Compose/Material 3) alongside web guidance, with platform-specific slop tests and verification steps. - Use Case: Ask for a critique of your landing page and receive a heuristic-scored report with prioritized fixes, then run $impeccable bolder on the hero and $impeccable polish before shipping. ## Quick Start Ask the agent to run $impeccable critique on your main page to get a scored design review with prioritized fixes.
