What problem does it solve? Frontend interfaces often ship bland, inconsistent, or technically weak because design work lacks a structured process. This Skill gives an AI agent a complete design-director workflow: it loads project context (PRODUCT.md, DESIGN.md), routes requests to 20+ specialized commands, and enforces a measurable craft floor covering contrast, spacing, typography, motion, and platform conformance. ## Core Features & Use Cases - Command-based design operations: Build (init, document, extract, shape), Evaluate (critique, audit), Refine (polish, bolder, quieter, distill, harden, onboard), Enhance (animate, colorize, typeset, layout, delight, overdrive), Fix (clarify, adapt, optimize), and Iterate (live, generate) commands each backed by a dedicated reference playbook. - Dual-agent design critique: Runs an independent design review and a deterministic detector scan as isolated sub-agents, then synthesizes a scored report using Nielsen's 10 heuristics, cognitive-load checks, and persona red flags, persisted to .impeccable/critique/ for trend tracking. - Web and native platform support: Separate references for iOS (SwiftUI/UIKit) and Android (Compose/Material 3) enforce platform conventions, safe-area insets, touch targets, and slop tests, with adb-based screenshot verification. - Use Case: Ask the agent to audit a dashboard page; it scores accessibility, performance, theming, responsive design, and implementation integrity out of 20, lists P0-P3 findings, and recommends the exact follow-up commands to fix them. ## Quick Start Ask the agent to run the impeccable audit command on your main page or component to get a scored quality report with prioritized fixes.