What problem does it solve? AI-generated interfaces tend to look generic, ship with accessibility and performance defects, and ignore platform conventions. This Skill gives an AI agent a disciplined design workflow so frontend work—landing pages, dashboards, app UI—comes out distinctive, on-brand, and technically sound instead of looking like a template. ## Core Features & Use Cases - Command-driven design workflow: 23 sub-commands organized into Build (craft, shape, init, document, extract), Evaluate (critique, audit), Refine (polish, bolder, quieter, distill, harden, onboard), Enhance (animate, colorize, typeset, layout, delight, overdrive), Fix (clarify, adapt, optimize), and Iterate (live browser-based variant picking). - Register and platform awareness: separates brand surfaces (marketing, landing pages) from product UI (dashboards, tools), and routes native iOS/Android projects to HIG and Material 3 references with platform-specific audit criteria. - Anti-slop enforcement: explicit bans on saturated AI design tells (gradient text, glassmorphism, cream backgrounds, eyebrow kickers, reflex font picks) plus scripted context detection, palette seeding, and a design-issue detector hook. - Use Case: Ask the agent to audit a landing page; it scores accessibility, performance, theming, responsiveness, and anti-patterns out of 20, lists P0–P3 findings, and recommends the exact follow-up commands to fix them. ## Quick Start Ask the agent to run $impeccable critique on your main landing page to get a scored UX review with prioritized fixes.
