What problem does it solve? LLMs produce statistically generic frontend code: centered heroes, purple gradients, Inter font, three-column card rows, and missing loading or error states. This Skill enforces engineered design rules so generated interfaces look intentionally designed rather than AI-default. ## Core Features & Use Cases - Bias-Corrected Design Rules: Bans common AI tells such as neon glows, pure black, Inter font, generic names, and 3-column card layouts, replacing them with calibrated typography, color, and layout directives. - Configurable Design Dials: Drives output through three tunable baselines (DESIGN_VARIANCE, MOTION_INTENSITY, VISUAL_DENSITY) that control asymmetry, animation depth, and information density. - Architecture & Performance Guardrails: Enforces React Server Component boundaries, Tailwind v3/v4 version checks, dependency verification against package.json, hardware-accelerated animations, and isolated client components for perpetual motion. - Use Case: Ask for a SaaS dashboard and receive a Bento-grid layout with spring-physics micro-interactions, skeleton loaders, empty states, and mobile-safe responsive fallbacks instead of a generic card page. ## Quick Start Ask the AI to build a React dashboard or landing page and it will apply these design rules, motion specs, and architecture constraints automatically.