What problem does it solve? LLM-generated frontend code tends to fall back on the same templated aesthetic: AI-purple gradients, centered heroes, three equal feature cards, and Inter everywhere. This Skill forces the agent to read the brief first, infer the right design direction, and ship interfaces that look deliberately designed rather than auto-generated. ## Core Features & Use Cases - Brief Inference and Design Read: Analyzes page kind, vibe words, references, audience, and constraints before writing code, then declares a one-line design read to anchor all decisions. - Three-Dial Configuration: Tunes DESIGN_VARIANCE, MOTION_INTENSITY, and VISUAL_DENSITY based on the brief, mapping signals like "minimalist" or "Awwwards" to concrete layout, motion, and density values. - Design System Mapping and Bias Correction: Selects official design systems (Fluent, Material, Carbon, shadcn/ui, Tailwind v4) when appropriate, and enforces anti-slop rules covering typography, color palettes, hero layout discipline, eyebrow restraint, and CTA contrast. - Use Case: A user asks for a premium consumer cookware landing page. The Skill blocks the default beige-and-brass palette, picks an alternative family like Cobalt + Cream, sets dials to 7/6/3, and ships a Tailwind v4 page with real generated imagery and a pre-flight audit. ## Quick Start Redesign my SaaS landing page so it feels Linear-style minimalist and does not look like a generic AI template.
