What problem does it solve? LLM-generated frontend code tends to look templated: AI-purple gradients, centered heroes, three equal feature cards, and generic glassmorphism. This Skill forces the agent to read the brief first, infer the right design direction, and ship interfaces that avoid these default patterns. ## Core Features & Use Cases - Brief Inference and Design Read: Analyzes page kind, vibe words, references, audience, and constraints, then declares a one-line design read before writing any code. - Three-Dial Configuration: Tunes DESIGN_VARIANCE, MOTION_INTENSITY, and VISUAL_DENSITY based on the brief, with presets for SaaS landings, portfolios, editorial sites, and public-sector pages. - Design System Mapping: Routes briefs to official packages (Fluent, Material 3, Carbon, Polaris, GOV.UK Frontend, shadcn/ui, Tailwind v4) instead of hand-rolled imitations. - Pre-Flight Layout Rules: Enforces hard constraints on hero sizing, eyebrow frequency, CTA contrast, bento cell counts, palette consistency, and zigzag alternation caps. - Use Case: Ask for a premium consumer cookware landing page and get a non-beige palette, asymmetric hero, real generated imagery, and a locked accent color audited across every section. ## Quick Start Use the design-taste-frontend skill to build a landing page for my SaaS product with a Linear-style minimalist feel.