What problem does it solve? AI-generated frontend code tends to look templated: purple gradients, centered heroes, three equal cards, and generic glassmorphism. This Skill forces the agent to read the brief first, infer the right design direction, and ship interfaces that avoid recognizable LLM defaults. ## Core Features & Use Cases - Brief Inference and Design Read: Analyzes page kind, vibe words, references, audience, and constraints, then declares a one-line design direction before writing 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 services. - Design System Mapping: Selects official packages (Fluent, Material 3, Carbon, Polaris, GOV.UK Frontend, shadcn/ui, Tailwind v4) when the brief matches a real system, and honestly implements aesthetics like bento, brutalism, or glassmorphism when it does not. - Pre-Flight Layout Discipline: Enforces hard rules on hero sizing, eyebrow restraint, CTA contrast, bento cell counts, zigzag caps, and palette consistency before shipping. - Use Case: Ask for a redesign of a premium consumer brand landing page and receive a React/Next.js + Tailwind v4 implementation with a non-default palette, real image assets, and a full audit against the anti-slop checklist. ## Quick Start Redesign my landing page for a premium cookware brand using the design-taste-frontend skill and avoid the usual beige-and-brass AI look.