What problem does it solve? LLM-generated frontend code tends to look templated and generic, repeating the same purple gradients, centered heroes, and card grids. This Skill forces the agent to read the brief first, infer the right design direction, and apply disciplined layout, typography, color, and motion rules so the output does not look like default AI slop. ## 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. - 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: Selects official packages (Fluent, Material, Carbon, Polaris, shadcn/ui, Tailwind v4) when the brief matches a real system, and gives honest implementation guidance for aesthetics like glassmorphism, bento, and brutalism. - Pre-Flight Layout Discipline: Enforces hard rules on hero sizing, eyebrow restraint, CTA contrast, bento rhythm, zigzag caps, and palette bans to catch templated output before shipping. - Use Case: Ask for a redesign of a premium cookware landing page and receive a React/Tailwind implementation with a deliberate non-default palette, asymmetric hero, real image assets, and a passed pre-flight audit. ## Quick Start Redesign my landing page using the taste-skill so it looks intentionally designed rather than templated.
