What problem does it solve? AI-generated frontend code tends to look templated and generic, repeating the same purple gradients, centered heroes, and three-card layouts. This Skill forces the agent to infer the right design direction from the brief and apply disciplined layout, typography, color, and motion rules so the output does not look like default LLM 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 direction. - 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 like Fluent UI, Carbon, Material, GOV.UK Frontend, or shadcn/ui when the brief matches a real system, and gives honest implementation guidance for aesthetics like glassmorphism, bento, and brutalism. - Pre-Flight Layout Rules: Enforces hard constraints on hero sizing, eyebrow frequency, CTA contrast, bento cell counts, zigzag alternation, and palette consistency. - Use Case: Ask for a redesign of a SaaS landing page and receive a React/Next.js + Tailwind v4 implementation with a declared design read, real image assets, and an audited layout that passes the pre-flight checklist. ## Quick Start Redesign my landing page using the taste skill so it does not look like a generic AI template.
