What problem does it solve? LLM-generated frontend code tends to look templated and generic, with default purple gradients, centered heroes, and repetitive card layouts. This Skill forces the agent to read the brief first, infer the right design direction, and ship interfaces that avoid recognizable AI design clichés. ## 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 services. - Design System Mapping: Selects official packages like Fluent UI, Carbon, Material 3, GOV.UK Frontend, or shadcn/ui when the brief matches a real system, instead of hand-rolling CSS. - Pre-Flight Audits: Enforces hard rules on hero layout, eyebrow restraint, CTA contrast, palette consistency, and section-layout diversity before shipping. - Use Case: Ask for a redesign of a premium cookware brand landing page and receive a React/Tailwind implementation with a deliberate non-default palette, real image assets, and a layout that passes the anti-slop checklist. ## Quick Start Redesign my SaaS landing page so it looks like a deliberate Linear-style design instead of a generic AI template.
