What problem does it solve? LLM-generated frontend code tends to fall back on the same templated aesthetic: purple gradients, centered heroes, three equal feature cards, and Inter on slate. This Skill forces the agent to read the brief first, infer the right design direction, and ship interfaces that do not look machine-generated. ## 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 per brief, with presets for SaaS landings, portfolios, editorial sites, and public-sector services. - Design System Mapping: Routes briefs to official packages (Fluent, Material, Carbon, Polaris, shadcn/ui, Tailwind v4) instead of hand-rolled imitations, with honest handling of aesthetics like glassmorphism and bento. - Anti-Slop Guardrails: Enforces rules against AI-purple defaults, serif overuse, eyebrow spam, zigzag repetition, wrapped CTAs, and low-contrast buttons, plus a mechanical pre-flight check. - Use Case: Ask for a premium consumer landing page and get a split-screen hero with a locked accent palette, real generated imagery, and Motion-based scroll animation instead of a beige-and-brass template. ## Quick Start Redesign my landing page to feel like a Linear-style minimalist SaaS site and apply the taste skill's pre-flight check before shipping.
