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 read the brief first, infer the right design direction, and ship interfaces that avoid recognizable LLM 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 and Pre-Flight Audit: Selects official design systems (Fluent, Material, Carbon, shadcn/ui, Tailwind v4) when applicable, bans AI-tell patterns (default serifs, beige-brass palettes, eyebrow overuse, zigzag repetition), and enforces accessibility contrast checks. - Use Case: Ask the agent to build a landing page for a B2B SaaS product; it declares a Linear-style minimalist read, picks Tailwind v4 with Geist, locks one accent color, and audits the hero, nav, and CTAs against hard layout rules before shipping. ## Quick Start Use the design-taste-frontend skill to build a landing page for my SaaS product targeting technical buyers with a clean minimalist feel.