What problem does it solve? AI-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 ship interfaces that avoid recognizable LLM design defaults. ## 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 (Fluent, Material, Carbon, shadcn/ui, Tailwind v4, Radix) when the brief matches a real system, and gives honest implementation guidance for aesthetics like glassmorphism, bento, and brutalism. - Anti-Slop Rules and Pre-Flight Audit: Enforces typography discipline, color consistency locks, layout diversification, CTA contrast checks, and eyebrow restraint to eliminate common AI design tells. - Use Case: Ask for a redesign of a designer portfolio with an editorial vibe, and the agent declares a design read, picks native CSS with scroll-driven animation and custom typography, then ships an asymmetric layout that passes its pre-flight checklist. ## Quick Start Redesign my landing page with a Linear-style minimalist feel using the design-taste-frontend skill and avoid generic AI design patterns.
