What problem does it solve? LLMs repeatedly produce generic frontend designs: narrow containers causing 6-line wrapped headings, gappy bento grids, cheap meta-labels, invisible button text, and identical left/right layouts. This Skill enforces a rigorous design engineering workflow that breaks these statistical defaults. ## Core Features & Use Cases - Deterministic Layout Randomization: Simulates Python RNG selection of hero architectures, typography stacks (Satoshi, Cabinet Grotesk, Outfit, Geist), and component arsenals so no two pages look alike. - Advanced GSAP Motion: Implements ScrollTrigger pinning, scrubbing text reveals, image scale/fade scroll effects, and card stacking with real @gsap/react code. - Structural Enforcement: Mandates AIDA page structure, gapless bento grids via grid-flow-dense, 2-3 line hero headings with wide containers, and a pre-flight design_plan verification block. - Use Case: Ask for a landing page for a SaaS product and receive a cinematic, motion-rich Next.js page with verified grid math, high-contrast CTAs, and zero banned meta-labels. ## Quick Start Ask the AI to build a landing page for your product using the gpt-taste skill and it will output a verified design plan followed by the full animated React code.