What problem does it solve? LLM-generated frontend code tends to produce repetitive layouts, narrow headings that wrap into many lines, gappy bento grids, invisible button text, and static pages without motion. This Skill enforces a strict design engineering process that eliminates these default failure patterns. ## Core Features & Use Cases - Deterministic Layout Randomization: Simulates a Python RNG step to select hero architectures, typography stacks, components, and GSAP paradigms so no two pages repeat the same layout. - Structural Rules: Enforces AIDA page structure, 2-3 line hero headings via wide containers, gapless bento grids using grid-flow-dense, and large section spacing. - Advanced Motion: Requires real GSAP ScrollTrigger implementations including pinning, scrubbing text reveals, card stacking, and image scale/fade effects. - Use Case: Ask for a SaaS landing page and receive a React/Tailwind page with a cinematic hero, dense bento feature grid, pinned scroll sections, and a pre-flight design plan verifying all constraints. ## 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 React UI code.