What problem does it solve? LLM-generated frontend code tends to repeat the same layouts, produce cramped sections, leave gaps in bento grids, and use cheap meta-labels. This Skill enforces a rigorous design system so generated UI code is varied, well-spaced, and motion-rich. ## 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 look alike. - Strict Layout Rules: Enforces AIDA page structure, 2-3 line hero headings via wide containers, gapless bento grids with grid-flow-dense, and large section spacing. - Advanced GSAP Motion: Requires ScrollTrigger pinning, scrubbing text reveals, image scale/fade scroll, and card stacking in every page. - Use Case: Ask for a landing page for a SaaS product and receive a complete 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 design rules and review the design plan before the code.