What problem does it solve? LLM-generated frontend code tends to repeat the same layouts, produce narrow multi-line headings, leave gaps in CSS grids, and ship static pages without motion. This Skill enforces a strict design engineering process that produces varied, motion-rich React landing pages. ## 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. - Structural Enforcement: Mandates AIDA page flow, ultra-wide hero containers capped at 2-3 heading lines, gapless bento grids using grid-flow-dense, and large section spacing. - Advanced Motion: Requires real GSAP ScrollTrigger patterns including pinning, scrubbing text reveals, image scale/fade on scroll, and card stacking. - 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 gallery, and high-contrast CTA footer, preceded by a verifiable design plan. ## Quick Start Use the gpt-taste skill to build a landing page for my AI note-taking app with a cinematic hero and scroll animations.