What problem does it solve? LLMs tend to produce repetitive, generic frontend layouts with narrow containers, multi-line wrapped headings, empty grid cells, and static interfaces. This Skill enforces strict design rules so generated React/Tailwind pages achieve editorial, award-site quality with varied layouts and rich motion. ## Core Features & Use Cases - Deterministic Layout Randomization: Simulates a Python RNG seeded by prompt length to select hero architectures, typography stacks, components, and GSAP paradigms, preventing repeated layouts. - Structural Enforcement: Mandates AIDA page flow, 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 patterns including pinning, scrubbing text reveals, card stacking, and image scale/fade effects. - Use Case: Ask for a landing page for a SaaS product and receive a complete React component with a cinematic hero, dense bento feature grid, pinned scroll gallery, and high-contrast CTA footer. ## Quick Start Use the gpt-taste skill to build a landing page for my photography portfolio with a cinematic hero and scroll animations.