What problem does it solve? LLM-generated frontend code tends to repeat the same layouts, produce cramped sections, leave gaps in CSS grids, and use low-contrast buttons. This Skill enforces a strict design system so generated React/Tailwind pages follow editorial typography, gapless bento grids, and scroll-driven GSAP motion. ## Core Features & Use Cases - Deterministic Layout Randomization: Simulates a Python RNG step to select hero architecture, typography stack, components, and GSAP paradigms so no two pages look alike. - AIDA Page Structure: Enforces Navigation, Attention (Hero), Interest (Bento), Desire (GSAP scroll sections), and Action (Footer/CTA) with large vertical spacing. - GSAP Motion Rules: Mandates ScrollTrigger 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 wide 2-line hero, dense bento grid, pinned scroll gallery, and a pre-flight design plan verifying layout math. ## Quick Start Ask the AI to build a landing page for your product using the gpt-taste skill and it will output a design plan followed by the full React UI code.