What problem does it solve? LLM-generated frontend pages often suffer from repetitive layouts, narrow containers causing 6-line wrapped headings, empty gaps in bento grids, invisible button text, and static interfaces. This Skill enforces strict design engineering rules to produce varied, motion-rich, mathematically correct UI code. ## Core Features & Use Cases - Deterministic Layout Randomization: Simulates Python-driven random selection of hero architectures, typography stacks, components, and GSAP paradigms to prevent repetitive outputs. - Strict Layout Rules: Enforces wide H1 containers (2-3 line limit), gapless bento grids via grid-flow-dense, AIDA page structure, and massive section spacing. - Advanced GSAP Motion: Implements scroll pinning, scrubbing text reveals, card stacking, and image scale/fade effects with hover physics. - 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 GSAP scroll sections, and a pre-flight design plan verifying all constraints. ## Quick Start Ask the agent to build a landing page for your product using the gpt-taste skill and it will output a verified design plan followed by the full UI code.
