gpt-taste

Generates award-level React landing pages with GSAP animations and randomized layout selection.

3|Updated Apr 20, 2026
One-click install
npx skills add https://github.com/langgenius/due-date-hq-jwl --skill gpt-taste-langgenius
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gpt-taste
Source: https://github.com/langgenius/due-date-hq-jwl/tree/main/.claude/skills/gpt-taste
Command: npx skills add https://github.com/langgenius/due-date-hq-jwl --skill gpt-taste-langgenius

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? LLM-generated frontend code tends to repeat the same narrow layouts, produce multi-line wrapped headings, leave gaps in bento grids, and ship static pages without motion. This Skill enforces a rigorous design engineering process that breaks those defaults and produces varied, motion-rich, editorial-quality landing pages. ## Core Features & Use Cases - Deterministic Layout Randomization: Simulates a Python RNG step to select hero architectures, typography stacks, component arsenals, and GSAP paradigms so no two pages look alike. - Strict Layout Rules: Enforces wide H1 containers with a 2-3 line limit, gapless bento grids via grid-flow-dense, massive section spacing, and an AIDA page structure. - Advanced GSAP Motion: Requires real ScrollTrigger implementations including pinning, scrubbing text reveals, card stacking, and image scale/fade scroll effects. - 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 spacing, grid math, and label bans. ## Quick Start Ask the AI to build a landing page for your product and it will output a design plan followed by the full animated React code.

Frequently Asked Questions about gpt-taste

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an animated landing page with GSAP and React?

Describe your product and request a landing page. The Skill outputs a design plan first, then full React code using Tailwind for layout and GSAP ScrollTrigger for pinning, scrubbing text reveals, card stacking, and image scale effects.

How to prevent AI-generated websites from looking repetitive?

This Skill simulates a Python randomization step seeded by the prompt's character count to deterministically pick one hero architecture, one typography stack, three component types, and two GSAP paradigms, forcing varied output each time.

What fonts and libraries does this design workflow use?

Typography is limited to Satoshi, Cabinet Grotesk, Outfit, or Geist, with Inter explicitly banned. Motion uses GSAP with @gsap/react and ScrollTrigger, styling uses Tailwind CSS, and icons come from @phosphor-icons/react.

Why do bento grids have empty gaps and how to fix them?

Gaps appear when col-span and row-span values do not interlock. The fix is applying Tailwind's grid-flow-dense class and mathematically verifying that all spans fill the grid completely, which this Skill enforces in its pre-flight check.

Does this approach work for non-landing-page UI like dashboards?

The rules are optimized for marketing pages following the AIDA structure with heroes, bento grids, and scroll storytelling. Dense application interfaces like dashboards or forms are outside its intended scope.