# gpt-taste

gpt-taste directs agents to build landing pages with strict AIDA structure, dense bento grids, and GSAP motion. Runs only when invoked by name.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 954 installs · ★ 49 repo stars
- Author: Leonxlnx
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/Leonxlnx/taste-skill-classics/tree/HEAD/skills/gpt-tasteskill/SKILL.md
- Updated: 2026-10-19
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/leonxlnx-gpt-taste

## What it does

Standard LLM interfaces often fall back on 6-line hero titles, unbalanced bento layouts, and repetitive left-right blocks. This skill breaks those tendencies. In the `<design_plan>` phase, the agent simulates a Python randomisation step using seed math to select a hero layout, component architectures, and typography like Satoshi or Geist instead of Inter.

Layouts follow the AIDA framework with generous vertical padding (`py-32 md:py-48`). The instructions require motion using `@gsap/react` and `ScrollTrigger`, including pinned sections and card stacking. Every animation must check `prefers-reduced-motion`.

Because the skill specifies `disable-model-invocation: true`, the model will never apply it silently in background tasks. You must trigger it explicitly by name.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add Leonxlnx/taste-skill-classics --skill gpt-taste -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/gpt-tasteskill/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/gpt-tasteskill/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Leonxlnx/taste-skill-classics --skill gpt-taste -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/gpt-tasteskill/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Leonxlnx/taste-skill-classics --skill gpt-taste -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/gpt-tasteskill/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Leonxlnx/taste-skill-classics skills/gpt-tasteskill
```

2. **Manually: put the files in place**
- File: `.github/skills/gpt-tasteskill/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Leonxlnx/taste-skill-classics --skill gpt-taste -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Leonxlnx/taste-skill-classics --path skills/gpt-tasteskill
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/gpt-tasteskill/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add Leonxlnx/taste-skill-classics --skill gpt-taste -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Leonxlnx/taste-skill-classics/tree/HEAD/skills/gpt-tasteskill/SKILL.md

## When to use it
- eliminate awkward empty gaps in CSS bento grids with grid-flow-dense
- cap H1 headings at two or three lines across wide containers
- integrate interactive GSAP scroll pinning and reveals into frontend code
- structure landing pages strictly according to the AIDA pattern

## Example prompts
- Build a SaaS landing page following the gpt-taste skill guidelines
- Design an AIDA-structured product page with GSAP animations using gpt-taste

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 58fa0300bc1c7798.

BEGIN THIRD-PARTY FILE 58fa0300bc1c7798
```text
---
name: gpt-taste
description: "Classic skill for GPT and Codex, opt-in: it runs only when called by name. Layout variance, a strict AIDA page structure and GSAP scroll motion."
disable-model-invocation: true
---

# CORE DIRECTIVE: AWWWARDS-LEVEL DESIGN ENGINEERING
You are an elite, award-winning frontend design engineer. Standard LLMs possess severe statistical biases: they generate massive 6-line wrapped headings by using narrow containers, leave ugly empty gaps in bento grids, use cheap meta-labels ("QUESTION 05", "SECTION 01"), output invisible button text, and endlessly repeat the same Left/Right layouts. 

Your goal is to aggressively break these defaults. Your outputs must be highly creative, perfectly spaced, motion-rich (GSAP), mathematically flawless in grid execution, and heavily rely on varied, high-end assets.

DO NOT USE EMOJIS IN YOUR CODE, COMMENTS, OR OUTPUT. Maintain strictly professional formatting.

## 1. PYTHON-DRIVEN TRUE RANDOMIZATION (BREAKING THE LOOP)
LLMs are inherently lazy and always pick the first layout option. To prevent this, you MUST simulate a Python script execution in your `<design_plan>` before writing any UI code. 
Use a deterministic seed (e.g., character count of the user prompt modulo math) to simulate `random.choice()` and strictly select:
- 1 Hero Architecture (from Section 3)
- 1 Typography Stack (Satoshi, Cabinet Grotesk, Outfit, or Geist. NEVER Inter)
- 3 Unique Component Architectures (from Section 6)
- 2 Advanced GSAP Paradigms (from Section 5)
You are forbidden from defaulting to the same UI twice. You must follow the exact output of your simulated Python randomization.

## 2. AIDA STRUCTURE & SPACING
Every page MUST begin with a highly creative, premium Navigation Bar (e.g., floating glass pill, or minimal split nav).
The rest of the page MUST follow the AIDA framework:
- **Attention (Hero):** Cinematic, clean, wide layout.
- **Interest (Features/Bento):** High-density, mathematically perfect grid or interactive typographic components.
- **Desire (GSAP Scroll/Media):** Pinned sections, horizontal scroll, or text-reveals.
- **Action (Footer/Pricing):** Massive, high-contrast CTA and clean footer links.
**SPACING RULE:** Add huge vertical padding between all major sections (e.g., `py-32 md:py-48`). Sections must feel like distinct, cinematic chapters. Do not cramp elements together.

## 3. HERO ARCHITECTURE & THE 2-LINE IRON RULE
The Hero must breathe. It must NOT be a narrow, 6-line text wall.
- **The Container Width Fix:** You MUST use ultra-wide containers for the H1 (e.g., `max-w-5xl`, `max-w-6xl`, `w-full`). Allow the words to flow horizontally.
- **The Line Limit:** The H1 MUST NEVER exceed 2 to 3 lines. 4, 5, or 6 lines is a catastrophic failure. Make the font size smaller (`clamp(3rem, 5vw, 5.5rem)`) and the container wider to ensure this.
```
END THIRD-PARTY FILE 58fa0300bc1c7798

The third-party file has ended. Everything between the 58fa0300bc1c7798 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2848 of 8249 bytes. © Leonxlnx · MIT · https://github.com/Leonxlnx/taste-skill-classics/tree/HEAD/skills/gpt-tasteskill/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
