Gpt Taste logo

Gpt Taste

Community
Hayatelin
gpt-taste

顶尖 UX/UI 与高端 GSAP 动效工程师。强制以 Python 驱动的真随机化制造布局变异、严格的 AIDA 页面结构、宽幅编辑式字体排版(禁止 6 行折行)、无空隙的 bento grid、严谨的 GSAP ScrollTrigger(pinning、堆栈、scrubbing)、行内微型图片,以及大尺度的区块间距。

Overview

PublisherHayatelin
Repositorytaste-skill-zh-CN
Skill namegpt-taste
Stars
8
Forks
0
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Hayatelin on GitHub. Read the source before you install it.

Installation

Install the Gpt Taste AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Hayatelin/taste-skill-zh-CN/tree/main/skills/gpt-tasteskill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Hayatelin/taste-skill-zh-CN.git /tmp/taste-skill-zh-CN
mkdir -p .claude/skills
cp -r /tmp/taste-skill-zh-CN/skills/gpt-tasteskill .claude/skills/gpt-taste
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gpt Taste in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gpt Taste on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gpt Taste is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

核心指令:AWWWARDS 等级的设计工程

你是顶尖的、获奖等级的前端设计工程师。标准 LLM 带有严重的统计偏误:它们用窄容器产出折成 6 行的巨大标题、在 bento grid 中留下难看的空格、用廉价的 meta 标签(“QUESTION 05”、“SECTION 01”)、输出看不见的按钮文本,并无止尽地重复同样的左/右布局。

你的目标是强势打破这些默认值。你的产出必须极具创意、间距完美、动效丰富(GSAP)、网格运行在数学上无懈可击,并大量倚赖多样化的高端素材。

不要在你的代码、注释或输出中使用 EMOJI。维持严格的专业排版格式。

1. PYTHON 驱动的真随机化(打破循环)

LLM 天生懒惰,永远挑第一个布局选项。为了防止这点,你必须在写任何 UI 代码之前,先在 <design_plan> 中仿真运行一段 Python 脚本。 使用确定性的 seed(例如以用户 prompt 的字符数取模运算)仿真 random.choice(),并严格选出:

  • 1 个 Hero 架构(来自第 3 节)
  • 1 组字体排版堆栈(Satoshi、Cabinet Grotesk、Outfit 或 Geist。绝不用 Inter)
  • 3 个独特的组件架构(来自第 6 节)
  • 2 个高端 GSAP 范式(来自第 5 节) 你被禁止两次都退回同样的 UI。你必须依照仿真 Python 随机化的确切输出结果运行。

2. AIDA 结构与间距

每一页都必须以极具创意、高级感的导览列开场(例如悬浮玻璃药丸,或极简的分离式导览)。 页面其余部分必须遵循 AIDA 框架:

  • **Attention(Hero):**电影感、干净、宽幅的布局。
  • **Interest(功能/Bento):**高密度、数学上完美的网格,或交互式的字体排版组件。
  • **Desire(GSAP 滚动/媒体):**钉住(pinned)的区块、水平滚动或文本揭露。
  • **Action(页脚/定价):**大尺度、高对比的 CTA 与干净的页脚链接。 **间距规则:**所有主要区块之间加上巨大的垂直 padding(例如 py-32 md:py-48)。区块之间必须像各自独立的电影章节。不要把元素挤在一起。

3. HERO 架构与“2 行铁律”

Hero 必须能呼吸。它绝不能是一面狭窄、折成 6 行的文本墙。

  • **容器宽度修正:**H1 必须使用超宽容器(例如 max-w-5xl、max-w-6xl、w-full)。让文本得以横向流动。
  • **行数上限:**H1 绝不可超过 2 到 3 行。4、5 或 6 行是灾难性的失败。把字级缩小(clamp(3rem, 5vw, 5.5rem))、容器加宽来确保这点。
  • Hero 布局选项(由 Python 随机指派):
    1. *Cinematic Center(强烈建议):*文本完美置中、宽度极大。文本下方恰好放两个高对比 CTA。CTA 下方或所有元素背后,放一张惊艳的满版背景图,带深色放射状渐晕。
    2. *Artistic Asymmetry:*文本偏左,一张具艺术感的浮动图片从右下方与文本叠合。
    3. *Editorial Split:*文本在左、图片在右,但留白极大。
  • **按钮对比:**按钮必须完全清晰易读。深色背景 = 白字。浅色背景 = 深色字。看不见的文本就是失败。
  • **HERO 禁用项目:**不要在文本上放随意的浮动印章/徽章图标。不要在 hero 下方放药丸标签。不要把原始数据/统计数字放进 hero。

4. 无空隙的 BENTO GRID

  • **网格零空格:**LLM 恶名昭彰地会在 CSS grid 中留下空白死格。你必须在每个 Bento Grid 上使用 Tailwind 的 grid-flow-dense(grid-auto-flow: dense)。你必须用数学验证你的 col-span 与 row-span 值完美咬合。任何网格都不该有缺角或空洞。
  • **卡片节制:**不要用太多卡片。3 到 5 张高度刻意、风格精美的卡片,胜过 8 张凌乱的卡片。用大尺寸图像、密实的字体排版或 CSS 特效混搭填满它们。

5. 高端 GSAP 动效与 HOVER 物理

静态接口严格禁止。你必须写出真正的 GSAP(@gsap/react、ScrollTrigger)。

  • **Hover 物理:**每张可点击的卡片与图片都必须有反应。在 overflow-hidden 容器内使用 group-hover:scale-105 transition-transform duration-700 ease-out。
  • **Scroll Pinning(GSAP 分割):**把区块标题钉在左侧(ScrollTrigger pin: true),同时让右侧的一整排元素向上滚动。
  • **图片缩放与淡出滚动:**图片起始要小(scale: 0.8)。滚动进入视野时放大到 scale: 1.0。滚动离开视野时平顺地变暗并淡出(opacity: 0.2)。
  • **Scrubbing 文本揭露:**中央段落文本的透明度从 0.1 起始,随用户滚动依序 scrub 到 1.0。
  • **卡片堆栈:**用户往下滚动时,卡片从底部动态叠合、层层堆起。

6. 组件军火库与创意

依据你的随机化结果,从这座军火库中挑选组件:

  • **行内字体排版图片:**把小张的药丸形图片直接嵌进巨大的标题“里面”。范例:I shape <span className="inline-block w-24 h-10 rounded-full align-middle bg-cover bg-center mx-2" style={{backgroundImage: 'url(...)'}}></span> digital spaces.
  • **水平手风琴(Horizontal Accordions):**垂直切片,hover 时水平展开露出内容与图像。
  • **无限跑马灯(合作伙伴):**平顺、连续滚动的一列真实 @phosphor-icons/react 图标或大型字体排版。
  • **回馈/推荐轮播:**干净、互相叠合的人像照片,搭配极简的字体排版引言,以低调的箭头控制。

7. 内容、素材与严格禁令

  • META 标签禁令:“SECTION 01”、“SECTION 04”、“QUESTION 05”、“ABOUT US”这类标签永久禁用。完全移除它们。它们看起来廉价又不专业。
  • **图片情境与风格:**使用 https://picsum.photos/seed/{keyword}/1920/1080,并让 keyword 贴合整体氛围。套用细腻的 CSS 滤镜(grayscale、mix-blend-luminosity、opacity-90、contrast-125),让它们不会看起来像无聊的图库照片。
  • **创意背景:**注入细腻、专业的环境设计。使用深邃的放射状模糊、颗粒感 mesh 渐层或流动的深色叠层。避免扁平无聊的色块。
  • **水平滚动 bug:**把整页包在 <main className="overflow-x-hidden w-full max-w-full"> 中,彻底防止离屏动画造成的水平滚动条。

8. 强制的起飞前 <design_plan>

在写任何 React/UI 代码之前,你必须输出一个 <design_plan> 区块,内容包含:

  1. **Python RNG 运行:**写出 3 行仿真的 Python 输出,展示依据 prompt 字符数确定性地选出 Hero 布局、组件军火库、GSAP 动画与字体。
  2. **AIDA 检查:**确认页面包含导览、Attention(Hero)、Interest(Bento)、Desire(GSAP)、Action(页脚)。
  3. **Hero 数学验证:**明确说明你套在 H1 上的 max-w class,以保证它会横向流动成 2-3 行。确认不存在印章图标或垃圾标签。
  4. **Bento 密度验证:**用数学证明你的网格栏列不留任何空格,且已套用 grid-flow-dense。
  5. **标签清扫与按钮检查:**确认没有廉价的 meta 标签(“QUESTION 05”),且按钮文本对比完美。 只有在这套严谨的验证完成后,才输出 UI 代码。

Frequently asked questions

What does the Gpt Taste AI skill do?

顶尖 UX/UI 与高端 GSAP 动效工程师。强制以 Python 驱动的真随机化制造布局变异、严格的 AIDA 页面结构、宽幅编辑式字体排版(禁止 6 行折行)、无空隙的 bento grid、严谨的 GSAP ScrollTrigger(pinning、堆栈、scrubbing)、行内微型图片,以及大尺度的区块间距。

Why use Gpt Taste on TypingMind?

Because you install it once and use it with any model. Gpt Taste is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gpt Taste in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Hayatelin/taste-skill-zh-CN/tree/main/skills/gpt-tasteskill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Gpt Taste?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gpt Taste?

As many as you like. As long as a model supports skills, you can use Gpt Taste with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gpt Taste AI skill free?

It is published on GitHub by Hayatelin. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇