又挖到一个好东西，叫 Taste Skill，GitHub 上已经拿了 20.3k Star。

简单来说，装上它之后，AI 生成的前端界面会好看很多。布局、字体、动效、留白，各方面都有明显提升，整体看起来有高级感。

它提供了好几个设计方向可以选，比如通用高级感、极简风格、粗野主义，还有一个专门用来改造老项目的审计修复技能，适合给已有页面做升级。

另外还有个图片技能挺有意思，可以先让 AI 生成网页或移动端的设计稿，然后再交给编程工具去实现，相当于把设计和开发拆成了两步走。

它还提供了三个可调参数，分别控制布局的实验程度、动画的丰富度和信息密度，可以根据自己的需求灵活调整，不会把你锁死在某一种风格里。

如果你经常用 AI 来构建前端应用，又受够了那种千篇一律的模板页面，可以装一个试试，效果确实不错。

传送门：

Leonxlnx/taste-skill

Source: https://github.com/Leonxlnx/taste-skill

Taste Skill

The Anti-Slop Frontend Framework for AI Agents

Portable Agent Skills that upgrade AI-built interfaces: stronger layout, typography, motion, and spacing instead of boilerplate-looking UIs. This repo also includes image-generation skills for reference boards (web, mobile, brand kits). Pair them with ChatGPT Images or similar generators, then hand the frames to Codex, Cursor, or Claude Code for implementation.

Disclaimer

Taste Skill has no official token, coin, or crypto project. Any token using my name, image, or project is unaffiliated and not endorsed by me.

_{Disclaimer · Install · Skills · Settings · Examples · Sponsor · Research · FAQ · License}

Feedback & Contributions

We would love your feedback. Suggestions and bug reports:

• Open a Pull Request or Issue on GitHub
• DM @lexnlin or @blueemi99
• Email us at [email protected]

Installing

The npx skills add CLI scans the skills/ folder in this repo, so all skills below (code and image-generation) install the same way.

npx skills add https://github.com/Leonxlnx/taste-skill

Install a single skill by its install name (the name: field inside the SKILL frontmatter, not the folder name):

npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend"

You can also copy any SKILL.md into your project or paste it into ChatGPT / Codex conversations.

Updating from the previous version

The default taste-skill (install name design-taste-frontend) is now v2 (experimental), a substantial rewrite of the original v1. If you already have v1 installed, just re-run the install command and you will be upgraded:

npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend"

The install name did not change, so no script updates are needed. The newer SKILL.md replaces the older one in place.

If you depend on the exact behavior of v1 and want to pin to it explicitly:

npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend-v1"

See CHANGELOG.md for the full v1 to v2 diff and the rationale.

Skills

Each skill does one job; you do not need all of them at once. Implementation skills output code. Image-generation skills output reference images only.

The Install name column is the exact value you pass to --skill.

Image generation skills

These produce design images only (no code). Use with ChatGPT Images, Codex image mode, or any agent that generates images.

Which one should I use?

• Start with taste-skill for the safest general default. (Now v2 experimental - see what changed in the CHANGELOG.)
• If you depend on the exact behavior of the original taste-skill, install taste-skill-v1 instead.
• Use gpt-taste when you want the stricter GPT/Codex-oriented rules and motion/layout enforcement.
• Use image-to-code-skill for image → analyze → code website workflows.
• Use redesign-skill to improve an existing codebase instead of greenfield styling.
• Add soft-skill, minimalist-skill, or brutalist-skill when the visual direction is already chosen.
• Add output-skill if the agent keeps truncating output.
• Use imagegen-frontend-web, imagegen-frontend-mobile, or brandkit when the deliverable is images (comps, flows, identity boards), then pass results to your coding agent.

Image-first tip

For image-to-code-skill, state the pipeline in the prompt, e.g.: follow the skill: generate images, then analyze, then code.

ChatGPT Images and Codex

Attach or paste imagegen-frontend-web, imagegen-frontend-mobile, or brandkit and ask for the frames you need, then feed the renders to Codex, Cursor, or Claude Code. Use image-to-code-skill when you want one workflow that both generates references and implements the site in code.

Settings (taste-skill only)

Numbers at the top of the file are 1-10 dials:

• DESIGN_VARIANCE: Layout experimentation (lower: centered/clean · higher: asymmetric/modern).
• MOTION_INTENSITY: Animation depth (lower: hover · higher: scroll/magnetic).
• VISUAL_DENSITY: Information per viewport (lower: spacious · higher: dense dashboards).

Examples

Created with taste-skill:

Support the project

If Taste Skill helps you, consider sponsoring:

Sponsor on GitHub

Current Sponsors

Research

Background writing that shaped these skills lives in research/.

Common Questions

How is this different from other AI design skills?
Multiple specialized variants, adjustable dials in key skills, anti-repetition rules informed by dedicated research. All are framework agnostic across major coding agents.

Does it work with React, Vue, Svelte?
Yes. Rules target design intent, not a single framework API.

What is SKILL.md?
A portable instruction file agents can load automatically; install via npx skills add or by copying into a repo or conversation.

Do image-generation skills install with npx skills add?
Yes. They live under skills/ alongside the code skills so the same CLI discovers them.

License

MIT License · Copyright (c) 2026 Leonxlnx