Antfu Design logo

Antfu Design

CommunityPopular
antfu
antfu-design

antfu-style design conventions, broadened. UnoCSS-first, class-based semantic tokens with dual light/dark for tooling and devtools UIs, plus design-read, anti-slop, and micro-interaction polish for landing pages and product surfaces. Use when building or refactoring any interface with UnoCSS.

Overview

Publisherantfu
Repositoryskills
Skill nameantfu-design
Stars
5.9K
Forks
333
Bundled files
13
LicenseMIT
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.

  • 13 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Antfu Design 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.
  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/antfu/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/antfu-design .claude/skills/antfu-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Antfu Design 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 Antfu Design 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 Antfu Design 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.

Use this when building interfaces with UnoCSS in any framework (React, Vue, Svelte, Solid, or plain HTML), from dense devtools panels to landing pages. Read core-design-read first to set the direction, then apply the token system plus the polish and anti-slop rules.

Core Rules

  • Use semantic shortcuts (bg-base, border-base, color-active, btn-action) instead of raw utility chains in markup.
  • Design light and dark mode together. Core tokens must work in both themes.
  • Name z-index layers (z-top-nav, z-panel-content, z-drawer-content). Do not use raw z values in templates.
  • Generate class-based utilities only (class="..."). Avoid Attributify syntax in generated code.
  • Keep icon/status class strings literal so UnoCSS can statically extract them (// @unocss-include when needed).
  • Use font-mono + tabular-nums for technical values (paths, SHAs, counters, timestamps, percentages).
  • For long paths and IDs, truncate visually but keep the full value in title.
  • Read the brief and set the three dials before choosing a look (core-design-read).
  • Borders for dense or structural surfaces, layered shadows for elevated ones (features-micro-interactions).
  • Zero em-dash and en-dash characters in any user-facing text (best-practices-anti-slop).

Starter shortcuts

A minimal semantic core. See core-starter-kit for the full uno.config.ts and base styles.

ts
shortcuts: [
  {
    'color-base': 'color-neutral-800 dark:color-neutral-200',
    'bg-base': 'bg-white dark:bg-#111',
    'bg-secondary': 'bg-#eee dark:bg-#222',
    'border-base': 'border-#8882',

    'bg-active': 'bg-#8881',
    'color-active': 'color-primary-600 dark:color-primary-300',
    'border-active': 'border-primary-600/25 dark:border-primary-400/25',

    'btn-action': 'inline-flex items-center gap-2 rounded border border-base px2 py1 op75 hover:op100 hover:bg-active disabled:pointer-events-none disabled:op30!',
    'op-fade': 'op65 dark:op55',
    'op-mute': 'op30 dark:op25',

    'z-top-nav': 'z-60',
    'z-panel-content': 'z-70',
    'z-drawer-content': 'z-100',
  },
]

Core References

TopicDescriptionReference
Core PrinciplesSemantic tokens, dark mode parity, z-index naming, class-first outputcore-principles
Starter KitCopy-paste UnoCSS starter config and base light/dark stylescore-starter-kit
Tokens and CombosToken families, reusable class combinations, mobile-safe shell tokenscore-tokens-and-combinations
Design Read and DialsRead the brief, declare a design read, set variance/motion/density dialscore-design-read

Best Practices

TopicDescriptionReference
Strict Rules and Pre-FlightDo/don't checklist and the consolidated pre-flightbest-practices-strict-rules
Class over AttributifyWhy generated code uses class utilities, with conversionsbest-practices-class-utilities-over-attributify
Anti-Slop HygieneThe dash ban and the AI-tell forbidden patternsbest-practices-anti-slop
Bias CorrectionTypography, color, layout, and materiality defaults to overridebest-practices-bias-correction

Features

TopicDescriptionReference
Data PresentationPaths, icons, time, date, numbers, badges, buttonsfeatures-data-presentation
Micro-InteractionsRadius, alignment, shadows, animation, numbers, outlines, hit areasfeatures-micro-interactions
Floating Vue OverridesShared Floating Vue setup and popper stylingfeatures-floating-vue-overrides

Advanced

TopicDescriptionReference
Pattern VocabularyNamed UI patterns to recognize and reach foradvanced-pattern-vocabulary
Redesign ProtocolDetect mode, audit first, preserve IA and SEOadvanced-redesign-protocol

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Antfu Design AI skill do?

antfu-style design conventions, broadened. UnoCSS-first, class-based semantic tokens with dual light/dark for tooling and devtools UIs, plus design-read, anti-slop, and micro-interaction polish for landing pages and product surfaces. Use when building or refactoring any interface with UnoCSS.

Why use Antfu Design on TypingMind?

Because you install it once and use it with any model. Antfu Design 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 Antfu Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/antfu/skills/tree/main/skills/antfu-design. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Antfu Design?

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 Antfu Design?

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

Is the Antfu Design AI skill free?

Yes. It is published on GitHub by antfu under the MIT license. 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 👇