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.

by antfu 5.8k GitHub stars MIT Updated Jun 23, 2026
antfu-design skill by antfu
antfu-design — Design skill by antfu

Overview

antfu-design is an open-source design skill for Claude Code and compatible agents, published by antfu. Its author describes it as: “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 p…”. The project has 5.8k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/antfu/skills ~/.claude/skills/antfu-design`.

What antfu-design does

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.

Best for

What’s inside

The SKILL.md for antfu-design is organised into these sections:

  • Core Rules
  • Starter shortcuts
  • Core References
  • Best Practices
  • Features
  • Advanced

Installation

Add antfu-design to your agent with:

git clone https://github.com/antfu/skills ~/.claude/skills/antfu-design

Review a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.

Supported agents

Neither the skill nor its repository names a specific agent. It uses the SKILL.md format, which several agents can load — check the repository for any agent-specific requirements.

License

antfu-design is published under the MIT license.

Strengths

  • Clear MIT license — safe to read and adapt within its terms
  • Ships in antfu/skills, an established project with 5,770 GitHub stars

Author

antfu 19 skills in the catalog · GitHub profile ↗
View skills

Topics

Need a skill like this, tailored to your team?Build a custom skill →

Frequently asked questions

What does antfu-design 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.
How do I install antfu-design?
Run git clone https://github.com/antfu/skills ~/.claude/skills/antfu-design in your agent, then reload your skills. Review the source at https://github.com/antfu/skills before installing.
Is antfu-design free to use?
Yes. antfu-design is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
Where does antfu-design come from?
antfu-design ships inside antfu/skills, a repository that contains 19 catalogued skills in total. The repository's 5,770 GitHub stars apply to that whole collection, not to this skill on its own.

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

Claude CodeCursorGemini CLI
3.9k GitHub stars MIT Updated Jul 29, 2026 Free

将任何小说蒸馏为可玩的游戏 · Turn any novel/story into a playable game — a 7-skill adaptation pipeline for Claude Code, Codex & Kimi Code(k3)

Claude CodeCodex
433 GitHub stars MIT Updated Jul 30, 2026 Free

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".

Gemini CLI
5.5k GitHub stars No license Updated Aug 18, 2026 Free

小省导购员多智能体数字人口播带货视频生成系统,以"小省导购员"为核心人设,打造专业购物助手+数字人口播带货视频一体化服务。涵盖五大智能体(小省导购员、带货脚本师、数字人口播生成师、带货画面设计师、音画合成师),产出"数字人口播+带货画面+字幕音效"的成品视频,适配抖音、快手等短视频平台,支持淘宝、京东、拼多多、唯品会等全平台商品信息,具备知识库自动存取能力。

Gemini CLI
5.5k GitHub stars No license Updated Aug 18, 2026 Free

小省导购员数字人带货版即梦视频提示词生成系统,基于四大智能体协同(提示词生成师、质量管控师、知识库运维师、跨环节适配师),按照"主体+运动+场景+(镜头语言+光影+氛围)"公式输出中英文双版提示词,适配5s短视频。确保人物一致性、视觉连贯性、情绪连贯性,支持知识库智能复用和跨工具适配(Suno音乐、AI绘画),为数字人带货视频提供高质量提示词生成服务。

Gemini CLI
5.5k GitHub stars No license Updated Aug 18, 2026 Free