B End Design System logo

B End Design System

Community
Ludi-Herry
b-end-design-system

B端工业级设计系统与组件规范执行Skill。将资深UI/UX设计系统、组件选型否定判据(avoidWhen/doNot)、弹窗抽屉模态解耦、六大业务页面模板骨架、0.5px微边框与光学同心圆角转化为可执行的AI生成与审查约束。用于B端页面设计、组件搭建、代码审查与高保真原型还原。

Overview

PublisherLudi-Herry
Repositoryb-end-design-system-skill
Skill nameb-end-design-system
Stars
21
Forks
1
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 Ludi-Herry on GitHub. Read the source before you install it.

Installation

Install the B End Design System 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/Ludi-Herry/b-end-design-system-skill/tree/main
  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/Ludi-Herry/b-end-design-system-skill.git \
  .claude/skills/b-end-design-system
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable B End Design System 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 B End Design System 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 B End Design System 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.

B端设计系统与组件规范 AI 执行引擎 (Ludi Design System Skill)

本 Skill 是面向 AI 编程助手(Agent、Claude Code、Cursor、Windsurf、Codex 等)的可执行设计系统指令层。它彻底终结“AI 拼装页面毫无设计感、组件乱堆、弹窗抽屉滥用、色彩失控”的行业通病,将资深设计师的决策直觉转化为确定性的工程生成约束。


核心执行工作流 (Standard Workflow)

每当接收到任何 B 端界面生成、修改或审查需求时,按以下六步顺序执行:

[步骤 1: 需求解构] ──► 抽取实体角色、核心对象、操作频次与生命周期状态
        │
[步骤 2: 模板匹配] ──► 从六大页面骨架中唯一确定页面形态 (references/05)
        │
[步骤 3: 布局骨架] ──► 搭建 PageHeader -> FilterPanel -> DataSection -> BulkActionBar
        │
[步骤 4: 选型判据] ──► 执行 7 大否定判据,确定 Modal vs Drawer vs Page (references/03 & 06)
        │
[步骤 5: 原子约束] ──► 坚守 Button 唯一主操作、Badge 80% 浅底深字、0.5px 微边框 (references/01 & 02)
        │
[步骤 6: 闭环走查] ──► 运行 15 项设计系统硬门禁与五态检查 (references/07)

必须遵守的三大底层硬红线 (Non-Negotiable Redlines)

  1. 绝对禁止粗黑边框与机器居中:

    • 分割线与卡片边框优先采用 0.5px 精细微边框(如 border: 1px solid rgba(226, 232, 240, 0.7))。
    • 外层与内层元素必须满足同心圆角几何法则:$R_{outer} = R_{inner} + Padding$。
    • 图标+文字按钮做光学重心微调,模态弹窗垂直位置固定于视口 38.2% 黄金分割位。
  2. 操作区与业务状态严肃性:

    • 主操作唯一:一个独立操作区域(页头、表格工具栏、弹窗底栏)最多只能有 1 个 Primary 主按钮。
    • 审批与责任二选一中立:“审批通过”与“驳回”均采用次级按钮样式,严禁用视觉色差诱导用户。
    • Badge 80% 浅底深字黄金法则:严禁无业务语义的彩虹乱配色;严禁用深色刺眼底色;必须带明确业务文案。
  3. 浮层防丢失与破坏性阻力:

    • 弹窗防手滑丢失:含录入表单的 Dialog/Modal 必须显式设置 maskClosable={false}。
    • 模态 ≠ 阻断:查看详情优先使用侧边抽屉 (Drawer) 或同页展开,保留列表背景上下文;需要独立协同分享时使用独立整页;避免无脑使用居中阻断弹窗。
    • 高危操作阻力:删除、清空、扣费必须使用 ConfirmDialog,标题中立交代对象,描述交代不可逆后果,按钮采用明确动宾文案(如“彻底删除”)。

深度参考规范库导航 (References Index)

遇到具体设计决策时,精准查阅 references/ 目录下的专门手册:

  • 基石与视觉法则:01-design-tokens-and-foundations.md
    • 色彩语义四层分级、0.5px 微边框配方、同心圆角几何计算、阴影防 overflow 裁切公式。
  • 基础原子组件:02-primitive-components.md
    • Button 五层视觉阶梯、主操作判定五步法、Badge 业务映射表、Radio/Switch/Select 否定判据。
  • 浮层与反馈系统:03-overlays-dialog-drawer.md
    • 模态与阻断解耦、Modal vs Drawer 选型决策树、三档推荐尺寸与三分屏高度、从列表进入详情四大判据。
  • 复合组件与数据结构:04-composite-components.md
    • DataGrid 表格列三向对齐、FilterPanel 三态、DescriptionGrid 四层区隔、BulkActionBar、五态覆盖法。
  • 六大页面模板骨架:05-page-templates-and-archetypes.md
    • 列表页 5 种形态、表单页 4 级复杂度、详情页 3 种模式、看板 KPI 约束、设置页即时保存判据。
  • 组件选型 7 大否定判据与反模式:06-component-priority-and-anti-patterns.md
    • 量级/频次/时长/重要性/语义/结构错配的退出机制、40+ 条高频避坑红线。
  • 交付前自查硬清单:07-design-system-audit-checklist.md
    • 15 项视觉与交互门禁走查表。

开箱即用实战模板 (Templates)

生成真实代码时,可直接参考或复制 templates/ 目录中的标准工程代码:

  • templates/list-page-template.tsx:标准查询表格 + 批量浮条 + 抽屉轻编辑 + 确认删除弹窗。
  • templates/form-page-template.tsx:Top-aligned 标签置顶 + 卡片语义分组 + 离开防丢脏检查。
  • templates/detail-page-template.tsx:DetailHeader + DescriptionGrid + Tabs 辅助页签 + 审计时间线。
  • templates/dashboard-page-template.tsx:问候语 + 4个核心 KPI 趋势卡片 + 轻量原生柱状图 + 快捷直通。

自动化校验脚本 (Lint Script)

代码生成完成后,可随时执行 Python 走查脚本自检:

bash
python scripts/audit-design-rules.py path/to/your/code

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 B End Design System AI skill do?

B端工业级设计系统与组件规范执行Skill。将资深UI/UX设计系统、组件选型否定判据(avoidWhen/doNot)、弹窗抽屉模态解耦、六大业务页面模板骨架、0.5px微边框与光学同心圆角转化为可执行的AI生成与审查约束。用于B端页面设计、组件搭建、代码审查与高保真原型还原。

Why use B End Design System on TypingMind?

Because you install it once and use it with any model. B End Design System 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 B End Design System in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Ludi-Herry/b-end-design-system-skill/tree/main. 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 B End Design System?

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 B End Design System?

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

Is the B End Design System AI skill free?

Yes. It is published on GitHub by Ludi-Herry 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 👇