Product Ui Director logo

Product Ui Director

Community
macistone71-jpg
product-ui-director

何庆丰定制的产品 UI/UX 设计、实现与验收 Skill。凡是新建、改版、评审或迭代 Web、移动端、桌面端界面,设计系统、页面、组件、交互、响应式、可访问性、配色、字体、数据图表或视觉质量时必须使用。覆盖需求简报→设计系统→差异化视觉→代码实现→真实浏览器验收→迭代记录,内置可搜索 UI/UX 数据和项目级设计记忆。

Overview

Publishermacistone71-jpg
Repositoryheqingfeng-product-ui-skill
Skill nameproduct-ui-director
Stars
9
Forks
0
Bundled files
66
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.

  • 66 bundled files

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

  • Open source

    Published by macistone71-jpg on GitHub. Read the source before you install it.

Installation

Install the Product Ui Director 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/macistone71-jpg/heqingfeng-product-ui-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/macistone71-jpg/heqingfeng-product-ui-skill.git \
  .claude/skills/product-ui-director
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Product Ui Director 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 Product Ui Director 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 Product Ui Director 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.

Product UI Director|何庆丰定制版

把“做得好看”改成可复用的产品工程:先理解产品,再建立设计系统;先形成差异,再写代码;最后必须在真实浏览器验收。

必须使用的场景

  • 新产品、页面、落地页、工作台、仪表盘、移动端或桌面端 UI;
  • 修改布局、配色、字体、间距、导航、表单、动效、图表和响应式;
  • 用户说“不专业、太像 AI、信息太乱、移动端崩、交互别扭”;
  • UI 代码评审、上线前验收、竞品视觉分析和设计系统沉淀。

纯后端、数据库、部署或不改变界面体验的任务不加载本 Skill。

不可跳过的原则

  1. 产品先于风格:先确认目标用户、核心任务、使用频率、平台、内容密度和风险,再选风格。
  2. 真实内容先于占位图:不得用虚构指标、虚假评价、无意义 lorem 或装饰性数字冒充产品证据。
  3. 差异化先于模板:禁止无理由使用“AI 紫色渐变 + 三张玻璃卡 + 巨大圆角”的默认 AI 审美。
  4. 一项目一套设计记忆:已有 design-system/<slug>/MASTER.md 时先读,不得静默覆盖。
  5. 功能正确优先:视觉不得破坏业务链路、数据状态、错误恢复、键盘导航和移动端可用性。
  6. 真实验收:不能只看代码宣布完成;必须打开页面、操作核心链路并检查至少 390px 与桌面视口。
  7. 保留来源:本 Skill 基于 MIT 开源项目定制,许可证与上游归属不得删除。

六阶段工作流

0. 读取现场

  • 读取 PRD、README、已有页面、品牌资产、技术栈和最近改动;
  • 检测技术栈,不能硬猜;
  • 查找并读取现有 design-system/**/MASTER.md、页面 override、UI 验收报告;
  • 新产品需要浏览 3–5 个直接或邻近竞品的官方页面,记录结构与交互,不复制视觉皮肤。

1. 建立产品 UI Brief

至少明确:产品任务、受众、平台、首要 CTA、关键信息、风险、内容密度、品牌性格、无障碍要求、支持视口。信息可从项目推断时直接推进,不反复询问。

需要创建项目文档时运行:

bash
python3 scripts/qf_project_init.py --project-root <项目根目录> --project-name "项目名" --product-type "产品类型" --platform web

脚本默认不覆盖已有文件。

2. 生成并持久化设计系统

新项目或系统级改版必须运行:

bash
python3 scripts/search.py "<产品类型 行业 风格约束>" --design-system --persist -p "项目名" --output-dir "<项目根目录>"

可用调节器:--variance 1-10、--motion 1-10、--density 1-10。工作台通常提高 density;内容产品降低 density;motion 只服务状态与因果。

已有 MASTER 时先读;除非用户明确授权,不得 --force。

3. 建立“产品签名”

每个产品至少定义 3 项可识别但不妨碍使用的签名:

  • 一个版式签名(如编辑部网格、制片时间线、纸张式阅读区);
  • 一个信息签名(如质量门禁、证据链、审核状态);
  • 一个交互签名(如排练模式、局部重做、渐进式预览)。

签名必须来自产品机制,不靠随机渐变、过量动效或装饰图形。

针对何庆丰现有产品类型,按需读取 references/heqingfeng-product-patterns.md。

4. 实现与针对性检索

只查询当前问题,不一次加载全部规则:

bash
python3 scripts/search.py "keyboard focus modal" --domain ux
python3 scripts/search.py "dashboard dense filters" --domain style
python3 scripts/search.py "form error recovery" --domain ux
python3 scripts/search.py "responsive card grid" --stack <检测到的技术栈>

查询空结果时只缩窄重试一次;仍为空要明确使用通用规则,不能伪造数据库命中。

实现要求:

  • 使用语义 token,不在组件中散落无意义颜色和间距;
  • 正文移动端默认至少 16px,控件具备可见 label;
  • Web 键盘焦点可见;触控目标按平台规范;
  • 不依赖 hover 完成主任务;
  • 异步流程有加载、成功、错误和恢复;
  • 动画尊重 prefers-reduced-motion;
  • 长中文、长英文、URL、数字和空数据都不破版。

5. 真实浏览器验收

页面可运行时必须使用浏览器完成核心任务。优先调用已安装的 ego-browser Skill:

  1. 桌面视口约 1440px:首屏层级、核心链路、弹窗/表单/导出;
  2. 移动视口 390px:确认 scrollWidth === innerWidth,无水平溢出;
  3. 键盘操作:焦点可见、顺序合理、Esc/返回可恢复;
  4. 状态:空、加载、错误、成功、禁用;
  5. 可读性:对比度、长文本、缩放、减少动效;
  6. 记录实际结果,不把“存在代码”写成“验收通过”。

Web/桌面验收读取 references/quick-reference.md 的 §1–§3;原生/移动端交付前读取 references/pro-rules.md。

可先运行静态预检:

bash
python3 scripts/product_ui_audit.py <项目根目录> --format markdown

静态结果只是风险提示,不能替代浏览器验收。

6. 沉淀迭代记忆

交付时更新:

  • design-system/<slug>/MASTER.md:稳定设计规则;
  • design-system/<slug>/pages/<page>.md:页面差异;
  • design-system/<slug>/DECISIONS.md:重要取舍与原因;
  • design-system/<slug>/UI-ACCEPTANCE.md:视口、任务、状态、缺陷和证据。

只记录真实验证。灰度数据、转化率、采用率未采集时标记“待验证”。

质量优先级

  1. Accessibility:对比、焦点、键盘、语义、替代文本;
  2. Touch & Interaction:目标尺寸、反馈、错误恢复;
  3. Performance:图片尺寸、CLS、字体、主线程;
  4. Product Fit:风格是否匹配产品任务;
  5. Responsive:移动优先、无水平溢出;
  6. Typography & Color:字级、行高、语义颜色;
  7. Motion:只表达因果,可中断、可减少;
  8. Forms & Feedback;9. Navigation;10. Charts。

完整规则按需读取 references/quick-reference.md。

交付硬门禁

以下任一项存在,不得宣布 UI 完成:

  • 主任务无法完成,或按钮只有视觉没有行为;
  • 390px 产生水平滚动;
  • 无来源却展示虚构用户数字、效果指标或评价;
  • 表单没有 label、错误原因或恢复路径;
  • 图标按钮无可访问名称,键盘焦点不可见;
  • 文本/关键控件对比度明显不达标;
  • 弹窗无法关闭,返回破坏状态,固定栏遮挡内容;
  • 只检查了代码,没有运行和操作页面;
  • 新项目没有设计系统,或擅自覆盖已有 MASTER。

本地知识库

本 Skill 保留上游可搜索数据:79 种风格、192 类产品与配色/推理、74 字体组合、119 UX 指南、图标、动效、图表和 22 类技术栈。scripts/search.py 与数据文件来自上游,定制工作流、项目模板和验收工具由本仓库新增。

Bundled files

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

and 6 more files.

Frequently asked questions

What does the Product Ui Director AI skill do?

何庆丰定制的产品 UI/UX 设计、实现与验收 Skill。凡是新建、改版、评审或迭代 Web、移动端、桌面端界面,设计系统、页面、组件、交互、响应式、可访问性、配色、字体、数据图表或视觉质量时必须使用。覆盖需求简报→设计系统→差异化视觉→代码实现→真实浏览器验收→迭代记录,内置可搜索 UI/UX 数据和项目级设计记忆。

Why use Product Ui Director on TypingMind?

Because you install it once and use it with any model. Product Ui Director 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 Product Ui Director in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/macistone71-jpg/heqingfeng-product-ui-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 Product Ui Director?

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 Product Ui Director?

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

Is the Product Ui Director AI skill free?

Yes. It is published on GitHub by macistone71-jpg 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 👇