Didi Board logo

Didi Board

Community
didixuxu
didi-board

Use when user provides a 口播稿 (spoken script) and wants it converted into an HTML slide presentation with hand-drawn SVG illustrations for screen recording. Trigger on "做板书", "口播稿转板书", "/board", "生成板书", "做背景板", or when user pastes a script and wants visual slides for video recording.

Overview

Publisherdidixuxu
Repositorydidi-skills
Skill namedidi-board
Stars
86
Forks
8
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Didi Board 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/didixuxu/didi-skills/tree/main/didi-board
  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/didixuxu/didi-skills.git /tmp/didi-skills
mkdir -p .claude/skills
cp -r /tmp/didi-skills/didi-board .claude/skills/didi-board
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Didi Board 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 Didi Board 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 Didi Board 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.

口播稿 → 板书 HTML 幻灯片

Overview

将口播稿拆解为 5-8 张幻灯片,生成一个带手绘风格 SVG 插图的 HTML 文件。 录屏时当背景板讲解用。

Input

口播稿文本(中文,通常 800-2000 字)

Output

一个完整的 HTML 文件,保存到 ~/Downloads/[topic]-board.html

Process

dot
digraph board_flow {
    "读取口播稿" [shape=box];
    "拆分逻辑板块" [shape=box];
    "识别每块视觉类型" [shape=box];
    "生成 HTML" [shape=box];
    "保存文件" [shape=box];

    "读取口播稿" -> "拆分逻辑板块";
    "拆分逻辑板块" -> "识别每块视觉类型";
    "识别每块视觉类型" -> "生成 HTML";
    "生成 HTML" -> "保存文件";
}

Step 1: 拆分口播稿为逻辑板块

将口播稿拆成 5-8 个逻辑单元,每个单元 = 1 张 slide。

拆分原则:

  • 每张 slide 只讲一个核心观点
  • 开头/定义类内容独占一张
  • 对比内容独占一张
  • 金句/总结独占一张
  • 不要超过 8 张(录屏节奏太慢)

Step 2: 识别每个板块的视觉类型

口播内容类型视觉模式布局
定义/概念解释类比插图(SVG)text-col + art-col
A vs B 对比左右对比表格 .compare全宽
列举问题/要点卡片网格(2-3列)全宽 grid
流程/步骤流程箭头 .flowtext-col + art-col
时间线/演进时间轴 SVGtext-col + art-col
核心金句/总结.callout 高亮框text-col + art-col

Step 3: 生成 HTML

使用 board-template.html 作为基础模板。关键要素:

字体:Caveat(手写英文) + Noto Sans SC(中文正文) 配色:

  • --ink: #1a1a1a(主色)
  • --accent-red: #c0392b(强调/警告)
  • --accent-blue: #2c5f8a(流程/结构)
  • --accent-green: #2d6a4f(正面/完成)
  • --paper: #faf8f3(背景纸张色)

每张 Slide 结构:

html
<div class="slide" id="s1">
  <div class="slide-num">1 / N</div>
  <div class="slide-title">
    中文标题
    <span class="en">English subtitle</span>
  </div>
  <div class="slide-body">
    <div class="text-col">
      <!-- 文字内容:.point / .callout / .flow / .compare -->
    </div>
    <div class="art-col">
      <!-- 手绘 SVG 插图 -->
    </div>
  </div>
</div>

SVG 插图规范

每张有 art-col 的 slide 都需要一个手绘风格的 SVG。

尺寸:150-180px 宽,200-230px 高 风格要求:

  • 使用 stroke 而非 fill(线条画风格)
  • 圆角矩形 rx="3-4" 模拟手绘
  • 虚线 stroke-dasharray="4,3" 表示关联/传递
  • 文字用 font-family="Caveat, cursive"
  • 颜色只用 CSS 变量中的 4 种
  • 适当使用 emoji 作为标记符号
  • 可以画:方框、圆、箭头、连线、标注

SVG 内容选择:

  • 定义类 → 类比图(如引擎=车、马=挽具)
  • 流程类 → 上下流转图
  • 对比类 → 左右对称图
  • 演进类 → 时间轴

可用组件

要点列表 .point

html
<div class="point">
  <div class="point-marker">①</div>
  <div class="point-text">
    <strong>加粗关键词</strong>带荧光笔效果
    <div class="point-sub">灰色补充说明</div>
  </div>
</div>

高亮框 .callout

html
<div class="callout">核心金句放这里</div>

自带 ★ 装饰和暖纸背景。

流程图 .flow

html
<div class="flow">
  <div class="flow-item">
    <div class="flow-box blue">步骤名</div>
    <div class="flow-label">补充说明</div>
  </div>
  <div style="padding-left:20px; font-size:22px; color:#aaa;">↓</div>
  <!-- 重复 -->
</div>

颜色类:.red .blue .green

对比表格 .compare

html
<div class="compare">
  <div class="compare-header">A 方案</div>
  <div class="compare-header">B 方案</div>
  <div class="compare-cell">A 的特点</div>
  <div class="compare-cell">B 的特点</div>
</div>

标签 .tag

html
<span class="tag red">关键词</span>
<span class="tag blue">分类</span>

完整模板

生成 HTML 时,使用 board-template.html 中的完整 CSS 和 JS。 只需要替换 slides 内容和 total 变量。

IMPORTANT: 参考 @board-template.html 获取完整的 CSS 样式和 JS 导航逻辑。 每次生成时复制完整模板,只替换 <!-- SLIDES GO HERE --> 部分。

Quality Checklist

  • 每张 slide 只有一个核心观点
  • 标题简洁有力(中文 + 英文副标题)
  • SVG 插图与内容相关,不是装饰
  • strong 标签用在真正的关键词上
  • 金句/核心观点用 .callout 框出
  • 总 slide 数在 5-8 张之间
  • HTML 文件可直接浏览器打开使用

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 Didi Board AI skill do?

Use when user provides a 口播稿 (spoken script) and wants it converted into an HTML slide presentation with hand-drawn SVG illustrations for screen recording. Trigger on "做板书", "口播稿转板书", "/board", "生成板书", "做背景板", or when user pastes a script and wants visual slides for video recording.

Why use Didi Board on TypingMind?

Because you install it once and use it with any model. Didi Board 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 Didi Board in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/didixuxu/didi-skills/tree/main/didi-board. 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 Didi Board?

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 Didi Board?

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

Is the Didi Board AI skill free?

It is published on GitHub by didixuxu. Check the repository for licensing terms. 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 👇