论文图表助手 logo

论文图表助手

Community
laborany
论文图表助手

智能图表生成助手,支持流程图、架构图、时序图等专业图表创建。 触发场景: (1) 用户需要创建流程图、架构图、时序图等 (2) 用户需要论文配图、技术文档插图 (3) 用户询问"帮我画个图"、"画个流程图"、"做个架构图" 支持: 论文配图、技术文档、演示汇报、教学材料等场景

Overview

Publisherlaborany
Repositorylaborany
Skill name论文图表助手
Stars
84
Forks
10
Bundled files
9
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.

  • 9 bundled files

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

  • Open source

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

Installation

Install the 论文图表助手 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/laborany/laborany.git /tmp/laborany
mkdir -p .claude/skills
cp -r /tmp/laborany/skills/diagram .claude/skills/laborany-5
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 论文图表助手 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 论文图表助手 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 论文图表助手 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.

Diagram 智能图表助手

核心原则

  1. 五阶段工作流: 需求理解 → 结构规划 → 设计构思 → 生成图表 → 迭代修改
  2. 增量修改优先: 只修改需要修改的部分,保留原图表完整性
  3. 主动澄清需求: 不确定时先问,不要猜测用户意图
  4. 等待用户回答: 使用 AskUserQuestion 后必须停止等待,绝对禁止自己假设答案继续执行

技术方案

静态 HTML + CDN

生成独立的 HTML 文件,内嵌 React 18 + Tailwind CSS 4 + html2canvas:

  • 零依赖,只需浏览器
  • 跨平台,Windows/Mac/Linux 通用
  • 一键导出 PNG

任务识别与路由

支持的图表类型

类型英文适用场景
流程图Flowchart算法步骤、业务流程、���策逻辑
架构图Architecture系统设计、模块关系、技术栈
时序图SequenceAPI 调用、消息传递、交互流程
类图Class面向对象设计、数据模型
思维导图Mindmap概念整理、知识结构

五阶段工作流

阶段一:需求理解

在开始任何操作前,必须:

1. 识别任务类型

  • 流程图 / 架构图 / 时序图 / 类图 / 思维导图 / 自定义

2. 收集素材

  • 读取用户提供的文档 (PDF/DOCX/MD)
  • 分析用户上传的图片
  • 整理关键信息点

3. 主动澄清不明确的需求

重要: 当需求不够明确时,必须使用 AskUserQuestion 工具询问用户,并等待用户回答后才能继续禁止: 自己假设用户的回答然后继续执行。

对于创建图表任务,如果用户没有明确指定,必须询问:

使用 AskUserQuestion 工具询问以下问题:

问题1: 图表类型是什么?
- 选项: 流程图 / 架构图 / 时序图 / 其他

问题2: 图表用途?
- 选项: 论文配图 / 技术文档 / 演示汇报 / 其他

问题3: 视觉风格偏好?
- 选项: 学术简约(黑白)/ 商务专业(蓝色系)/ 彩色活泼 / 极简现代

调用 AskUserQuestion 后,必须停止并等待用户回答。绝对不能自己假设答案继续执行。

阶段二:结构规划

1. 生成图表结构大纲

markdown
## 图表大纲

### 图表类型: [类型]

### 节点列表:
1. [节点类型]: [内容]
2. [节点类型]: [内容]
...

### 连接关系:
- 1 → 2
- 2 → 3 (条件标签)
...

2. 等待用户确认

使用 AskUserQuestion 工具询问:

问题: 大纲是否符合您的预期?
- 选项: 确认,开始设计 / 需要调整大纲 / 添加更多内容

等待用户回答后再继续。

阶段三:设计构思

1. 选择/应用主题

可用预设主题:

  • academic - 学术主题(黑白配色,简洁风格)
  • corporate - 商务主题(蓝色配色,专业风格)
  • colorful - 彩色主题(多彩配色,活泼风格)
  • minimal - 极简主题(灰度配色,极简风格)

2. 规划视觉呈现

确定:

  • 节点样式(圆角、阴影、边框)
  • 连线样式(颜色、粗细、箭头)
  • 字体大小与间距
  • 整体布局方向(水平/垂直)

阶段四:生成图表

1. 生成 HTML 文件

参考 references/react-components.mdtemplates/ 目录下的模板。

2. 保存文件

保存到用户工作目录的 figures/ 文件夹:

figures/
└── {描述性名称}.html

3. 告知用户

图表已生成���

文件位置: figures/{name}.html

请用浏览器打开此文件预览,点击"导出 PNG"按钮可下载图片。

⚠️ 注意:由于应用内限制,PNG 导出功能需要在 Chrome/Edge 浏览器中打开 HTML 文件才能使用。

阶段五:迭代修改

1. 接收用户反馈

2. 定位修改位置

  • 使用节点编号
  • 使用节点内容
  • 使用元素类型(标题/节点/连线)

3. 增量更新

直接修改 HTML 文件中的 React 组件代码。

4. 生成修改摘要

markdown
## 修改摘要

本次修改共涉及 N 处变更:

1. [节点/位置]: [原内容] → [新内容]
2. [样式]: [调整说明]

5. 询问后续需求

使用 AskUserQuestion 工具询问:

问题: 接下来您想?
- 选项: 继续修改其他部分 / 调整刚才的修改 / 确认完成

等待用户回答后再继续。


参考文档

文档路径内容
React 组件references/react-components.md节点、连线组件
Tailwind 样式references/tailwind-styles.md主题、样式类
设计原则references/design-principles.md论文图表规范
工作流指南WORKFLOW.md多轮修改详细流程

模板文件

模板路径用途
流程图templates/flowchart.html算法、业务流程
架构图templates/architecture.html系统设计
时序图templates/sequence.htmlAPI 调用、消息传递
类图templates/class.html面向对象设计
思维导图templates/mindmap.html概念整理、知识结构

素材处理

PDF 文档处理

当用户提供 PDF 文档时:

  1. 读取文档:使用 Read 工具读取 PDF 内容
  2. 提取信息:识别关键信息点(标题、步骤、流程、关系)
  3. 整理结构:将信息整理为图表结构大纲
  4. 确认理解:使用 AskUserQuestion 确认提取的信息是否准确

图片物料处理

当用户提供图片参考时:

  1. 查看图片:使用 Read 工具查看图片内容
  2. 分析结构:识别图片中的图表类型、节点、连接关系
  3. 提取元素:提取可复用的设计元素(颜色、布局、风格)
  4. 生成新图:基于分析结果生成新的图表

处理原则

  • 不盲目复制:理解素材意图,而非机械复制
  • 主动确认:提取信息后必须与用户确认
  • 增量整合:多个素材时,逐步整合信息

输出约定

  • 目录: 用户工作目录下的 figures/
  • 命名: {描述性名称}.html
  • 示例: figures/login-flow.html, figures/system-arch.html

HTML 文件结构

html
<!DOCTYPE html>
<html lang="zh-CN">
<head>
  <meta charset="UTF-8">
  <title>图表标题</title>
  <!-- CDN 依赖 -->
  <script src="https://cdn.tailwindcss.com"></script>
  <script src="https://unpkg.com/react@18/umd/react.production.min.js"></script>
  <script src="https://unpkg.com/react-dom@18/umd/react-dom.production.min.js"></script>
  <script src="https://unpkg.com/html2canvas@1.4.1/dist/html2canvas.min.js"></script>
  <script src="https://unpkg.com/@babel/standalone/babel.min.js"></script>
</head>
<body>
  <div id="root"></div>
  <script type="text/babel">
    // React 组件代码
  </script>
</body>
</html>

依赖

无需安装任何依赖,只需要:

  • 现代浏览器(Chrome/Firefox/Edge/Safari)
  • 网络连接(加载 CDN)

Code Style Guidelines

  • Write concise code
  • Avoid verbose variable names and redundant operations
  • 中文注释,ASCII 风格分块
  • 函数短小,只做一件事

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 论文图表助手 AI skill do?

智能图表生成助手,支持流程图、架构图、时序图等专业图表创建。 触发场景: (1) 用户需要创建流程图、架构图、时序图等 (2) 用户需要论文配图、技术文档插图 (3) 用户询问"帮我画个图"、"画个流程图"、"做个架构图" 支持: 论文配图、技术文档、演示汇报、教学材料等场景

Why use 论文图表助手 on TypingMind?

Because you install it once and use it with any model. 论文图表助手 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 论文图表助手 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/laborany/laborany/tree/main/skills/diagram. 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 论文图表助手?

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 论文图表助手?

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

Is the 论文图表助手 AI skill free?

Yes. It is published on GitHub by laborany 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 👇