Gpt Vis logo

Gpt Vis

Organization
antvis
gpt-vis

推荐并生成合适的数据可视化图表,使用 GPT-Vis 库。支持两种输出模式:(1)语法模式——生成 Syntax 或 JSON 配置;(2)代码模式——生成完整的运行代码。支持 26 种图表类型。

Overview

Publisherantvis
Repositorychart-visualization-skills
Skill namegpt-vis
Stars
494
Forks
38
Bundled files
1
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.

  • 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 antvis on GitHub. Read the source before you install it.

Installation

Install the Gpt Vis 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/antvis/chart-visualization-skills.git /tmp/chart-visualization-skills
mkdir -p .claude/skills
cp -r /tmp/chart-visualization-skills/skills/gpt-vis .claude/skills/gpt-vis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gpt Vis 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 Gpt Vis 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 Gpt Vis 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.

GPT-Vis 图表可视化技能

GPT-Vis 是一个 AI 原生的可视化库,专为 LLM 时代设计。它采用框架无关的架构,支持 26 种图表类型,通过简单自然的语法让 LLM 能够轻松生成高质量的可视化图表。

步骤

  1. 意图识别:根据用户意图和数据特征选择图表类型
  2. 确定输出模式:根据上下文选择语法模式或代码模式
  3. 生成输出:按所选模式生成内容

支持的图表类型

type 值适用场景
line时间序列趋势
area时间序列趋势+总量
column分类数据对比
bar分类对比(标签长)
pie部分占整体比例
scatter两变量关系
dual-axes不同量级数据对比
histogram连续数值频次分布
boxplot数据分布与异常值
violin数据分布密度
radar多维度对比
funnel流程转化率
waterfall累计增减变化
liquid百分比/进度
word-cloud词频展示
venn集合交并关系
treemap层级数据占比
sankey流量流向
flow-diagram流程步骤
mindmap层级知识梳理
indented-tree树节点层级/目录
network-graph实体间关联关系
organization-chart组织层级
fishbone-diagram根因分析
table表格数据展示
summary内容总结

输出模式

模式一:语法模式(Syntax / JSON)

用于 LLM 应用集成场景,生成图表配置供 GPTVis.render() 消费。支持两种格式:

  • Syntax 格式:类 Markdown 缩进语法,适合流式输出(LLM 逐 token 生成时可实时渲染)
  • JSON 格式:标准 JSON 对象,适合结构化 API 调用

两种格式等价,GPTVis.render() 均可直接接受。

模式二:代码模式

用于用户需要可直接运行的完整代码场景。生成包含安装说明和完整代码的输出。

GPTVis API

GPTVis 是库的统一入口类,负责创建、渲染和销毁图表。

构造函数

typescript
new GPTVis(options: VisualizationOptions)

VisualizationOptions:

参数类型必填默认值说明
containerstring | HTMLElementCSS 选择器或 DOM 元素
widthnumber图表宽度(px)
heightnumber图表高度(px)
theme'default' | 'light' | 'dark' | 'academy''light'主题
wrapperbooleanfalse是否显示外层 UI 容器(含标签页、下载、复制等)
localestring'zh-CN'wrapper 内文案语言

方法

render(config: string | object): void

渲染图表。接受两种输入:

  • Syntax 字符串:以 vis [type] 开头的文本,自动解析为配置对象
  • JSON 配置对象:包含 type 字段的对象
  • 纯文本:不以 vis 开头的字符串会被当作 summary 类型渲染

多次调用 render() 会自动销毁前一个图表再渲染新图表。

destroy(): void

销毁当前图表实例,释放资源。

语法模式:JSON 格式

直接输出符合图表 TypeScript 类型的 JSON 对象,GPTVis.render() 可直接消费。

JSON 示例

json
{
  "type": "column",
  "data": [
    { "category": "A产品", "value": 30, "group": "线上" },
    { "category": "B产品", "value": 50, "group": "线上" }
  ],
  "title": "产品销量对比",
  "axisXTitle": "产品",
  "axisYTitle": "销量(万)",
  "stack": true,
  "theme": "academy",
  "style": {
    "palette": ["#5B8FF9", "#61DDAA"]
  }
}

语法模式:Syntax 格式

类 Markdown 缩进语法,支持流式渲染。第一行必须是 vis [type]

语法规则

基本属性key value,每行一个:

title 年度趋势
theme dark

对象数组data 下每项用 - 开头,子字段缩进:

{ data: { time: string; value: number; }[]; }

对应:

data
  - time 2020
    value 100
  - time 2021
    value 120

纯值数组 — 每项用 - 开头:

{ data: number[] }

对应:

data
  - 10
  - 20

含空格的字符串值 — 用引号(单引号或双引号)包裹;不含空格时可省略引号:

categories
  - "North America"
  - '东南 亚'
  - 欧洲

嵌套对象 — 对象名占一行,子属性缩进:

{ style?: { backgroundColor?: string; palette?: string[] } }

对应:

style
  backgroundColor #f0f2f5
  palette
    - #5B8FF9
    - #61DDAA

递归树形children 数组用 - 缩进:

type TreeData = { name: string; children?: TreeData[] };
{ data: TreeData; }

对应:

data
  name 根节点
  children
    - name 子节点A
      children
        - name 孙节点
    - name 子节点B

Syntax 完整示例

vis column
data
  - category A产品
    value 30
    group 线上
  - category B产品
    value 50
    group 线上
title 产品销量对比
axisXTitle 产品
axisYTitle 销量(万)
stack true
theme academy
style
  palette
    - #5B8FF9
    - #61DDAA

Markdown 语法

当输出为 Markdown 格式时,使用 GPT-Vis 作为 fenced code block 的语言标记,内容区写入完整的 Syntax 格式

markdown
```GPT-Vis
vis line
data
  - time 2020
    value 100
```

格式:

```GPT-Vis
<完整的 Syntax 内容,首行 vis <chart-type>>
```

语法规则:

  • 语言标记固定为 GPT-Vis
  • 内容区使用 Syntax 格式规则编写,首行必须包含 vis <chart-type>(完整列表见上方支持的图表类型
  • 代码块会被 Markdown 插件转换为 ,由浏览器端渲染

注意:Markdown 模式下,内容区必须写首行 vis <type>,与纯 Syntax 模式格式一致。

代码模式

根据目标框架生成完整可运行代码。

安装方式

NPM:

bash
npm install @antv/gpt-vis
javascript
import { GPTVis } from '@antv/gpt-vis';

CDN:

html
<script src="https://unpkg.com/@antv/gpt-vis/dist/umd/index.min.js"></script>

CDN 引入后通过 GPTVis.GPTVis 访问主类。

HTML 完整示例

html
<html>
  <head>
    <script src="https://unpkg.com/@antv/gpt-vis/dist/umd/index.min.js"></script>
  </head>
  <body>
    <div id="container"></div>
    <script>
      const gptVis = new GPTVis.GPTVis({
        container: '#container',
        width: 600,
        height: 400,
      });

      gptVis.render(`
vis line
data
  - time 2020
    value 100
  - time 2021
    value 120
title 年度趋势
`);
    </script>
  </body>
</html>

图表类型配置

通用配置

所有图表均包含以下字段,后续各图表类型定义中省略这些字段。各小节标题即为 type 值(如 linecolumn),对应上方图表类型表中的 type 列。

{ type: string; title?: string; theme?: 'default' | 'light' | 'dark' | 'academy'; style?: { backgroundColor?: string; palette?: string[] } }

line / area

{ data: { time: string | number; value: number; group?: string }[]; axisXTitle?: string; axisYTitle?: string; stack?: boolean; style?: { lineWidth?: number } }

stack 仅 area 支持。

column / bar

{ data: { category: string; value: number; group?: string }[]; axisXTitle?: string; axisYTitle?: string; stack?: boolean; group?: boolean }

pie

value 不可使用百分比数字。

{ data: { category: string; value: number }[]; innerRadius?: number }

innerRadius 设为 0.6 变为环图。

scatter

{ data: { x: number; y: number; group?: string }[]; axisXTitle?: string; axisYTitle?: string }

dual-axes

{ categories: string[]; series: { type: 'line' | 'column'; data: number[]; axisYTitle?: string }[]; axisXTitle?: string; style?: { startAtZero?: boolean } }

histogram

{ data: number[]; binNumber?: number; axisXTitle?: string; axisYTitle?: string }

boxplot / violin

同一 category 需多条数据以展示分布。

{ data: { category: string; value: number; group?: string }[]; axisXTitle?: string; axisYTitle?: string; style?: { startAtZero?: boolean } }

radar

{ data: { name: string; value: number; group?: string }[]; align?: boolean }

align: 是否对齐各维度比例尺,默认 false(各轴独立缩放);true 时所有轴共享同一最大值,适合多系列绝对数值对比。

funnel

{ data: { category: string; value: number; }[]; }

waterfall

value 可为负数表示减少。palette 为色板数组,顺序为 [正值色, 负值色, 汇总色]。

{ data: { category: string; value: number }[]; axisXTitle?: string; axisYTitle?: string; style?: { palette?: string[] } }

liquid

percent 范围 0~1。

{ percent: number; shape?: 'rect' | 'circle' | 'pin' | 'triangle' }

word-cloud

{ data: { text: string; value: number; }[]; }

venn

交集用逗号分隔集合标识:sets: "A,B"label 用于显示图表上对应集合的名称

{ data: { sets: string | string[]; value: number; label?: string }[] }

treemap

type TreeNode = { name: string; value: number; children?: TreeNode[] };
{ data: TreeNode[] }

sankey

{ data: { source: string; target: string; value: number }[]; nodeAlign?: 'left' | 'center' | 'right' | 'justify' }

flow-diagram / network-graph

source/target 引用节点的 name

type GraphData = { nodes: { name: string }[]; edges: { source: string; target: string; name?: string }[] };

// flow-diagram
{ data: GraphData }

// network-graph
{ data: GraphData; layout?: 'force' | 'circular' | 'grid' | 'radial' | 'concentric' | 'dagre' }

mindmap / indented-tree / organization-chart

type TreeData = { name: string; children?: TreeData[] };

// mindmap
{ data: TreeData; direction?: 'H' | 'LR' | 'RL' }

// indented-tree
{ data: TreeData; direction?: 'LR' | 'RL' | 'H' }

// organization-chart
type OrganizationChartData = {
  name: string;
  description?: string;
  children?: OrganizationChartData[];
};

{ data: OrganizationChartData }

mindmap 默认 'H',indented-tree 默认 'LR'

fishbone-diagram

type FishboneNode = { name: string; children?: FishboneNode[] };
{ data: FishboneNode; style?: { texture?: 'rough' | 'default' } }

texture: 'rough' 为手绘风格。

table

{ data: Record<string, string | number>[]; }

summary

summary 与其他图表类型完全不同:不使用 Syntax/JSON 配置,而是使用 T8 语法(Markdown + 语义标注)。

⚠️ 生成 summary 前必须:先读取 references/summary.md 获取 T8 语法规则、完整实体类型列表、属性字段定义、生成要求和示例,然后再生成内容。跳过此步骤将导致语法错误。

最佳实践

  1. 饼图分类不超过 5 个,超过建议合并为"其它"或改用条形图
  2. 不要用饼图展示趋势,不要用折线图展示无序分类
  3. 数值字段必须是数字类型,分类字段必须是文本类型
  4. 连续数值的分布(如薪资、成绩、年龄)必须用直方图(histogram)
  5. 多维数据字段映射:有两个分类维度时,x 轴维度写 time/category,另一个写 group
  6. 语法模式优先用 Syntax 格式(流式友好)
  7. 代码模式默认生成 HTML + CDN 方案(零安装),用户指定框架时再用 npm 方案

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 Gpt Vis AI skill do?

推荐并生成合适的数据可视化图表,使用 GPT-Vis 库。支持两种输出模式:(1)语法模式——生成 Syntax 或 JSON 配置;(2)代码模式——生成完整的运行代码。支持 26 种图表类型。

Why use Gpt Vis on TypingMind?

Because you install it once and use it with any model. Gpt Vis 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 Gpt Vis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/antvis/chart-visualization-skills/tree/master/skills/gpt-vis. 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 Gpt Vis?

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 Gpt Vis?

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

Is the Gpt Vis AI skill free?

Yes. It is published on GitHub by antvis 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 👇