
Chart Visualization
- 5.5k installs
- 454 repo stars
- Updated July 31, 2026
- antvis/chart-visualization-skills
chart-visualization selects an AntV chart type, calls the gpt-vis API with curl, and returns a Markdown image URL.
About
The chart-visualization skill turns structured user data into shareable chart images through the AntV Studio gpt-vis API. Agents first analyze the dataset and user intent, then map data characteristics to an appropriate visualization type: line or area for time trends, dual-axes when scales differ, bar or column for category comparisons, histogram for distributions, pie or treemap for composition, sankey or scatter for flows and correlations, and organization-chart or mind-map for hierarchies. It builds a JSON payload with required type and source fields, posts it with curl to the hosted endpoint, and returns the image URL in Markdown format. The skill documents data schemas per chart, optional theme and sizing controls, axis titles, and specialized types including radar, funnel, liquid, word-cloud, boxplot, violin, network-graph, fishbone-diagram, flow-diagram, and spreadsheet tables. Use it when an agent must visualize metrics, comparisons, or flows without embedding a local charting library, following the documented workflow from analysis through Markdown image output.
- Maps data traits to 20+ AntV chart types before API calls.
- Posts JSON with type and source chart-visualization-skills via curl.
- Returns gpt-vis resultObj URLs as Markdown images.
- Documents per-chart data schemas, themes, and axis titles.
- Covers trends, comparisons, distributions, flows, and hierarchies.
Chart Visualization by the numbers
- 5,511 all-time installs (skills.sh)
- +172 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #94 of 2,245 Frontend Development skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
chart-visualization capabilities & compatibility
- Capabilities
- chart type selection guide for trends, compariso · curl post to https://antv studio.alipay.com/api/ · per type data schema reference for 20+ chart kin · theme, width, height, and axis title configurati · markdown image output from resultobj url
- Use cases
- data analysis · presentations · documentation
- Runs
- Hosted SaaS
- Pricing
- Free
What chart-visualization says it does
请求体为 JSON,必须包含 `type` 和 `source: "chart-visualization-skills"` 字段。
将 `resultObj` 中的 URL 以 Markdown 图片格式输出:``
**时间序列**:用 `line`(趋势)或 `area`(累计趋势);两个不同量纲用 `dual-axes`
npx skills add https://github.com/antvis/chart-visualization-skills --skill chart-visualizationAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 5.5k |
|---|---|
| repo stars | ★ 454 |
| Security audit | 2 / 3 scanners passed |
| Last updated | July 31, 2026 |
| Repository | antvis/chart-visualization-skills ↗ |
How do I turn tabular or time-series data into a chart image inside an agent workflow?
Generate bar, line, pie, scatter, radar, sankey, mind-map, and flow charts via AntV gpt-vis API.
Who is it for?
Agents that need quick bar, line, pie, sankey, radar, or hierarchy charts without a local renderer.
Skip if: Custom D3 or canvas chart code, real-time dashboards, or edits to an existing rendered image.
When should I use this skill?
User needs bar, line, pie, scatter, radar, sankey, mind-map, flow, or other AntV chart types from data.
What you get
A hosted chart image URL rendered as Markdown plus the JSON payload used to generate it.
- chart image URL
- markdown image embed
- JSON API request body
By the numbers
- Supports 15+ chart types including line, bar, pie, scatter, sankey, funnel, and radar
Files
请根据用户输入的内容,将数据可视化为图表。
步骤
1. 分析用户数据和需求,选择最合适的图表类型 2. 构造符合规范的 JSON 请求体 3. 使用 curl 工具调用 API 生成图表图片 4. 将返回的图片 URL 以 Markdown 图片格式输出
图表选择指南
根据用户的数据特征和需求,选择最合适的图表类型:
- 时间序列:用
line(趋势)或area(累计趋势);两个不同量纲用dual-axes - 比较类:用
bar(横向分类对比)或column(纵向分类对比);频率分布用histogram - 占比类:用
pie(比例构成)或treemap(层级占比) - 关系与流程:用
scatter(相关性)、sankey(流向)或venn(集合重叠) - 层级与树形:用
organization-chart或mind-map - 专用类型:
radar:多维度对比funnel:流程阶段转化liquid:百分比/进度word-cloud:文本词频boxplot/violin:统计分布network-graph:复杂节点关系fishbone-diagram:因果分析flow-diagram:流程图spreadsheet:结构化数据表或透视表
API 接口
POST https://antv-studio.alipay.com/api/gpt-vis
请求体为 JSON,必须包含 type 和 source: "chart-visualization-skills" 字段。
示例:
curl -X POST https://antv-studio.alipay.com/api/gpt-vis \
-H "Content-Type: application/json" \
-d '{"type":"line","source":"chart-visualization-skills","data":[{"time":"2025-01","value":100}],"title":"示例图表"}'返回示例:
{"success":true,"resultObj":"https://..."}将 resultObj 中的 URL 以 Markdown 图片格式输出:
支持的图表类型
| 分类 | 图表类型 |
|---|---|
| 比较类 | 条形图(bar)、柱状图(column)、瀑布图(waterfall)、双轴图(dual-axes) |
| 趋势类 | 面积图(area)、折线图(line)、散点图(scatter) |
| 分布类 | 箱线图(boxplot)、直方图(histogram)、小提琴图(violin)、漏斗图(funnel) |
| 占比类 | 饼图(pie)、水波图(liquid)、词云(word-cloud) |
| 层级类 | 组织架构图(organization-chart)、思维导图(mind-map)、矩形树图(treemap)、桑基图(sankey) |
| 关系类 | 关系图(network-graph)、韦恩图(venn) |
| 流程类 | 流程图(flow-diagram)、鱼骨图(fishbone-diagram) |
| 多维类 | 雷达图(radar) |
| 表格类 | 表格/透视表(spreadsheet) |
通用可选参数
| 参数 | 类型 | 默认值 | 说明 |
|---|---|---|---|
| theme | string | "default" | 主题:"default" / "academy" / "dark" |
| width | number | 600 | 图表宽度 |
| height | number | 400 | 图表高度 |
| title | string | "" | 图表标题 |
| style.texture | string | "default" | 纹理:"default" / "rough"(手绘风格) |
带坐标轴的图表还支持:axisXTitle、axisYTitle。
各图表 data 格式
- area / line:
{time: string, value: number, group?: string}[],可选 stack: boolean - bar:
{category: string, value: number, group?: string}[],可选 group / stack (默认 stack: true) - column:
{category: string, value: number, group?: string}[],可选 group (默认 true) / stack - scatter:
{x: number, y: number, group?: string}[] - pie:
{category: string, value: number}[],可选 innerRadius: number (0-1) - radar:
{name: string, value: number, group?: string}[] - funnel:
{category: string, value: number}[] - waterfall:
{category: string, value?: number, isTotal?: boolean, isIntermediateTotal?: boolean}[] - dual-axes: categories: string[], series: {type: "column"|"line", data: number[], axisYTitle?: string}[]
- histogram:
number[],可选 binNumber: number - boxplot / violin:
{category: string, value: number, group?: string}[] - liquid: percent: number (0-1),可选 shape: "circle"|"rect"|"pin"|"triangle"
- word-cloud:
{text: string, value: number}[] - sankey:
{source: string, target: string, value: number}[],可选 nodeAlign - treemap:
{name: string, value: number, children?: ...}[](最深 3 层) - venn:
{sets: string[], value: number, label?: string}[] - network-graph / flow-diagram:
{nodes: {name: string}[], edges: {source: string, target: string, name?: string}[]} - fishbone-diagram / mind-map:
{name: string, children?: ...}(最深 3 层) - organization-chart:
{name: string, description?: string, children?: ...}(最深 3 层),可选 orient: "horizontal"|"vertical" - spreadsheet:
Record<string, string | number>[],可选 rows / columns / values(透视表字段)
Related skills
FAQ
What does chart-visualization do?
It analyzes your data, picks an AntV chart type, POSTs JSON to gpt-vis, and outputs the returned image URL as Markdown.
When should I use chart-visualization?
Invoke when you have structured metrics or categories and need a shareable chart image via the AntV API.
What fields are required in the API request?
The JSON body must include type and source set to chart-visualization-skills plus chart-specific data.
Is Chart Visualization safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.