Skip to content
Back to search

ava-skills

MarketplaceWorks with Claude CodeGitHub

๐Ÿ‘พ AI-native Visual Analytics framework build for agents.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/antvis/AVA with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/antvis/AVA'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/antvis--ava/badge.svg)](/listings/antvis--ava)

HTML

<a href="/listings/antvis--ava"><img src="/api/listings/antvis--ava/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

๐Ÿ“ฆ Installation

Install the v4 beta with Node.js 22.13+:

npm install @antv/ava@beta

๐Ÿ’ป Usage

Investigate a monthly sales decline: measure the change, identify the largest contributors, and visualize the breakdown.

Load data

Download [sales.csv](__tests__/datasets/sales.csv) to your working directory. The sample contains 240 orders across 2025, with products, regions, channels, sales, and profit.

import { AVA } from '@antv/ava';

const ava = new AVA({
  llm: {
    model: '<your-model>',
    apiKey: '<your-api-key>',
    // baseURL: '<your-provider-api-url>',
  },
});

await ava.source({ type: 'csv-file', options: { path: './sales.csv' } });

Ask questions

Measure the overall change using `sales`, the amount after discounts:

const overview = await ava.analyze(`
  Compare total sales in January and February 2025 using the sales column.
  Include the change and percentage change.
`);
console.log(overview.text);

Expected: sales fell from **38,897.18 to 21,804.11**, down **17,093.07 (43.94%)**.

Find the products contributing to the decline:

const result = await ava.analyze(`
  Compare January and February 2025 sales by product using the sales column.
  Show both months and the change, ordered by the largest decline.
`);
console.log(result.text);
console.table(result.data);

Expected breakdown:

| Product | January sales | February sales | Change | | --- | ---: | ---: | ---: | | Laptop | 19,688.10 | 3,596.00 | โˆ’16,092.10 | | Standing Desk | 9,655.80 | 5,546.10 | โˆ’4,109.70 | | Monitor | 6,536.25 | 4,731.00 | โˆ’1,805.25 | | Pen Set | 232.20 | 127.71 | โˆ’104.49 | | Bookshelf | 1,225.50 | 1,251.30 | +25.80 | | Copy Paper | 59.19 | 137.06 | +77.87 | | Notebook | 31.50 | 137.03 | +105.53 | | Keyboard | 215.64 | 1,015.31 | +799.67 | | Office Chair | 1,253.00 | 5,262.60 | +4,009.60 |

Laptops contributed the largest decline, while office chairs delivered the largest increase.

Visualize charts

Chart each product's contribution to the sales change:

import { writeFile } from 'node:fs/promises';

const chart = await ava.visualize({
  query: 'Plot the sales change by product from January to February 2025 as a bar chart.',
  data: result.data,
});
if (chart) {
  await writeFile('sales-change.html', chart.html);
}

Open `sales-change.html` in a browser with internet access.

Find questions to explore

Get suggested questions for your data:

const suggestions = await ava.suggest();
console.log(suggestions);

> ๐Ÿ’ก **Suggested questions** > > How do sales change month by month? > > Which products contribute the most profit? > > How do sales compare across channels?

Understand your data

Check missing values and sales ranges:

console.log(await ava.schema());
console.log(await ava.profile({ metrics: ['row_count', 'null_count', 'min', 'max'] }));

The sample has one missing `region` and one missing `quantity`.

Release resources when finished:

await ava.dispose();

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json ยท Manifest ยท 19 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "ava-skills",
  3. "owner": {
  4. "name": "AntV Visualization Team"
  5. },
  6. "metadata": {
  7. "description": "AVA skills for data analysis and visualization",
  8. "version": "1.0.0"
  9. },
  10. "plugins": [
  11. {
  12. "name": "ava",
  13. "description": "Explore, query, analyze, and visualize structured data with the AVA CLI.",
  14. "source": "./",
  15. "strict": false,
  16. "skills": ["./skills/ava"]
  17. }
  18. ]
  19. }
README.md ยท README ยท 277 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. **English** | [็ฎ€ไฝ“ไธญๆ–‡](./README.zh-CN.md)
  2. <div align="center">
  3. <h1>AVA, AI-native Visual Analytics</h1>
  4. <img width="200" height="120" src="https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*yOHIQ48aRwgAAAAAAAAAAAAADmJ7AQ/original" alt="AVA logo">
  5. </div>
  6. <p align="center">
  7. <a href="https://ava.antv.vision">
  8. <img src="https://img.shields.io/badge/Website-2F54EB?style=for-the-badge" alt="Website" />
  9. </a>
  10. <a href="https://ava.antv.vision/documentation/">
  11. <img src="https://img.shields.io/badge/Docs-722ED1?style=for-the-badge" alt="Documentation" />
  12. </a>
  13. <a href="https://ava.antv.vision/ai/">
  14. <img src="https://img.shields.io/badge/AI%20Agent-EB2F96?style=for-the-badge" alt="AI Agent" />
  15. </a>
  16. <a href="https://sive.antv.antgroup.com/" title="A data analysis app built with AVA">
  17. <img src="https://img.shields.io/badge/Try%20Sive-13A8A8?style=for-the-badge" alt="Try Sive" />
  18. </a>
  19. <a href="https://github.com/antvis/ava">
  20. <img src="https://img.shields.io/badge/GitHub-000000?style=for-the-badge&logo=github&logoColor=white" alt="GitHub" />
  21. </a>
  22. <a href="https://ava.antv.vision/llms.txt">
  23. <img src="https://img.shields.io/badge/LLMS-FA8C16?style=for-the-badge" alt="llms" />
  24. </a>
  25. </p>
  26. [AVA](https://github.com/antvis/AVA) (<img src="https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*QzIsSrfsCW0AAAAAAAAAAAAADmJ7AQ/original" width="16" alt="AVA examples"> Visual Analytics) is a technology framework designed for more convenient visual analytics. **A** stands for AI-native, Automated, and Augmented; **VA** stands for Visual Analytics.
  27. <p align="center">
  28. <a href="https://ava.antv.vision/">
  29. <img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*MMXYTJ0KhukAAAAAgEAAAAgAegfkAQ/original" width="100%" alt="AVA agent workflow: data access, schema inspection, profiling, metric definitions, analysis, visualization, and follow-up questions, with verifiable SQL and results." />
  30. </a>
  31. </p>
  32. > [!NOTE]
  33. > **Think of AVA as PandasAI for JavaScript. ๐Ÿ’ฌ๐Ÿ“Š๐Ÿค–**
  34. >
  35. > It brings natural-language data analysis and visualization to your apps and AI agents.
  36. ## โœจ Why AVA?
  37. <table width="100%">
  38. <tr>
  39. <td width="33%" valign="top">
  40. <h3>๐Ÿ”Œ Analysis across data sources</h3>
  41. <p>Join data from files and databases <strong>in a single query</strong>.</p>
  42. <a href="https://ava.antv.vision/documentation/data/sources/#connect-multiple-sources">Connect multiple sources โ†’</a>
  43. </td>
  44. <td width="33%" valign="top">
  45. <h3>๐Ÿ”Ž Grounded answers</h3>
  46. <p>Inspect the <strong>queries and results</strong> behind each answer.</p>
  47. <a href="https://ava.antv.vision/documentation/analysis/overview/">Trusted analysis โ†’</a>
  48. </td>
  49. <td width="33%" valign="top">
  50. <h3>๐Ÿ“Š Smart visualization</h3>
  51. <p>Get charts guided by <strong>your question and data</strong>.</p>
  52. <a href="https://ava.antv.vision/documentation/visualization/overview/">Visualization โ†’</a>
  53. </td>
  54. </tr>
  55. <tr>
  56. <td width="33%" valign="top">
  57. <h3>๐Ÿ’ป Local execution</h3>
  58. <p>Choose <strong>where analysis runs</strong> and which model endpoint it uses.</p>
  59. <a href="https://ava.antv.vision/documentation/engines/overview/">Execution engines โ†’</a>
  60. </td>
  61. <td width="33%" valign="top">
  62. <h3>๐ŸŽฏ Published benchmarks</h3>
  63. <p>Check accuracy against <strong>reference answers</strong> under published test conditions.</p>
  64. <a href="https://ava.antv.vision/documentation/reference/benchmarks/">Benchmarks โ†’</a>
  65. </td>
  66. <td width="33%" valign="top">
  67. <h3>๐Ÿค– Agent integration</h3>
  68. <p>Your agent reasons; <strong>AVA executes</strong> the data workflow.</p>
  69. <a href="https://ava.antv.vision/documentation/agent-skill/">Agent integration โ†’</a>
  70. </td>
  71. </tr>
  72. </table>
  73. ## ๐Ÿš€ Getting started
  74. Install AVA with Node.js 22.13+:
  75. ```bash
  76. npm install @antv/ava
  77. ```
  78. ## ๐Ÿ’ป Usage
  79. Download [sales.csv](__tests__/datasets/sales.csv) and configure your model:
  80. ```typescript
  81. import { AVA } from '@antv/ava';
  82. const ava = new AVA({
  83. llm: {
  84. model: '<your-model>',
  85. apiKey: '<your-api-key>',
  86. // baseURL: '<your-provider-api-url>',
  87. },
  88. });
  89. ```
  90. ### 1. Load
  91. ```typescript
  92. await ava.source({ type: 'csv-file', options: { path: './sales.csv' } });
  93. ```
  94. > [!NOTE]
  95. > **Data preview**
  96. >
  97. > First 3 of 240 rows, selected columns:
  98. >
  99. > | order_date | product | sales |
  100. > | --- | --- | ---: |
  101. > | 2025-01-01 | Monitor | 224.10 |
  102. > | 2025-01-02 | Office Chair | 680.20 |
  103. > | 2025-01-04 | Monitor | 2,191.20 |
  104. ### 2. Explore
  105. Inspect the structure and data quality, then add [business definitions](https://ava.antv.vision/documentation/data/semantic/):
  106. ```typescript
  107. const schema = await ava.schema();
  108. const profile = await ava.profile({ metrics: ['row_count', 'null_count'] });
  109. await ava.semantic(undefined, () => ({
  110. description: 'Use the sales column for amounts after discounts and order_date for monthly comparisons.',
  111. }));
  112. ```
  113. > [!NOTE]
  114. > **Analysis context**
  115. >
  116. > | Context | Details |
  117. > | --- | --- |
  118. > | Structure | `data`: 12 columns |
  119. > | Quality | 240 rows; 1 missing `region` and 1 missing `quantity` |
  120. > | Semantics | `sales` is after discounts; monthly comparisons use `order_date` |
  121. ### 3. Suggest
  122. ```typescript
  123. const suggestions = await ava.suggest(3);
  124. ```
  125. > [!NOTE]
  126. > **Suggested questions** (examples)
  127. >
  128. > - How did sales change from January to February 2025?
  129. > - Which products contributed most to the sales decline?
  130. > - How do sales and profit vary by region?
  131. ### 4. Analyze
  132. ```typescript
  133. const result = await ava.analyze(
  134. 'Compare January and February 2025 sales by product. Show both months and the change, ordered by the largest decline.'
  135. );
  136. ```
  137. > [!NOTE]
  138. > **Analysis result**
  139. >
  140. > Total sales fell **43.94%**, led by a **16,092.10** decline in laptop sales.
  141. >
  142. > First 3 of 9 products:
  143. >
  144. > | Product | January sales | February sales | Change |
  145. > | --- | ---: | ---: | ---: |
  146. > | Laptop | 19,688.10 | 3,596.00 | โˆ’16,092.10 |
  147. > | Standing Desk | 9,655.80 | 5,546.10 | โˆ’4,109.70 |
  148. > | Monitor | 6,536.25 | 4,731.00 | โˆ’1,805.25 |
  149. ### 5. Visualize
  150. ```typescript
  151. const chart = await ava.visualize({
  152. query: 'Plot the sales change by product from January to February 2025 as a bar chart.',
  153. data: result.data,
  154. });
  155. ```
  156. > [!NOTE]
  157. > **Chart preview**
  158. >
  159. > <img src=".github/assets/sales-change.png" width="800" alt="Sales change by product from January to February 2025, with decreases in red and increases in green.">
  160. >
  161. > *Powered by [GPT-Vis](https://gpt-vis.antv.vision/).*
  162. ## ๐Ÿ”Œ Connect your data
  163. <table width="100%">
  164. <tr>
  165. <td align="center" width="12.5%"><a href="https://ava.antv.vision/documentation/data/sources/#csv"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*SEIZRJCeCuYAAAAAQBAAAAgAegfkAQ/original" width="32" height="32" alt="CSV" /><br />CSV</a></td>
  166. <td align="center" width="12.5%"><a href="https://ava.antv.vision/documentation/data/sources/#json"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*VBNjQJDMvMIAAAAAHYAAAAgAegfkAQ/original" width="32" height="32" alt="JSON" /><br />JSON</a></td>
  167. <td align="center" width="12.5%"><a href="https://ava.antv.vision/documentation/data/sources/#parquet"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*-_h8RrPPA54AAAAAFkAAAAgAegfkAQ/original" width="32" height="32" alt="Parquet" /><br />Parquet</a></td>
  168. <td align="center" width="12.5%"><a href="https://ava.antv.vision/documentation/data/sources/#excel"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*GfCXT7Mb_5gAAAAAQCAAAAgAegfkAQ/original" width="32" height="32" alt="Excel" /><br />Excel</a></td>
  169. <td align="center" width="12.5%"><a href="https://ava.antv.vision/documentation/data/sources/#text"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*XrY8SK_9fGwAAAAAEsAAAAgAegfkAQ/original" width="32" height="32" alt="Text" /><br />Text</a></td>
  170. <td align="center" width="12.5%"><a href="https://ava.antv.vision/documentation/data/online-services/feishu-bitable/"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*Rly3Rou8Wv8AAAAAQFAAAAgAegfkAQ/original" width="32" height="32" alt="Feishu Bitable" /><br />Feishu Bitable</a></td>
  171. <td align="center" width="12.5%"><a href="https://ava.antv.vision/documentation/data/online-services/tencent-smartsheet/"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*wH-PT4nF70wAAAAAMkAAAAgAegfkAQ/original" width="32" height="32" alt="Tencent Docs" /><br />Tencent Docs</a></td>
  172. <td align="center" width="12.5%"><a href="https://ava.antv.vision/documentation/data/online-services/github/"><img src="site/public/logos/github.svg" width="32" height="32" alt="GitHub" /><br />GitHub</a></td>
  173. </tr>
  174. <tr>
  175. <td align="center"><a href="https://ava.antv.vision/documentation/data/sources/#sqlite"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*3xulRYi0wWkAAAAAQBAAAAgAegfkAQ/original" width="32" height="32" alt="SQLite" /><br />SQLite</a></td>
  176. <td align="center"><a href="https://ava.antv.vision/documentation/data/sources/#mysql"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*8TDeSpgXAi0AAAAAQEAAAAgAegfkAQ/original" width="32" height="32" alt="MySQL" /><br />MySQL</a></td>
  177. <td align="center"><a href="https://ava.antv.vision/documentation/data/sources/#postgresql"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*h6xsS5N0EbcAAAAAQFAAAAgAegfkAQ/original" width="32" height="32" alt="PostgreSQL" /><br />PostgreSQL</a></td>
  178. <td align="center"><a href="https://ava.antv.vision/documentation/data/sources/#sql-server"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*XVBPSaYT6p0AAAAAQJAAAAgAegfkAQ/original" width="32" height="32" alt="SQL Server" /><br />SQL Server</a></td>
  179. <td align="center"><a href="https://ava.antv.vision/documentation/data/sources/#mongodb"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*5VYbTakXL7EAAAAAIlAAAAgAegfkAQ/original" width="32" height="32" alt="MongoDB" /><br />MongoDB</a></td>
  180. <td align="center"><a href="https://ava.antv.vision/documentation/data/sources/#supabase"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*IWbeTqNDuu4AAAAAFFAAAAgAegfkAQ/original" width="32" height="32" alt="Supabase" /><br />Supabase</a></td>
  181. <td align="center"><a href="https://ava.antv.vision/documentation/data/sources/#clickhouse"><img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*o0VuQ5NvHZ8AAAAAELAAAAgAegfkAQ/original" width="32" height="32" alt="ClickHouse" /><br />ClickHouse</a></td>
  182. <td align="center"><a href="https://ava.antv.vision/documentation/data/sources/#snowflake"><img src="site/public/logos/snowflake.svg" width="32" height="32" alt="Snowflake" /><br />Snowflake</a></td>
  183. </tr>
  184. </table>
  185. > [!TIP]
  186. > **Missing a data source? ๐Ÿ’ก๐Ÿ› ๏ธ**
  187. >
  188. > **[๐Ÿ’ฌ Open an issue](https://github.com/antvis/AVA/issues/new/choose)** ยท **[๐Ÿ› ๏ธ Submit a pull request](https://github.com/antvis/AVA/compare)**
  189. ## ๐ŸŽฏ Benchmarks
  190. We evaluate AVA on established benchmarks to measure the accuracy and efficiency of its data analysis.
  191. <img src="https://mdn.alipayobjects.com/huamei_aphk1k/afts/img/A*XjhtSbWcb70AAAAAUlAAAAgAegfkAQ/original" width="100%" alt="DataBench and Spider2-Lite evaluation results comparing raw data, schema and profile, and semantic context.">
  192. [Evaluation setup and reports โ†’](https://ava.antv.vision/documentation/reference/benchmarks/)
  193. ## ๐Ÿงฉ More ways to use AVA
  194. ### Use with an Agent
  195. Ask your AI agent:
  196. ```text
  197. Install the AVA skill with `npx skills add antvis/AVA`, then follow its setup instructions.
  198. ```
  199. [Agent setup guide โ†’](https://ava.antv.vision/documentation/agent-skill/)
  200. ### Use from the CLI
  201. Load and analyze data from your terminal:
  202. ```bash
  203. ava source ./sales.csv
  204. ava analyze '<dataset-id>' 'Compare January and February 2025 sales by product.'
  205. ```
  206. See the [CLI guide](https://ava.antv.vision/documentation/reference/cli/) for setup and commands.
  207. ## ๐Ÿ“š Resources
  208. - [Documentation](https://ava.antv.vision/documentation/) โ€” Guides and examples
  209. - [Analysis strategies](https://ava.antv.vision/documentation/analysis/strategies/) โ€” Direct and loop execution
  210. - [API Reference](https://ava.antv.vision/documentation/reference/api/) โ€” Methods and configuration
  211. - [AI](https://ava.antv.vision/ai/) โ€” Try out AVA in the browser environment
  212. - [Benchmarks](https://ava.antv.vision/documentation/reference/benchmarks/) โ€” Evaluation results
  213. - [Issues](https://github.com/antvis/AVA/issues) โ€” Bug reports and feature requests
  214. ## ๐Ÿค๐Ÿ› ๏ธ Contributing
  215. Contributions are welcome. Include tests, examples, and documentation with new features.
  216. Run `npm test` to test your changes. For model-backed tests, copy `.env.example` to `.env` and add your model settings.
  217. ## ๐Ÿ“‘ Papers
  218. [VizLinter](https://vegalite-linter.idvxlab.com/) - Chen, Q., Sun, F., Xu, X., Chen, Z., Wang, J. and Cao, N., 2021. VizLinter: A Linter and Fixer Framework for Data Visualization. *IEEE transactions on visualization and computer graphics*, 28(1), pp.206-216.
  219. [ใ€Šๆ•ฐๆฎๅฏ่ง†ๅŒ–่ฎพ่ฎก็š„็ฑปๅž‹ๅญฆๅฎž่ทตใ€‹๏ผˆExploring the Typology of Visualization Design๏ผ‰](https://oversea.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFD&dbname=CJFDAUTO&filename=MSDG202203021&uniplatform=OVERSEAS_EN&v=HcZsiecIxauSoKEB1s92_BImgnrMiazYsfZUpb-gcl0zXYx_MEwv5alz1UgtPjz1) - ่“ๆ˜Ÿๅฎ‡, ็Ž‹ๅ˜‰ๅ–†. ๆ•ฐๆฎๅฏ่ง†ๅŒ–่ฎพ่ฎก็š„็ฑปๅž‹ๅญฆๅฎž่ทต, ใ€Š็พŽๆœฏๅคง่ง‚ใ€‹, 2022(3), 149-152.
  220. ## โš–๏ธ License
  221. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If itโ€™s helped, pass it on.