AVA ChartGenie LogoAVA
AI

Explore your data with AVA

to analyze the sample data or upload your own CSV, Excel (.xlsx), or JSON file (up to 25 MB). Follow each step to inspect the code, charts, and results.

Need SQL, Python, Parquet, or database connections?

From data to understanding

What would you like
to discover?

Start with the sample dataset or upload a CSV, Excel, or JSON file. Choose a question below, or ask your own.

monthly-sales-2026.csv· 9 rows
AVA Agent Skill

Give your agent
visual analytics.

Install the AVA Skill to work with your own files and databases. Your agent plans the analysis; AVA runs the queries and renders the charts.

The core workflow uses your agent’s existing model. No separate AVA model key is required.

Paste into your terminal-based AI agent. It will check your environment, install AVA, and verify the setup.

Read the Skill guide

01 · Install the CLI and Skill

npm install -g @antv/ava@beta
npx --yes skills add antvis/AVA --skill ava --yes

macOS or Linux · Node.js 22.13+ · CLI + project Skill

02 · Start a new agent session

“Use the AVA skill to analyze ./sales.csv. Compare sales by region and save a chart. Include the query and results table so I can verify the analysis.”

Preview the install prompt
Install AVA's Agent Skill in the current project so you can analyze data and create charts for me.

1. Check that this environment runs macOS or Linux, with Node.js 22.13 or later and npm available. Use an existing Node version manager if an upgrade is needed. If you cannot meet these requirements, explain what is missing.
2. Install the CLI with `npm install -g @antv/ava@beta`. Verify that `ava --help` and `ava source --help` work.
3. Install the skill for the detected agents in this project with `npx --yes skills add antvis/AVA --skill ava --yes`.
4. Read the installed ava/SKILL.md and its environment setup reference. Verify the installed skill with `npx --yes skills list`.
5. Smoke-test the CLI using a tiny CSV in a new temporary directory: load it with `ava source`, inspect it with `ava schema`, and execute a simple aggregate with `ava query`. Use the returned dataset ID and the actual table name from the schema. Dispose of this test session afterward.

Use your own reasoning for analysis; do not ask me for an additional AVA model API key. Report the installed CLI version, skill location, and verification results. If anything fails, explain the error instead of claiming success. Tell me whether I need to start a new agent session to load the skill.