Skip to main content
skill CX Codex

databricks-aibi-dashboards — Claude Code skill for AI/BI dashboards

A skill for building Databricks AI/BI (formerly Lakeview) dashboards: picks widgets, tests SQL, deploys through the CLI.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add databricks/databricks-agent-skills --skill databricks-aibi-dashboards -a claude-code
Open on GitHub

What databricks-aibi-dashboards does

The skill walks an agent through creating, updating and publishing AI/BI dashboards in Databricks. Lakeview dashboards use their own JSON structure, so a model left alone tends to produce a file that will not load. The widget index maps each type to a version — counter and table are version 2, bar and line are version 3, combo and choropleth-map are version 1. A wrong version breaks the widget, and that is the most common failure.

Reference files cover widget specifications, custom Vega-Lite visualizations and a command cheat sheet. The agent lists tables, reads the schema, runs every SQL query through the CLI, and only then deploys. Custom charts go through Vega-Lite, which does not support every Vega example, so check that your marks and transforms are covered before you commit to one.

You need the Databricks CLI at v1.0.0 or newer. On create and update, --dataset-catalog and --dataset-schema work as flags only: put them in --json and the CLI drops them without a warning. Re-pass both on every update, or bare-table queries break. If your CLI rejects --warehouse on the query command, set DATABRICKS_WAREHOUSE_ID in the environment instead.

What it helps with

  • build an AI/BI dashboard JSON that actually loads
  • pick the right widget version for a counter or bar chart
  • test every SQL query through the CLI before deploying
  • publish a dashboard into a specific workspace folder
  • add a custom Vega-Lite chart when standard widgets fall short

Example prompts for the agent

  • Build an AI/BI dashboard with a KPI counter on top and monthly revenue line, test all queries via CLI, then deploy
  • Update the existing dashboard and add a pivot widget with retention by cohort
  • Create a bullet chart with a target marker per category using custom-vega-viz

How to install databricks-aibi-dashboards

1Skills CLI (Vercel)

npx skills add databricks/databricks-agent-skills --skill databricks-aibi-dashboards -a claude-code

2Manually: put the files in place

~/.claude/skills/databricks-aibi-dashboards/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/databricks-aibi-dashboards/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about databricks-aibi-dashboards

How do I install databricks-aibi-dashboards in Claude?

Run npx skills add databricks/databricks-agent-skills --skill databricks-aibi-dashboards -a claude-code. The skill lands in ~/.claude/skills/databricks-aibi-dashboards/SKILL.md.

What does databricks-aibi-dashboards do?

It guides an agent through creating, updating and publishing Databricks AI/BI dashboards. It supplies the JSON structure, widget versions and the order for testing SQL before deploy.

What do I need to run this skill?

The Databricks CLI at v1.0.0 or newer. Queries run through databricks experimental aitools tools query, and deployment goes through databricks lakeview.

Similar skills

All skills for Data and databases →

From the same set7

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor