# databricks-aibi-dashboards

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

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 305 installs · ★ 368
- Author: databricks
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/databricks/databricks-agent-skills/tree/HEAD/skills/databricks-aibi-dashboards/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/databricks-aibi-dashboards

## What it 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.

## Requirements
- Works with: Databricks

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-aibi-dashboards -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/databricks-aibi-dashboards/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/databricks-aibi-dashboards/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-aibi-dashboards -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/databricks-aibi-dashboards/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-aibi-dashboards -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/databricks-aibi-dashboards/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install databricks/databricks-agent-skills databricks-aibi-dashboards
```

2. **Manually: put the files in place**
- File: `.github/skills/databricks-aibi-dashboards/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-aibi-dashboards -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/databricks/databricks-agent-skills --path skills/databricks-aibi-dashboards
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/databricks-aibi-dashboards/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-aibi-dashboards -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/databricks/databricks-agent-skills/tree/HEAD/skills/databricks-aibi-dashboards/SKILL.md

## When to use it
- 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
- 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

## Similar
- [sql-queries](https://affpapa.org/en/nevibecode/skills/sql-queries.md) — skill · 4500 installs
- [migrating-dbt-project-across-platforms](https://affpapa.org/en/nevibecode/skills/migrating-dbt-project-across-platforms.md) — skill · 526 installs
- [neon-ai-gateway](https://affpapa.org/en/nevibecode/skills/neon-ai-gateway.md) — skill · 27700 installs
- [cx-dashboards](https://affpapa.org/en/nevibecode/skills/cx-dashboards.md) — skill · 3300 installs
- [kibana-dashboards](https://affpapa.org/en/nevibecode/skills/kibana-dashboards.md) — skill · 4300 installs
- [dt-app-dashboards](https://affpapa.org/en/nevibecode/skills/dt-app-dashboards.md) — skill · 2800 installs

From the same set: [databricks/databricks-agent-skills](https://affpapa.org/en/nevibecode/by/databricks/databricks-agent-skills.md) — 12 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md