# databricks-data-discovery

databricks-data-discovery routes table discovery, data queries, and SQL drafting to Databricks Genie via the CLI. Built for data engineers exploring Unity Catalog schemas.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 1200 installs · ★ 408 repo stars
- Author: databricks
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/databricks/databricks-agent-skills/tree/HEAD/skills/databricks-data-discovery/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/databricks-data-discovery

## What it does

This skill guides coding assistants to delegate schema searches and metrics computation directly to Databricks Genie One instead of running brute-force catalog lookups. When you inquire about where a dataset lives or ask for summaries, the agent invokes `databricks genie ask -s <session-label> "..."`. Genie executes within the Databricks data plane, tapping Unity Catalog metadata and semantic context to return grounded answers, charts, and executable SQL.

Work is partitioned intentionally. Genie handles dataset profiling and preliminary query generation, while your primary coding agent takes over to write files, manage jobs, or handle DDL changes like `CREATE` and `UPDATE`. Passing the same label via `-s` preserves conversational state across follow-ups, while distinct flags let you run queries concurrently without context bleed.

Using `databricks genie ask` requires `databricks CLI` v1.9.0 or newer alongside an authenticated workspace profile; older CLI installs fall back to `databricks experimental genie ask`. Without a configured profile, CLI commands fail before reaching Genie.

## Requirements
- Works with: Databricks

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install databricks/databricks-agent-skills skills/databricks-data-discovery
```

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-data-discovery -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-data-discovery/SKILL.md

## When to use it
- locate schemas and tables across Unity Catalog from fuzzy text
- generate validated SQL queries without memorizing table schemas
- calculate metric breakdowns and trends through terminal commands
- preserve analytical context across multi-turn data questions

## Example prompts
- What tables exist in wanderbricks and where is customer usage stored?
- Ask Genie for the top 5 product categories by revenue with SQL included
- Break down those revenue metrics by region using the same session

## Similar
- [databricks-cli](https://affpapa.org/en/nevibecode/plugins/databricks-cli.md) — plugin · ★ 1104 repo stars
- [azure-databricks-platform-architect](https://affpapa.org/en/nevibecode/agents/azure-databricks-platform-architect.md) — subagent · ★ 6505 repo stars
- [data-engineering-patterns-fabric-databricks](https://affpapa.org/en/nevibecode/skills/data-engineering-patterns-fabric-databricks.md) — skill · 1600 installs
- [databricks](https://affpapa.org/en/nevibecode/rules/databricks.md) — rule · ★ 3589 repo stars
- [oracle-ai-data-platform-workbench-databricks-migrator](https://affpapa.org/en/nevibecode/plugins/oracle-ai-data-platform-workbench-databricks-migrator.md) — plugin · ★ 62 repo stars
- [databricks-expert](https://affpapa.org/en/nevibecode/skills/databricks-expert.md) — skill · 215 installs

From the same set: [databricks/databricks-agent-skills](https://affpapa.org/en/nevibecode/by/databricks/databricks-agent-skills.md) — 30 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
