databricks-data-discovery — Claude Code skill: setup guide
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.
no license 1,200 installs ★ 408 updated 2026-10-24
npx skills add databricks/databricks-agent-skills --skill databricks-data-discovery -a claude-codeWhat databricks-data-discovery 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.
What it helps with
- 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 for the agent
- 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
How to install databricks-data-discovery
1Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-data-discovery -a claude-code2Manually: put the files in place
~/.claude/skills/databricks-data-discovery/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/databricks-data-discovery/
1Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-data-discovery -a codex2Manually: put the files in place
.agents/skills/databricks-data-discovery/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-data-discovery -a cursor2Manually: put the files in place
.cursor/skills/databricks-data-discovery/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install databricks/databricks-agent-skills skills/databricks-data-discovery2Manually: put the files in place
.github/skills/databricks-data-discovery/SKILL.md1Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-data-discovery -a gemini-cli2Platform CLI
gemini skills install https://github.com/databricks/databricks-agent-skills --path skills/databricks-data-discoveryManually: put the files in place
.devin/skills/databricks-data-discovery/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-data-discovery -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about databricks-data-discovery
How to install databricks-data-discovery in Claude Code?
Run npx skills add databricks/databricks-agent-skills --skill databricks-data-discovery -a claude-code. The definition is placed in ~/.claude/skills/databricks-data-discovery/SKILL.md.
What does databricks-data-discovery do?
It intercepts data questions, catalog discovery, and query drafting prompts, sending them directly to Databricks Genie One via the CLI.
Which CLI version is required?
You need databricks CLI version 1.9.0 or higher with an active authentication profile. Older releases must rely on databricks experimental genie ask.