databricks-genie-agents
About databricks-genie-agents
A skill for creating, managing, and querying Databricks Genie Agents, for teams exploring structured Unity Catalog data in natural language. It covers the lifecycle from design through diagnosis, optimization, and migration.
Key features
- 01Designs and creates Genie Agents
- 02Queries and validates through conversation APIs
- 03Diagnoses incorrect or empty answers
- 04Tunes quality using evaluations
- 05Exports, imports, and migrates across workspaces
Use cases
- 01Creating a curated data Q&A agent for a business area
- 02Validating agent queries and responses
- 03Investigating unexpected Genie Agent results
- 04Migrating agents between workspaces
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/databricks-genie-agentsin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
agents/openai.yamlassets/databricks.svgreferences/create-genie-agent.mddiagnose-genie-agent.mdgenie-agent-cicd.mdoptimize-genie-agent.mdquery-genie-agent.mdserialized-space.mduc-persistence.mdDetails
From the project READMEDatabricks Genie Agents
Create, manage, and query Genie Agents (formerly Genie Spaces) - natural language interfaces for SQL-based data exploration.
Overview
Genie Agents allow users to ask natural language questions about structured data in Unity Catalog. The system translates questions into SQL queries, executes them on a SQL warehouse, and presents results conversationally.
A Genie Agent is a curated agent scoped to specific data — its tables, sample questions, and instructions are authored for a particular business area. This is distinct from Genie One / the general "ask Genie" data-discovery path (see the databricks-data-discovery skill), which answers questions across your data without a curated, per-scope agent.
Genie Agent Lifecycle
| Phase | Reference | Load when | Typical CLI |
|---|---|---|---|
| Design + Create | create-genie-agent.md | Always load before creating or updating. Gather requirements, profile data, design surfaces, get approval — before any CLI | discover-schema → create-space / update-space |
| Query / validate | query-genie-agent.md | Querying via Conversation API or Agent mode API; authoring SQL for Metric View sources | start-conversation / get-message |
| Diagnose | diagnose-genie-agent.md | Agent gives wrong/empty answers — gather space ID + failing question + observed behavior first | get-space --include-serialized-space; system.query.history |
| Optimize | optimize-genie-agent.md | Benchmark-driven quality tuning — gather space ID + optimization goal + benchmark target first | genie-create-eval-run; update-space |
| Export / migrate | genie-agent-cicd.md | Export, import, cross-workspace migration, batch migration, DABs/CI-CD | get-space → remap → create-space |
| — | serialized-space.md | Constructing or debugging serialized_space payloads — field schemas, constraints, Python helper | — |
| — | uc-persistence.md | Setting up UC Delta tables for multi-pass optimization history — CREATE TABLE DDL only | — |
Typical flow: create → query/validate → diagnose → optimize.
Prerequisites
- Tables in Unity Catalog — bronze/silver/gold tables with the data
- SQL Warehouse — a warehouse to execute queries (auto-detected if not specified)
Related Skills
- databricks-data-discovery - General natural-language data exploration / "ask Genie" (Genie One) across your data; use it when you are not targeting a specific curated Genie Agent
- databricks-metric-views - Build governed business metrics that Genie consumes. See SKILL.md for metric-view design rules that affect Genie answer quality, and query-patterns.md for the
MEASURE()query rules Genie must follow. - databricks-agent-bricks - Use Genie Agents as agents inside Supervisor Agents
- databricks-unity-catalog - Manage the catalogs, schemas, and tables Genie queries