databricks-genie

Create and manage Databricks Genie Spaces for natural-language SQL querying.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/aaronachermann/PolentaEncoders --skill databricks-genie-aaronachermann
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-genie
Source: https://github.com/aaronachermann/PolentaEncoders/tree/main/.github/skills/databricks-genie
Command: npx skills add https://github.com/aaronachermann/PolentaEncoders --skill databricks-genie-aaronachermann

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables teams to create, manage, export, import, migrate, and query Databricks Genie Spaces so non-technical users can explore Unity Catalog data with natural-language questions instead of writing and debugging SQL manually.

Core Features & Use Cases

  • Space Management: Idempotent create/update, get, list, and delete operations for Genie Spaces with table bindings and sample questions.
  • Conversation Querying: Programmatic natural-language question answering via the Conversation API with support for follow-up context using conversation_id.
  • Export / Import / Migration: Export serialized_space for backup or migration, perform catalog name remapping, and import or clone spaces across workspaces while preserving instructions and certified SQL examples.
  • Data Inspection & Testing: Inspect table schemas and statistics prior to space creation and execute SQL directly to validate queries.
  • Real-world Example: Export a "Sales Analytics" Genie Space from prod, remap the catalog names in the serialized payload, and import it into a dev workspace with an appropriate warehouse.

Quick Start

Ask the Sales Genie for total sales last month by calling the ask_genie tool with the target space_id and the question "What were total sales last month?".

Frequently Asked Questions about databricks-genie

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query Databricks Unity Catalog using natural language instead of SQL?

You can query Unity Catalog using natural language by creating a Databricks Genie Space with table bindings. Non-technical users then ask questions conversationally, and the Genie Space translates them into SQL queries automatically.

How do I export and import Databricks Genie Spaces between workspaces?

You can export and import Databricks Genie Spaces between workspaces by generating a serialized_space payload for backup or migration. During import, you can remap catalog names to clone the space while preserving instructions and certified SQL examples.

What permissions do I need to migrate Genie Spaces across Databricks workspaces?

Migrating Genie Spaces across Databricks workspaces requires appropriate workspace permissions, specifically CAN EDIT or create privileges. You also need access to Unity Catalog tables, a SQL warehouse, and the serialized_space operations for export and import.

Can I use the Databricks Genie Conversation API for follow-up questions?

Yes, you can use the Databricks Genie Conversation API for programmatic natural-language question answering. It supports follow-up context by passing a conversation_id, allowing multi-turn conversational data exploration against your bound tables.

How do I inspect Unity Catalog table schemas before creating a Genie Space?

You can inspect Unity Catalog table schemas and statistics prior to Genie Space creation using data inspection features. This allows you to validate table structures and execute SQL directly to test queries before binding tables to the space.

What is the best way to manage Databricks Genie Spaces programmatically?

The best way to manage Databricks Genie Spaces programmatically is through idempotent create, update, get, list, and delete operations. This allows you to manage table bindings and sample questions while maintaining conversational data exploration capabilities.