Databricks Core
Wire your agent to Databricks CLI auth, SQL execution, and fast table discovery without walking every catalog by hand.
Overview
databricks-core is an agent skill for the Build phase that guides Databricks CLI auth, information_schema table search, and SQL execution for data exploration.
Install
npx skills add https://github.com/databricks/databricks-agent-skills --skill databricks-coreWhat is this skill?
- Starts with system.information_schema keyword search instead of 10+ step catalog/schema/table enumeration
- Covers Databricks CLI auth profiles and experimental aitools SQL query execution
- Focused on schema discovery and ad-hoc SQL for data exploration workflows
- Branded default prompt: use $databricks-core for CLI, auth, and exploration
- Warns manual catalog enumeration wastes 10+ agent steps
Adoption & trust: 610 installs on skills.sh; 149 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need warehouse tables and SQL answers from Databricks but your agent keeps burning steps listing catalogs and schemas one by one.
Who is it for?
Solo builders with a Databricks workspace who want agent-driven discovery and SQL without manual CLI babysitting.
Skip if: Teams with no Databricks account or builders who only need static mock data with zero cloud queries.
When should I use this skill?
User asks for Databricks CLI, auth, SQL, or table discovery in a workspace.
What do I get? / Deliverables
The agent queries information_schema by keyword, runs SQL with the right CLI profile, and returns schema-aware results for downstream app or pipeline work.
- Executed SQL results
- Resolved table catalog/schema/name paths
Recommended Skills
Journey fit
Solo builders plug lakehouse data and jobs into the product during build, not at idea or launch. Databricks is an external platform integration—CLI profiles, queries, and schema lookup—not generic frontend or docs work.
How it compares
Use as a procedural Databricks CLI companion—not a hosted MCP server or generic SQL cheat sheet.
Common Questions / FAQ
Who is databricks-core for?
Indie and solo developers shipping features that read from Databricks who want their coding agent to handle CLI auth, table lookup, and SQL in one workflow.
When should I use databricks-core?
During build when integrating analytics or backend data paths—e.g. finding customer event tables before writing an API, validating metrics SQL before ship, or debugging pipeline tables in operate.
Is databricks-core safe to install?
It implies shell access to Databricks CLI and live warehouse queries; review the Security Audits panel on this page and scope CLI profiles to least-privilege before running in production workspaces.
SKILL.md
READMESKILL.md - Databricks Core
interface: display_name: "Databricks" short_description: "CLI, auth, and data exploration" icon_small: "./assets/databricks.svg" icon_large: "./assets/databricks.png" brand_color: "#FF3621" default_prompt: "Use $databricks-core for Databricks CLI, auth, and data exploration." <svg width="300" height="331" viewBox="0 0 300 331" fill="none" xmlns="http://www.w3.org/2000/svg"> <path d="M283.923 136.449L150.144 213.624L6.88995 131.168L0 134.982V194.844L150.144 281.115L283.923 204.234V235.926L150.144 313.1L6.88995 230.644L0 234.458V244.729L150.144 331L300 244.729V184.867L293.11 181.052L150.144 263.215L16.0766 186.334V154.643L150.144 231.524L300 145.253V86.2713L292.536 81.8697L150.144 163.739L22.9665 90.9663L150.144 17.8998L254.641 78.055L263.828 72.773V65.4371L150.144 0L0 86.2713V95.6613L150.144 181.933L283.923 104.758V136.449Z" fill="#FF3621"/> </svg> # Data Exploration Tools for discovering table schemas and executing SQL queries in Databricks. ## Finding Tables by Keyword **⚠️ START HERE if you don't know which catalog/schema contains your data.** Use `information_schema` to search for tables by keyword — do NOT manually iterate through `catalogs list` → `schemas list` → `tables list`. Manual enumeration wastes 10+ steps. ```bash # Find tables matching a keyword databricks experimental aitools tools query \ "SELECT table_catalog, table_schema, table_name FROM system.information_schema.tables WHERE table_name LIKE '%keyword%'" \ --profile <PROFILE> # Then discover schema for the tables you found databricks experimental aitools tools discover-schema catalog.schema.table1 catalog.schema.table2 --profile <PROFILE> ``` ## Overview The `databricks experimental aitools tools` command group provides tools for data discovery and exploration: - **discover-schema**: Batch discover table metadata, columns, types, sample data, and statistics - **query**: Execute SQL queries against Databricks SQL warehouses **When to use this**: Use these commands whenever you need to: - Discover table schemas and metadata - Execute SQL queries against warehouse data - Explore data structure and content - Validate data or check table statistics ## Prerequisites 1. **Authenticated Databricks CLI** - see [CLI Authentication Guide](databricks-cli-auth.md) for OAuth2 setup and profile configuration 2. **Access to Unity Catalog tables** with appropriate read permissions 3. **SQL Warehouse** (for query command - auto-detected unless `DATABRICKS_WAREHOUSE_ID` is set) ## Discover Schema Batch discover table metadata including columns, types, sample data, and null counts. ### Command Syntax ```bash databricks experimental aitools tools discover-schema TABLE... [flags] ``` Tables must be specified in **CATALOG.SCHEMA.TABLE** format. ### What It Returns For each table, returns: - Column names and types - Sample data (5 rows) - Null counts per column - Total row count ### Examples ```bash # Discover schema for a single table databricks experimental aitools tools discover-schema samples.nyctaxi.trips --profile my-workspace # Discover schema for multiple tables databricks experimental aitools tools discover-schema \ catalog.schema.table1 \ catalog.schema.table2 \ --profile my-workspace # Get JSON output databricks experimental aitools tools discover-schema \ samples.nyctaxi.trips \ --output json \ --profile my-workspace ``` ### Common Use Cases 1. **Understanding table structure before querying** ```bash databricks experimental aitools tools discover-schema catalog.schema.customer_data --profile my-workspace ``` 2. **Comparing schemas across multiple tables** ```bash databricks experimental aitools tools discover-schema \ catalog.schema.table_v1 \ catalog.schema.table_v2 \ --profile my-workspace ``` 3. **Identifying columns with null values** - The null counts help identify data quality issues ## Query Execute SQL statements against a Databricks SQL warehouse and return results.