Databricks Python Sdk

This gives Claude everything it needs to work with Databricks: the Python SDK for managing resources, Databricks Connect for running Spark locally, CLI commands, and direct REST API access when the SDK doesn't cut it. The documentation coverage is solid, with clear examples for clusters, jobs, SQL warehouses, and Unity Catalog operations. I like that it includes the predictable URL patterns for the SDK docs and explicitly warns against common mistakes like setting master mode in Databricks Connect. If you're writing code that talks to Databricks instead of just notebooks in the UI, this is the reference you want loaded.

skills.sh installs: 183
GitHub stars: 2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add databricks-solutions/ai-dev-kit --skill databricks-python-sdk --agent claude-code

Installs into .claude/skills of the current project.

Files

Databricks Development Guide

This skill provides guidance for Databricks SDK, Databricks Connect, CLI, and REST API.

SDK Documentation: https://databricks-sdk-py.readthedocs.io/en/latest/ GitHub Repository: https://github.com/databricks/databricks-sdk-py

Environment Setup

Use existing virtual environment at .venv or use uv to create one
For Spark operations: uv pip install databricks-connect
For SDK operations: uv pip install databricks-sdk
Databricks CLI version should be 0.278.0 or higher

Configuration

Default profile name: DEFAULT
Config file: ~/.databrickscfg
Environment variables: DATABRICKS_HOST, DATABRICKS_TOKEN

Databricks Connect (Spark Operations)

Use databricks-connect for running Spark code locally against a Databricks cluster.

from databricks.connect import DatabricksSession

# Auto-detects 'DEFAULT' profile from ~/.databrickscfg
spark = DatabricksSession.builder.getOrCreate()

# With explicit profile
spark = DatabricksSession.builder.profile("MY_PROFILE").getOrCreate()

# Use spark as normal
df = spark.sql("SELECT * FROM catalog.schema.table")
df.show()

SKILL.md on GitHub