databricks-execution-compute

Installation
SKILL.md

Databricks Execution & Compute

Run code on Databricks. Four execution modes—choose based on workload. Most examples below use the Databricks CLI (Databricks Sandbox is SDK-driven); see the databricks-core skill for install and authentication.

Execution Mode Decision Matrix

Aspect Databricks Connect ⭐ Serverless Job Interactive Cluster Databricks Sandbox
Use for Spark code (ETL, data gen) Heavy processing (ML) State across tool calls, Scala/R Untrusted / agent-generated code, isolated env
Startup Instant ~25-50s cold start ~5min if stopped ~1s (warm start)
State Within Python process None Via context_id Home dir persisted across stop/restart
Languages Python (PySpark) Python, SQL Python, Scala, SQL, R Any (general Linux shell)
Dependencies withDependencies() CLI with environments spec Install on cluster Install in sandbox, or spec.environment.image_uri (UC container artifact) for a custom image

Decision Flow

Main decision point: if you're using Declarative Automation Bundles (DABs) then follow the instructions of the databricks-dabs skill first. In short, you can use databricks bundle run to run code associated with jobs, pipelines, and other resources. This can be recognized by looking for a databricks.yml file in the project root. If these resources don't exist, or if you're not using DABs, then proceed with the below.

Installs
360
GitHub Stars
406
First Seen
Jun 26, 2026