databricks-execution-compute

Execute Spark, Python, SQL, Scala, and R code on Databricks compute resources.

31|18|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/ThomazRossito/data-agents --skill databricks-execution-compute
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-execution-compute
Source: https://github.com/ThomazRossito/data-agents/tree/main/skills/databricks/databricks-execution-compute
Command: npx skills add https://github.com/ThomazRossito/data-agents --skill databricks-execution-compute

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It removes the complexity of choosing and managing the right Databricks compute option for running Spark, Python, SQL, Scala, or R workloads, while handling cluster lifecycle and cost considerations.

Core Features & Use Cases

  • Execution Mode Decision Matrix: Guides selection between Databricks Connect, Serverless Jobs, and Interactive Clusters based on workload characteristics.
  • MCP Tools: execute_code, list_compute, manage_cluster, and manage_sql_warehouse enable running code, discovering resources, and managing clusters or warehouses.
  • Use Cases: Fast Spark development with Connect, heavy ML training on Serverless Jobs, or stateful multi-step pipelines on Interactive Clusters.

Quick Start

Ask the assistant to run my data processing script on Databricks with the appropriate compute mode.

Frequently Asked Questions about databricks-execution-compute

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

FAQPage Schema
How do I choose between Databricks Connect, Serverless Jobs, and Interactive Clusters for running Spark workloads?

Choosing the right Databricks compute depends on workload characteristics: use Databricks Connect for fast Spark development, Serverless Jobs for heavy ML training, and Interactive Clusters for stateful multi-step pipelines. An execution mode decision matrix guides the selection.

Can I execute Python, SQL, Scala, and R code on Databricks using MCP tools?

Yes, you can execute Python, SQL, Scala, and R code on Databricks using the execute_code MCP tool. It supports running workloads across Databricks Connect, serverless jobs, and interactive clusters.

What's the best way to manage Databricks cluster lifecycle and SQL warehouses programmatically?

The best way to manage Databricks compute resources programmatically is by using the manage_cluster and manage_sql_warehouse MCP tools. These tools enable discovering resources with list_compute and handling cluster lifecycle and cost considerations.

Do I need Python 3.12 and databricks-connect configuration to run code on Databricks?

Yes, you need Python 3.12 and databricks-connect configuration to satisfy the requirements for running code via Databricks Connect. These prerequisites ensure proper execution and management of your Databricks compute resources.

When should I use Databricks Serverless Jobs instead of Interactive Clusters for data processing?

Use Databricks Serverless Jobs for heavy ML training and isolated task execution, whereas Interactive Clusters are better suited for stateful multi-step pipelines. The execution mode decision matrix helps determine the optimal compute choice based on workload characteristics.