skills.rest
itsadijmbt
itsadijmbtCOMMUNITY
Explore all skills by this author →
GitHub

databricks-execution-compute

Routes Databricks workloads to optimal compute modes via MCP tools.

1|Updated Apr 24, 2026
Search Tags:#databricks#sql warehouse#cluster lifecycle#compute orchestration#spark execution#serverless jobs#interactive clusters
One-click install
npx skills add https://github.com/itsadijmbt/SecureMCP-Servers --skill databricks-execution-compute-itsadijmbt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: databricks-execution-compute
Source: https://github.com/itsadijmbt/SecureMCP-Servers/tree/main/TEST_SERVERS/PORTED_TO_SECUREMCP/databrickslab-mcp/ai-dev-kit/databricks-skills/databricks-execution-compute
Command: npx skills add https://github.com/itsadijmbt/SecureMCP-Servers --skill databricks-execution-compute-itsadijmbt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you execute code on Databricks reliably, choosing the right execution mode and managing compute resources so your workloads run without unnecessary setup or downtime.

Core Features & Use Cases

  • Mode selection for execution: Decide between Databricks Connect, Serverless Jobs, or Interactive Clusters based on workload needs like Spark vs non-Spark, startup time, and whether state must persist.
  • Compute orchestration tools: Run remotely with execute_code, list available clusters with list_compute, and manage cluster lifecycle with manage_cluster (including creating/starting/terminating when required).
  • SQL warehouse operations: Use manage_sql_warehouse to create/modify/delete SQL warehouses for SQL-oriented tasks.
  • Practical use case: You need to run a data generation or ETL Spark workload; pick Databricks Connect for fast local iteration, or use Serverless Job/Interactive Cluster when the job is heavy or needs state across multiple calls.

Quick Start

Use the Skill to execute your workload on Databricks by saying: "Run my Python code on Databricks using the best available compute mode for a Spark workload, and tell me what cluster or mode you used."

Frequently Asked Questions about databricks-execution-compute

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

FAQPage Schema
How do I execute Python, SQL, Scala, and R code on Databricks?▼

Databricks code execution routes your Python, SQL, Scala, and R workloads to Databricks Connect, Serverless Jobs, or Interactive Clusters based on workload type and state requirements.

What's the best way to choose between Databricks Connect, Serverless Jobs, and Interactive Clusters?▼

Choosing between Databricks Connect, Serverless Jobs, and Interactive Clusters depends on workload needs: use Databricks Connect for fast local Spark iteration, Serverless Jobs for heavy processing, and Interactive Clusters when state must persist across multiple tool calls.

Can I manage cluster lifecycle and list compute resources directly within Databricks?▼

Yes, you can manage cluster lifecycle and list compute resources directly within Databricks by using specific MCP tools to list available clusters and handle creating, starting, or terminating clusters as required for safe orchestration.

Does this Databricks compute orchestration support SQL warehouse operations?▼

Yes, Databricks compute orchestration supports SQL warehouse operations by allowing you to use dedicated management tools to create, modify, and delete SQL warehouses specifically for SQL-oriented tasks.

When should I use Serverless Jobs instead of Databricks Connect for Spark workloads?▼

You should use Serverless Jobs instead of Databricks Connect when your Spark workload is heavy or requires state to persist across multiple tool calls, whereas Databricks Connect is better suited for fast local iteration.

Related Skills

Explore More Software Engineering Skills→
rbutinarrbutinar

databricks-run

Execute Databricks Notebooks and Jobs on clusters via command line.

Community
Advanced
UnicornUnicorn

data-analysis-agent

Analyze tabular CSV, JSON, and spreadsheet datasets to produce statistical summaries, anomalies, and visualizations.

Official
Intermediate
aryan083aryan083
1

spark-engineer

Automate creation and management of Spark jobs for distributed data processing.

Community
Advanced
m19cm19c

databricks-python-sdk

Manage Databricks clusters, jobs, and SQL queries via the Python SDK.

Community
Advanced