Skip to main content
skill CX Codex

databricks-execution-compute — Claude Code skill

databricks-execution-compute is a skill that runs code on Databricks and helps choose a compute mode for Spark scripts, longer jobs, and interactive clusters.

no license 359 installs ★ 408 updated 2026-11-03

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add databricks/databricks-agent-skills --skill databricks-execution-compute -a claude-code
Open on GitHub

What databricks-execution-compute does

This skill guides code execution on Databricks with Python, Scala, SQL, or R. It points Spark workloads toward Databricks Connect and longer-running work, such as ML, toward serverless jobs. Read the reference for the selected mode before running it. The skill requires Databricks CLI version 1.0.0 or later; databricks-core covers CLI setup and authentication.

The CLI workflow can upload a notebook, submit a job, check its state, and retrieve its output. It also supports cluster discovery and compute management. Interactive clusters take 3–8 minutes to start and incur charges while running, so the skill advises against launching one without a clear need.

What it helps with

  • run a Spark script through Databricks Connect
  • submit a long-running ML task as a serverless job
  • check a run's status and retrieve its output
  • find available clusters before choosing one

Example prompts for the agent

  • Run my_spark_script.py locally through Databricks Connect.
  • Submit train.py as a serverless job and return its result.
  • List clusters with databricks clusters list --output json and ask me which one to use.

How to install databricks-execution-compute

1Skills CLI (Vercel)

npx skills add databricks/databricks-agent-skills --skill databricks-execution-compute -a claude-code

2Manually: put the files in place

~/.claude/skills/databricks-execution-compute/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/databricks-execution-compute/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about databricks-execution-compute

How do I install databricks-execution-compute in Claude Code?

Run npx skills add databricks/databricks-agent-skills --skill databricks-execution-compute -a claude-code. The skill file is at ~/.claude/skills/databricks-execution-compute/SKILL.md.

What does databricks-execution-compute do?

It guides code execution on Databricks and compute management through the Databricks CLI. It routes Spark work toward Databricks Connect and longer jobs toward serverless execution.

Which Databricks CLI version does the skill require?

Use Databricks CLI version 1.0.0 or later. databricks-core covers CLI installation and authentication.

Similar skills

All skills for Data and databases →

From the same set30

The whole set →
databricks-ai-functions Use this skill to add Databricks AI Functions to SQL and PySpark pipelines, or to prepare documents for a custom RAG workflow. CX Codex +1 372installs databricks-metric-views The databricks-metric-views skill writes governed business metrics as YAML and checks whether a given measure belongs in a metric view at all. CX Codex +1 371installs databricks-aibi-dashboards Builds Databricks AI/BI dashboards from the ground up: knows the Lakeview JSON layout and makes the agent run every SQL query through the CLI first. CX Codex +1 366installs databricks-apps-python databricks-apps-python — a skill for Claude Code, Codex, Cursor and other agents that adds Python backend support for Databricks Apps. CX Codex +1 363installs databricks-python-sdk Guidance for building with the Databricks Python SDK, Connect, CLI, and REST API. Use it when your code needs to work with Databricks services. CX Codex +1 358installs databricks-mlflow-evaluation databricks-mlflow-evaluation — a skill for running mlflow.genai.evaluate(), building scorers and datasets, aligning judges with MemAlign, and watching production quality on Databricks. CX Codex +1 355installs databricks-ml-training databricks-ml-training is a skill for training classifiers and regressors on Databricks with XGBoost, scikit-learn, LightGBM, or PyTorch, and tracking runs with MLflow. CX Codex +1 354installs databricks-lakeflow-connect databricks-lakeflow-connect — a skill for Claude Code builds and debugs Lakeflow Connect ingestion from SQL Server, PostgreSQL, MySQL, and Oracle into Unity Catalog. It covers CDC and query-based loads. CX Codex +1 348installs

Project sponsors

Companies that keep this analytics open