Databricks Jobs

databricks/databricks-agent-skillsOfficial

This one's all about building and deploying Databricks Lakeflow Jobs using Asset Bundles, the Python SDK, or the CLI. It walks you through scaffolding new projects with `databricks bundle init`, configuring multi-task DAGs with dependencies, and setting up different task types like notebooks, Python wheels, SQL, dbt, and pipelines. The skill covers triggers (cron, file arrival, table updates), compute configuration with job clusters, and includes worked examples for ETL and ML workflows. The Asset Bundles approach is the recommended path here, treating your job definitions as declarative YAML that you can version control and deploy across environments. Worth invoking before you start building data engineering workflows so you set things up right from the start.

skills.sh installs: 1K
GitHub stars: 393
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add databricks/databricks-agent-skills --skill databricks-jobs --agent claude-code

Installs into .claude/skills of the current project.

Files

Lakeflow Jobs Development

FIRST: Use the parent databricks-core skill for CLI basics, authentication, profile selection, and data exploration commands.

Compute: jobs run on serverless by default. Before you choose compute or write any cluster setting, use the databricks-serverless skill; it decides serverless or classic and the performance mode.

Lakeflow Jobs orchestrate data workflows with multi-task DAGs, flexible triggers, and comprehensive monitoring. Jobs support diverse task types and can be managed via Declarative Automation Bundles (DABs), Python SDK, or CLI.