Migrate Databricks workloads from classic compute to serverless compute. Use when migrating notebooks, jobs, pipelines, or Scala JARs (`spark_jar_task`) from classic clusters to serverless, checking if existing code is serverless-compatible, or writing new serverless-compatible code. Provides concrete fixes for the serverless Spark Connect architecture and guides the full migration.
Install
npx skills add databricks/databricks-agent-skills --skill databricks-serverless-migrationnpx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a claude-code -gnpx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a codex -ggemini skills install https://github.com/databricks/databricks-agent-skills.git --path skills/databricks-serverless-migrationgh skill install databricks/databricks-agent-skills databricks-serverless-migrationgit clone --depth 1 https://github.com/databricks/databricks-agent-skills /tmp/databricks__databricks-agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/databricks__databricks-agent-skills/skills/databricks-serverless-migration ~/.claude/skills/databricks-serverless-migration # Claude Code
cp -R /tmp/databricks__databricks-agent-skills/skills/databricks-serverless-migration ~/.agents/skills/databricks-serverless-migration # Codex, Cursor, Gemini CLI, Copilot, OpenCode