skill CX Codex

databricks-serverless-migration — Claude Code skill

Q: How do I install databricks-serverless-migration in Claude Code?

Run `npx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a claude-code`, then open `~/.claude/skills/databricks-serverless-migration/SKILL.md`.

Q: What does the skill need to run?

`databricks CLI` v0.292.0 or newer, plus the parent `databricks-core` skill for authentication and profile selection.

A skill that checks Databricks notebooks and jobs for serverless compatibility, names the broken parts and walks the migration step by step.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a claude-code

Open on GitHub

What databricks-serverless-migration does

Point the agent at your notebooks, jobs or pipelines and it tells you whether the workload runs on serverless compute. It first gathers the classic cluster setup: instance type, DBR version, libraries, init scripts, networking. Then it reads the code and sorts every finding into one of three buckets. Things Databricks is still adding support for, things you have to change yourself, and things that will never run on serverless.

The fixes are specific. RDD calls get rewritten to the DataFrame API, DBFS paths move to UC Volumes, Hive Metastore tables go to Unity Catalog, ProcessingTime triggers become AvailableNow. Cluster-level Spark configs are dropped, since serverless tunes them on its own. Scala JAR jobs take a separate path: build against 2.13.16, and depend on databricks-connect with % Provided scope rather than bundling spark-core.

You need databricks CLI v0.292.0 or newer. The skill also leans on the parent databricks-core skill for authentication and profile selection, so those CLI steps stall without it. Upgrading classic DBR between versions is a different job with a different compatibility surface, and this skill does not cover it. When a workload spans several notebooks, the agent handles them one at a time because the context window fills up fast otherwise.

What it helps with

check whether an existing notebook runs on serverless compute
rewrite RDD code with the DataFrame API
move DBFS paths onto UC Volumes
rebuild a Scala JAR job for serverless
strip Spark configs that serverless sets itself

Example prompts for the agent

Check etl_daily.py for anything that breaks on serverless compute
Rewrite the DBFS reads in this notebook to use UC Volumes
Rebuild build.sbt for the spark_jar_task job so it runs on serverless

How to install databricks-serverless-migration

1Skills CLI (Vercel)

npx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a claude-code

2Manually: put the files in place

~/.claude/skills/databricks-serverless-migration/SKILL.md

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

1Skills CLI (Vercel)

npx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a codex

2Manually: put the files in place

.agents/skills/databricks-serverless-migration/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a cursor

2Manually: put the files in place

.cursor/skills/databricks-serverless-migration/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install databricks/databricks-agent-skills databricks-serverless-migration

2Manually: put the files in place

.github/skills/databricks-serverless-migration/SKILL.md

1Skills CLI (Vercel)

npx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a gemini-cli

2Platform CLI

gemini skills install https://github.com/databricks/databricks-agent-skills --path skills/databricks-serverless-migration

Manually: put the files in place

.devin/skills/databricks-serverless-migration/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a opencode

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

Questions about databricks-serverless-migration

How do I install databricks-serverless-migration in Claude Code?

Run npx skills add databricks/databricks-agent-skills --skill databricks-serverless-migration -a claude-code, then open ~/.claude/skills/databricks-serverless-migration/SKILL.md.

What does databricks-serverless-migration do?

It reviews Databricks code against the serverless compute architecture and Spark Connect: RDD usage, DBFS paths, Hive Metastore, streaming triggers, init scripts, JAR tasks. Each finding comes with a concrete fix.

What does the skill need to run?

databricks CLI v0.292.0 or newer, plus the parent databricks-core skill for authentication and profile selection.

Similar skills

All skills for Data and databases →

xlsx official anthropics Creates, reads, edits, and converts spreadsheet files. Use it when the requested deliverable is an Excel workbook or another tabular file. 187,223installs google-agents-cli-observability official Google This skill guides you through tracing and monitoring AI agents, including ADK agents. Use it when you need to inspect agent execution or monitor a deployed agent. CX Codex +1 511,300installs caveman-evidence-review JuliusBrussee A read-only skill reviews Caveman Cloud evidence on LLM spend, traces, and routing. Use it to see where a project’s model budget goes. CX Codex +1 104,500installs migration JuliusBrussee Enforces reversible, compatibility-safe transitions for schema, data, and API updates. Useful whenever data loss or rollout downtime is unacceptable. CX Codex +1 103,900installs performance-optimization addyosmani An agent skill that measures before it changes code: Core Web Vitals budgets, N+1 queries, missing indexes and slow endpoints. CX Codex +1 65,200installs supabase official supabase Guides the agent through database configuration and strict RLS policies in Supabase. CX Codex GP ChatGPT 8installs

From the same set18

databricks-jobs Teaches your coding agent to build and ship Lakeflow Jobs on Databricks: tasks, dependencies, triggers, alerts. Useful when a new data pipeline should be defined in code, not clicked together. CX Codex +1 943installs databricks-lakebase This skill guides agents through Databricks Lakebase Postgres projects, app connectivity, scaling, and synced tables. Use it when working with Lakebase databases or OLTP storage. CX Codex +1 903installs databricks-dabs Teaches the agent to build, validate and deploy Declarative Automation Bundles in Databricks, covering jobs, pipelines, dashboards and apps. CX Codex +1 892installs databricks-model-serving A skill that steers the agent through Databricks Model Serving endpoint work: creation, version swaps, traffic splits, logs. Useful when model rollouts go through CLI or MLflow. CX Codex +1 715installs databricks-vector-search Skill for creating Databricks vector indexes and querying embeddings in Delta tables. Useful for RAG applications and semantic search. CX Codex +1 380installs databricks-dbsql Equips your coding agent with advanced Databricks SQL patterns, pipe syntax, H3 geospatial functions, and embedded LLM queries. CX Codex +1 364installs databricks-unity-catalog Helps agents handle Unity Catalog permissions, configure row filters and column masks, manage storage, and query system tables in Databricks. CX Codex +1 325installs databricks-app-design Design data screens for custom Databricks Apps built with AppKit/React. Use it for KPIs, reports, charts, tables, and Genie or chat views. CX Codex +1 315installs