# oracle-ai-data-platform-workbench-databricks-migrator

Automates migrating Databricks notebooks, job DAGs, and catalog schemas to Oracle AIDP. It runs and verifies code on a live cluster via Claude Code.

- plugin · `type=plugin` · Claude Code · ★ 57
- Author: Oracle
- License: UPL-1.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/oracle-samples/oracle-aidp-samples/tree/HEAD/ai/claude-code-plugins/oracle-ai-data-platform-workbench-databricks-migrator
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/plugins/oracle-ai-data-platform-workbench-databricks-migrator

## What it does

This plugin converts Databricks workflows and Unity Catalog DDL to run on Oracle AI Data Platform. The migration happens in two stages. First, it analyzes `%run` dependencies and rewrites syntax. Next, it submits code cell by cell to a live AIDP cluster over WebSocket, checking Spark logs and error streams. When a cell fails, the built-in loop attempts up to 10 automated fixes.

The bundled Python runtime resides inside the plugin directory under `engine/`. It requires no separate repository clone. During execution, commands such as `saveAsTable` or `INSERT INTO` are rerouted into an isolated sandbox schema. Production tables stay untouched.

Migration requires a running cluster in `Active` status. Without active compute and local OCI credentials, the verification loop will fail.

## Requirements
- Works with: Databricks

## Install

### Claude Code (native platform)

**Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin install oracle-ai-data-platform-workbench-databricks-migrator@claude-plugins-official
```
In the agent chat (not a shell):
```text
/plugin marketplace add anthropics/claude-plugins-official
```

## When to use it
- Migrate Databricks notebooks and task DAGs to an AIDP cluster
- Translate Unity Catalog table DDL into DataLake schemas
- Test and auto-repair failing notebook cells directly on live compute
- Redirect write operations into a sandbox schema to protect existing data

## Example prompts
- Run `aidp-migrator-bootstrap` to verify OCI credentials and AIDP cluster status.
- Build an AIDP migration plan for the Databricks workspace using `env-coords.md`.
- Execute `aidp-fixup-cell` on the failing cell in the converted notebook.

## Similar
- [firebase](https://affpapa.org/en/nevibecode/plugins/firebase.md) — plugin · ★ 44770
- [power-platform-architect](https://affpapa.org/en/nevibecode/plugins/power-platform-architect.md) — plugin · ★ 40451
- [power-bi-development](https://affpapa.org/en/nevibecode/plugins/power-bi-development.md) — plugin · ★ 40451
- [partners](https://affpapa.org/en/nevibecode/plugins/partners.md) — plugin · ★ 40451
- [oracle-to-postgres-migration-expert](https://affpapa.org/en/nevibecode/plugins/oracle-to-postgres-migration-expert.md) — plugin · ★ 40451
- [openapi-to-application-csharp-dotnet](https://affpapa.org/en/nevibecode/plugins/openapi-to-application-csharp-dotnet.md) — plugin · ★ 40451

From the same set: [oracle-samples/oracle-aidp-samples](https://affpapa.org/en/nevibecode/by/oracle-samples/oracle-aidp-samples.md) — 3 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md