oracle-ai-data-platform-workbench-databricks-migrator Plugin
Plugin Claude Code Development Migration & ModernizationData Engineering & AnalyticsDatabases & StorageThe explanation below is AI-generated. Please verify it against the sources.
This is a Claude Code plugin that lets a user drive the Oracle AI Data Platform (AIDP) Databricks Migration Toolkit in natural language, according to the README. It automates migrating Databricks notebooks, jobs, schedules, and catalog DDL onto AIDP, using a Pass-1 dependency rewrite followed by a Pass-2 cell-by-cell execute/verify/fix loop that runs on a live AIDP cluster with Claude tool use. The plugin is self-contained, bundling the full Python migrator engine under engine/, so no separate repository clone is required after install. Running an actual migration still requires prerequisites such as Python 3.10+ dependencies, OCI authentication, an Active AIDP cluster, and an ANTHROPIC_API_KEY. Per the README, the current version is v0.2.0, it is MIT-licensed, and it states that it does not collect, store, transmit, or share user data.
Overview
Per its homepage documentation, Oracle AI Data Platform Workbench is Oracle's service for cataloging, ingesting, and analyzing data, providing a platform and framework for building data analytics pipelines. This plugin is a Claude Code add-on, per the README, that drives that platform's Databricks Migration Toolkit to port Databricks workloads onto AIDP.
What you can do with oracle-ai-data-platform-workbench-databricks-migrator
- Build a migration manifest/DAG from a Databricks workspace path (aidp-build-dag)
- Scan source tables/paths for availability before migrating (aidp-check-data)
- Run an end-to-end job migration with Pass-1 dependency rewrite and Pass-2 cell-by-cell execute/verify/fix (aidp-migrate-job)
- Rewind and re-execute a failing cell from a given history index (aidp-fixup-cell)
- Resume an interrupted migration, skipping already-migrated notebooks (aidp-resume-migration)
- Migrate Unity Catalog/HMS DDL to AIDP via an 18-rule rewriter and batched replay (aidp-migrate-catalog)
- Configure s3:// to oci:// bucket/namespace mappings used by the DDL rewriter (aidp-bucket-mapping)
- Set up a consecutive-zero-window acceptance contract for batch/streaming convergence (aidp-acceptance-contract)
- Use guided slash commands such as /migrate-job, /migrate-catalog, /check-data, and /migration-status
- Use specialist agents (databricks-notebook-analyzer, migration-reviewer) to analyze source notebooks or review migrated .ipynb output
Sources
Original description (English)
Drive the Oracle AI Data Platform (AIDP) Databricks Migration Toolkit in natural language. Plans and executes automated Databricks → AIDP migrations of notebooks, jobs, schedules, and catalog DDL — Pass-1 dependency rewrite + Pass-2 cell-by-cell execute/verify/fix on a live AIDP cluster with Claude.