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

How to start

1. Paste the command into Claude Code and press Enter.
2. Restart Claude Code so the plugin loads.
3. Try it: type /check-data or /migrate-catalog.

What it adds

4 commands · 2 agents · 10 skills

Commands Type it in Claude Code

• /check-dataPre-migration data-availability scan. Reads a manifest, probes every spark.read.* / saveAsTable target on the AIDP cluster, reports OK / MISSING / EMPTY.
• /migrate-catalogGuided catalog migration flow. Extract Databricks Unity Catalog / HMS metadata, preview the 18-rule DDL rewrite, then batched replay on AIDP. Asks before destr…
• /migrate-jobGuided full-job migration flow. Walks the user from "I want to migrate this Databricks job" through DAG → data check → migrate → status, asking before each pha…
• /migration-statusParse + summarize the JOB_REPORT.md produced by a prior migration run. Surfaces cell pass/fail/fix counts per task, lists the failing cells, and recommends a n…

Agents Claude hands work to these

• databricks-notebook-analyzerUse this agent when the user has pointed at a single Databricks notebook (.ipynb / .py / .scala) and wants to know what it does, what it depends on, what risks…
• migration-reviewerUse this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loo…

Skills Claude loads these when the task fits

• aidp-acceptance-contractYAML-driven acceptance contract for batch and streaming pipelines that need convergence verification, not just "no exceptions". Declares PASS only after K cons…
• aidp-bucket-mappingConfigure the s3:// → oci:// bucket / namespace mapping the migrator uses to rewrite paths during notebook + catalog migration. Use when (a) the user has exter…
• aidp-build-dagBuild a migration manifest (the execution DAG) from a Databricks workspace path or workflow ID. Walks %run dependency chains, captures dbutils.notebook.run inv…
• aidp-check-dataPre-migration data-availability scan. Reads every notebook in a migration manifest, extracts every spark.read.table / spark.read.parquet / saveAsTable referenc…
• aidp-fixup-cellTargeted rewind of a migrated notebook. Re-executes cells from history index N onwards (or a specific cell range) through the execute+verify+fix loop, with a '…
• aidp-migrate-catalogMigrate Databricks Unity Catalog / HMS schemas + tables onto AIDP. Two-stage extract→rewrite→replay pipeline. The rewriter applies 18 DDL rules (3-part→2-part…
• aidp-migrate-jobRun the full Databricks→AIDP migration against a manifest. Pass-1 walks the %run dep tree and rewrites Databricks APIs in each dep notebook code-only. Pass-2 e…
• aidp-migrator-bootstrapOne-shot environment readiness check for the Oracle AIDP Databricks migrator. Verifies Python deps, OCI auth, AIDP cluster reachability, and your env-coords fi…
• aidp-migrator-overviewRouter skill. Read this first whenever the user mentions migrating a Databricks workload (notebooks, jobs, catalogs, schedules) onto Oracle AI Data Platform (A…
• aidp-resume-migrationResume an interrupted migration. The migrator caches already-migrated notebooks (in-memory + on-cluster) so subsequent runs skip them. Use when a prior aidp-mi…

Read from the plugin's own files in oracle-samples/oracle-aidp-samples, 26 Oct 2026.

What it needs

No keys or settings: its files ask for none.