aidp-cluster-ops

First-time setup. Use when the user wants to install/upload the AIDP Spark connectors helper package into their AIDP workspace, or has just installed this plugin and asks "how do I set it up", "first-time setup", "install the helpers", "bootstrap aidp connectors". Drives the AIDP MCP tools to push the helper package to /Workspace/Shared/ and runs a sanity import.

Read or write Azure SQL Database from an AIDP notebook through the AIDP `aidataplatform` Spark format handler. Use when the user mentions Azure SQL, Azure SQL Database, AZURE_SQLSERVER, or a database.windows.net endpoint. Auth is SQL username/password.

Read and write Azure Data Lake Storage Gen2 (`abfss://`) from an AIDP notebook. Use when the user mentions ADLS, Azure Data Lake, abfss, or wants to ingest from a multi-cloud Azure source. Auth is OAuth client-credentials (Service Principal client_id + secret + tenant).

Read and write AWS S3 (`s3a://`) from an AIDP notebook. Use when the user mentions S3, AWS S3 bucket, s3a, or has AWS access keys. Auth is access key + secret key via the Hadoop S3A connector. boto3 is also available for non-Spark management operations (list, copy).

Connect from an AIDP notebook to Oracle AI Lakehouse (ALH), Autonomous Data Warehouse (ADW), or Autonomous Transaction Processing (ATP). Prefer the AIDP `aidataplatform` Spark format handler for wallet/password and catalog.id paths (`ORACLE_ALH` / `ORACLE_ATP`), but use raw Spark JDBC for IAM DB-token because the AIDP connector does not support DB-token auth yet.

Show the Snowflake-to-AIDP migration as a stage table before running it - which stages are supposed to run, which have run, and what each one found, with the writing stages marked. Use when the user asks what the plugin will do, what stage comes next, where a run got to, why something was skipped, or wants an overview before approving a migration - AND proactively after any stage finishes during a migration session, to report status and the next stage without waiting to be asked. Read-only; touches no environment.

Check connectivity and permissions on both ends before any migration work. Verifies Snowflake is reachable and readable (list databases, read INFORMATION_SCHEMA) and, when AIDP coordinates are supplied, that the target catalog is readable and optionally writable. Use before the first assessment, when credentials change, or whenever a stage fails with an authorization error and you need to know which end is at fault.

Provision the migration environment inside AIDP for the prod flow - the workspace (name auto-translated to the simplest safe charset), the migration-assets compute cluster, optional cluster libraries from requirements-aidp.txt, the backup-snowflake-migration/ workspace folder holding the data-migration scripts and the plan artifacts, and the migration jobs (discover, structure, reconcile, plus one copy job per schema of the approved plan, each passing its schema as a task parameter). Use when the user wants to set up AIDP for the migration, upload the migration scripts, create the migration workspace or cluster, or wire the migration jobs. Dry-run by default.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Wire dependency-cruiser into a TypeScript repo so each package is a deep module, with implementation hidden in subfolders and reachable only through its entry-point files. User-invoked.

Conduct a retrospective on a coding session.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements