oracle-ai-data-platform-workbench-engineer-agent Plugin
Plugin Claude Code Development Data Engineering & AnalyticsDatabases & StorageAI Agents & AI App DevelopmentThe explanation below is AI-generated. Please verify it against the sources.
This is a Claude Code plugin that provides a 37-skill "engineer agent" for operating the Oracle AI Data Platform (AIDP) Workbench in natural language. According to the README, it discovers the user's catalog into a grounding cache, translates plain English into Spark SQL, and runs the full lakehouse lifecycle (CREATE/INSERT/UPDATE/DELETE/MERGE, OPTIMIZE/VACUUM, time-travel). It also ingests files, profiles data and sets quality rules, authors and repairs pipelines, provisions clusters, and debugs jobs via the Spark UI. Beyond data operations, it covers platform governance (roles, credential store, Delta Sharing, audit logs), native Git, bundles, and MLOps/MLflow, and it runs via the official Oracle aidp CLI (falling back to oci raw-request when the CLI is not installed).
Overview
According to the homepage, Oracle AI Data Platform Workbench is a cloud service that provides the platform and framework for cataloging, ingesting, and analyzing data, and for building data analytics pipelines. The plugin described here is an agent that operates this Workbench service on behalf of the user inside Claude Code, per the README.
What you can do with oracle-ai-data-platform-workbench-engineer-agent
- Discover and explore the data catalog, building a grounding cache (catalog/semantic/verified-query files) for accurate NL-to-SQL generation (README)
- Run the Spark/Delta lakehouse SQL lifecycle: CREATE/INSERT/UPDATE/DELETE/MERGE, OPTIMIZE/VACUUM, DESCRIBE HISTORY, and time-travel (README)
- Ingest files, profile tables, and set data quality rules; monitor with observability skills (README)
- Author and repair pipelines (cron-based), provision Compute/AI Compute clusters, and debug jobs through the Spark UI (README)
- Govern the platform: roles and per-resource permissions, credential store, Delta Sharing, audit logs, Git, bundles, and MLOps/MLflow (README)
- Build and ship AI: Agent Flows (13 node types with guardrails), Knowledge Base RAG, high-code LangGraph/aidputils agents, and reusable Tools (README)
- Use signature differentiators: LLM calls inline in Spark SQL via ai_generate(), and cross-source federation in one Spark session (README)
Sources
Original description (English)
Oracle AI Data Platform (AIDP) Workbench engineer agent for Claude Code — a 37-skill agent that operates the full Spark/Delta lakehouse in natural language. Discovers your catalog into a grounding cache, turns plain English into accurate Spark SQL, and runs the lifecycle (CREATE/INSERT/UPDATE/DELETE/MERGE, OPTIMIZE/VACUUM, time-travel). Ingests files, profiles data and sets quality rules, authors and repairs pipelines, provisions clusters, and debugs via the Spark UI. Governs the platform (roles, credential store, Delta Sharing, audit logs), plus native Git, bundles, and MLOps/MLflow. Runs via the official Oracle aidp CLI.