oracle-ai-data-platform-workbench-suite

Operate the entire Oracle AI Data Platform (AIDP) Workbench in natural language — a 37-skill agent (not a single-engine orchestrator). Discovers your catalog into a grounding cache (FK/join hints + value dictionaries), turns plain English into accurate Spark SQL, and runs the full lakehouse SQL lifecycle (CREATE/INSERT/UPDATE/DELETE/MERGE/OPTIMIZE/VACUUM/DESCRIBE HISTORY/time-travel on the Spark/Delta lakehouse). Ingests files, profiles data and sets quality rules, authors and repairs cron pipelines, provisions clusters (Compute/AI Compute), and debugs via the Spark UI. Governs the platform (roles + per-resource permissions, credential store, Delta Sharing, audit logs, user settings; plus native Git, bundles, and MLOps/MLflow in Preview) and ships AI — Agent Flows across 13 node types with guardrails (content moderation, prompt-attack prevention, PII detection), Knowledge Base RAG, high-code LangGraph/aidputils agents, and reusable Tools. A semantic model + verified-query repository are matched before free generation for accuracy. Signature differentiators: LLM-in-SQL via ai_generate('openai.gpt-5.4', '<prompt>') and cross-source federation in one Spark session. Runs via the official Oracle aidp CLI with an oci raw-request REST fallback — under either api_key or oci-session-token auth. Additive to your Oracle stack.

Oracle AI Data Platform Workbench Spark connectors for Claude Code. 23 connector skills covering every data source workbench customers commonly need: Oracle Autonomous DB family (ALH/ADW/ATP) via wallet/IAM-DB-Token/API-key, generic Oracle Database, ExaCS, Oracle PeopleSoft, Oracle Siebel, Fusion ERP REST, Fusion BICC, EPM Cloud Planning, Essbase 21c, OCI Streaming (Kafka), OCI Object Storage, Apache Iceberg, plus PostgreSQL, MySQL/HeatWave, SQL Server, Apache Hive, Salesforce, Snowflake, Azure ADLS Gen2, AWS S3, generic REST, custom JDBC, and Excel. v0.5.0 adds 5 new connectors plus pushdown.sql / catalog.id / manifest.path patterns from oracle-samples PR #46.

Drive the Oracle AI Data Platform (AIDP) Databricks Migration Toolkit in natural language. Self-contained — the full Python engine (scripts/, aidp_compat/) ships bundled under engine/ and is invoked from skills via ${CLAUDE_PLUGIN_ROOT}/engine/scripts/. Teaches Claude how to plan and execute an automated end-to-end migration of Databricks (Unity Catalog / HMS) notebooks, jobs, schedules, and catalog DDL onto AIDP — Pass-1 dependency resolution + Pass-2 cell-by-cell execute/verify/fix on a live AIDP cluster using Claude with tool use. Covers job_migrate.py orchestration, catalog migration (18 DDL rewrite rules: 3-part→2-part name flatten, s3://→oci:// via bucket-map, source-format preserved with delta.* property scrub), workflow DAG manifest building, fixup_cell rewind, pre-migration data-availability checks, write-redirect sandbox schema, and the acceptance-contract pattern for batch/streaming convergence. Bundles 10 skills, 4 slash commands, 2 reviewer agents, and 4 reference docs + an env-coords template (cli-map, ddl-rewrite-rules, gotchas, job-report-format + env-coords.template.md).

Productized Fusion → Oracle AI Data Platform pipeline. Curated BICC extracts for the most-asked Fusion ERP/HCM/SCM datasets, bronze→silver→gold medallion architecture, conformed COA/calendar/org/supplier/item dimensions, ready-made AR-aging/AP-aging/GL-balance/PO-backlog/Supplier-spend gold marts, and MCP-native Oracle Analytics Cloud (OAC) workbook authoring. OAC AIDP connection and dataset creation remain governed manual OAC UI steps; the legacy .bar OAC REST install path still ships for snapshot deployments. End-user consumption via OAC MCP (Preview) chat in Claude/Cline/Copilot. Same pattern shown in the official Oracle blog 'Bring Fusion Data into AIDP Workbench Using BICC', productized. Additive to and complementary with Oracle's managed Fusion data offerings — never positioned as a replacement.