oracle-ai-data-platform-workbench-aws-migrator

Run the full Oracle AI Data Platform (AIDP) data-engineering surface from Codex in natural language - 37 skills: discover catalog, ask in English, AI-in-SQL, optimize/time-travel, pipelines, clusters, governance, agent flows, MLOps, migration. Self-contained (OCI CLI + api_key DEFAULT profile); the AIDP MCP is an optional accelerator.

37 skills · hooks

Oracle AI Data Platform Workbench Spark connectors for Codex. Includes 27 connector skills for Oracle, OCI, SaaS, JDBC, object storage, streaming, REST, Excel, and multi-cloud data sources, including DB2 guidance. Includes Google BigQuery read-only ingestion and external-catalog guidance.

29 skills

Migrate a Snowflake database to Oracle AI Data Platform with a fixed, auditable runbook. Provisions a migration workspace and cluster, registers the Snowflake database as an EXTERNAL catalog and creates the INTERNAL target catalog, discovers the estate with an in-AIDP workflow, translates types and names into a reviewed plan, creates the target schemas and empty Delta tables on AIDP compute, and registers one copy job per schema (INSERT-SELECT, verified by row counts) for the customer to run. Inventories what is not a table or a view, security posture and table-maintenance state, and presents the data-movement options without choosing for you. Read-only against Snowflake, dry-run by default against AIDP, every create read back; teardown releases the compute or removes everything the migration created.

11 skills · 9 commands

Build and operate Oracle Fusion-to-AIDP medallion pipelines, gold marts, OAC datasets, and MCP-authored workbooks.

16 skills · 1 MCP server

Drive the Oracle AI Data Platform (AIDP) Databricks Migration Toolkit in natural language. Self-contained for Codex: the OpenAI-based Python migration engine ships bundled under engine/ and is staged by the SessionStart hook to ~/.aidp-migrator/engine. Teaches Codex 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 plus Pass-2 cell-by-cell execute/verify/fix on a live AIDP cluster using an OpenAI model with tool use. Covers job_migrate.py orchestration, catalog migration, 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.

16 skills · hooks

Migrate Informatica ETL onto Oracle AI Data Platform from Codex: mappings become PySpark notebooks, workflows become AIDP jobs carrying the session dependency graph, Quartz schedules and a declarable timezone, with worklets expanded. Reads IDMC/IICS cloud mapping JSON and PowerCenter 10.x repository XML; 8.x and 9.x are refused by a version gate rather than mis-migrated. The transformation compiler is deterministic and needs no model -- an OpenAI key only widens what the rules cannot reach, behind a validator and a hallucination check. Reads and writes are catalog-addressed, so no JDBC URLs or credentials appear in a generated notebook. Anything that cannot be converted faithfully becomes an explicit review item with a named reason and a rebuild path, never a silent approximation.

11 skills · hooks

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Framework updates, migration planning, and architectural transformation workflows

4 skills · 3 commands · 2 agents

Long-term semantic memory for Claude Code, powered by OpenViking

5 skills · 1 command · 1 MCP server · hooks