Build a Data Pipeline with MotherDuck

Use this skill when the user needs an ingestion-to-serving workflow, not just a single load step.

This is a use-case skill. It orchestrates motherduck-connect, motherduck-load-data, motherduck-model-data, motherduck-query, motherduck-share-data, and motherduck-ducklake.

Start Here: Is a MotherDuck Server Active?

Always determine this first.

• If a remote MotherDuck MCP server or local MotherDuck server is active, use it.
• If the user already knows the destination database, confirm it before designing stages.
• Explore the live environment:
  • current databases and schemas
  • raw, staging, and analytics boundaries if they already exist
  • source tables, target tables, and table grain
  • key columns, date fields, and join keys

Use that discovery to decide whether the pipeline is: