Generates a complete warehouse schema reference file by discovering all your databases, tables, and columns, then enriching them with context from dbt models, Gusty SQL, and schema docs. Runs parallel subagents to crawl multiple databases at once and identifies large tables that need date filters. The output is a version-controlled markdown file with concept-to-table mappings, categorical value families, and the data layer hierarchy. The real win is turning "find me customer data" from a 10-query fishing expedition into an instant lookup. After generation, it can append a Quick Reference table to your CLAUDE.md so the schema is always in context for queries. Run once per project, refresh when your schema changes or you want to update business context.
npx skills add https://github.com/astronomer/agents --skill warehouse-init