Warehouse Init

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.

skills.sh installs: 841
GitHub stars: 459
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add astronomer/agents --skill warehouse-init --agent claude-code

Installs into .claude/skills of the current project.

Files

Initialize Warehouse Schema

Generate a comprehensive, user-editable schema reference file for the data warehouse.

Scripts: ../analyzing-data/scripts/ — All CLI commands below are relative to the analyzing-data skill's directory. Before running any scripts/cli.py command, cd to ../analyzing-data/ relative to this file.

What This Does

Discovers all databases, schemas, tables, and columns from the warehouse
Enriches with codebase context (dbt models, gusty SQL, schema docs)
Records row counts and identifies large tables
Generates .astro/warehouse.md - a version-controllable, team-shareable reference
Enables instant concept→table lookups without warehouse queries

Process

Step 1: Read Warehouse Configuration

cat ~/.astro/agents/warehouse.yml

Get the list of databases to discover (e.g., databases: [HQ, ANALYTICS, RAW]).

Step 2: Search Codebase for Context (Parallel)

Launch a subagent to find business context in code:

Task(
    subagent_type="Explore",
    prompt="""
    Search for data model documentation in the codebase:

SKILL.md on GitHub

Details

Repository: github.com/astronomer/agents
Categories: Frontend Development, Sales & Marketing
First seen: Jun 3, 2026