Cosmos Dbt Core

Converts dbt Core projects into Airflow DAGs or TaskGroups using Astronomer Cosmos. The skill walks you through the config stack: project location, parsing strategy (manifest vs dbt_ls), execution mode (local, Kubernetes, virtualenv, or the faster watcher modes), warehouse connection via ProfileConfig, and test behavior. It targets Cosmos 1.11+ and Airflow 3.x but includes Airflow 2.x compatibility notes. The checklist format is helpful because Cosmos has a lot of knobs to turn, and picking the wrong load mode or execution mode will either break your setup or make it unnecessarily slow. Use this when you need dbt running inside Airflow with proper task granularity, not when you're using dbt Fusion.

skills.sh installs: 990
GitHub stars: 459
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add astronomer/agents --skill cosmos-dbt-core --agent claude-code

Installs into .claude/skills of the current project.

Files

Cosmos + dbt Core: Implementation Checklist

Execute steps in order. Prefer the simplest configuration that meets the user's constraints.

Version note: This skill targets Cosmos 1.11+ and Airflow 3.x. If the user is on Airflow 2.x, adjust imports accordingly (see Appendix A).

Reference: Latest stable: https://pypi.org/project/astronomer-cosmos/

Before starting, confirm: (1) dbt engine = Core (not Fusion → use cosmos-dbt-fusion), (2) warehouse type, (3) Airflow version, (4) execution environment (Airflow env / venv / container), (5) DbtDag vs DbtTaskGroup vs individual operators, (6) manifest availability.