Language:JapaneseEnglish

data-engineering Claude Code Plugin

Topics
Data Engineering & Analytics · Databases & Storage · Cloud, Deployment & CI/CD
First cataloged
2026-07-09 (UTC)
Explanation last updated
2026-07-16 (UTC)
Source (GitHub) last updated
2026-08-05 (UTC) (22 days ago)

The explanation below is AI-generated. Please verify it against the sources.

This plugin adds data engineering tooling to Claude Code, centered on an MCP server that connects to Apache Airflow instances and a collection of skills for warehouse work and DAG development. According to the README, it bundles the Airflow MCP server together with more than 20 skills covering schema discovery, SQL analysis, lineage tracing, DAG authoring, testing, debugging, dbt integration via Cosmos, and migration from Airflow 2.x to 3.x. It works with either self-hosted open source Airflow or Astronomer's Astro platform, and it can connect to warehouses such as Snowflake, PostgreSQL, BigQuery, and other databases through SQLAlchemy. A terminal CLI named af is also included for direct interaction with an Airflow instance. Installation is done as a Claude Code plugin or via a skills installer, and configuration relies on local YAML and environment files for warehouse and Airflow credentials.

About the service

Astro is Astronomer's managed hosting platform for Apache Airflow, offering deployment management, observability, and an AI assistant called Otto according to the homepage. The plugin's tooling can target either an Astro deployment or a self-managed open source Airflow instance, connecting through the Airflow REST API.

What you can do with data-engineering

  • Generate warehouse schema metadata for faster lookups via the warehouse-init skill
  • Run SQL-based data analysis using a background Jupyter kernel
  • Check data freshness and profile tables for quality issues
  • Trace upstream and downstream data lineage and annotate task-level lineage
  • Author, test, and debug Apache Airflow DAGs
  • Deploy Airflow projects to Astro, Docker Compose, or Kubernetes
  • Run dbt Core or dbt Fusion projects as Airflow DAGs through Cosmos
  • Migrate existing DAGs from Airflow 2.x to Airflow 3.x
  • Use the af CLI to list DAGs, trigger runs, and check Airflow health from the terminal

Sources

Back to list