authoring-dags

Author and validate Airflow DAGs using MCP-based guidance.

Updated Jan 15, 2026
One-click install
npx skills add https://github.com/rory-data/copilot --skill authoring-dags-rory-data
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: authoring-dags
Source: https://github.com/rory-data/copilot/tree/main/skills/authoring-dags
Command: npx skills add https://github.com/rory-data/copilot --skill authoring-dags-rory-data

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creates and validates Airflow DAGs using standardized patterns and MCP-based guidance to reduce errors and onboarding time for new DAG authors.

Core Features & Use Cases

  • DAG creation guidance: structured templates and patterns for common DAG structures.
  • Validation workflow: step-by-step MCP-based validation (import checks, DAG details, warnings).
  • Testing integration: recommended testing workflow via testing-dags skill; cross-skill synergy.

Quick Start

Create a new DAG file following the MCP workflow and validate it with the MCP tools before triggering tests.

Frequently Asked Questions about authoring-dags

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I author Airflow DAGs using standardized patterns to reduce errors?

To author Airflow DAGs with standardized patterns, this Skill provides structured templates and MCP-based guidance for creating, validating, and testing DAGs to reduce errors and onboarding time.

What is the best way to validate Airflow DAGs before triggering tests?

The best way to validate Airflow DAGs is through a step-by-step MCP-based workflow that performs import checks, reviews DAG details, and identifies warnings before executing testing workflows.

How does MCP tooling work for Airflow DAG discovery and validation?

MCP tooling for Airflow DAG discovery and validation works by enforcing safe, CLI-free interactions to standardize pattern adoption, check imports, and prevent errors across development to production environments.

Can I use MCP tools to debug Airflow DAGs in a production environment?

Yes, you can use MCP tools to debug Airflow DAGs across development to production environments, applying standardized patterns and validation workflows to prevent errors without relying on CLI interactions.

What are the limitations of authoring Airflow DAGs without CLI interactions?

Authoring Airflow DAGs without CLI interactions limits direct command-line execution, relying strictly on MCP tooling for safe discovery, validation, and testing workflows to enforce best-practice standards and prevent errors.