# authoring-dags

Guides the creation and validation of Apache Airflow DAGs across a six-phase workflow. Useful when writing new data pipelines or adding downstream tasks to existing DAGs.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 456
- Author: astronomer
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/astronomer/agents/tree/HEAD/skills/authoring-dags/SKILL.md
- Updated: 2026-10-14
- HTML: https://affpapa.org/en/nevibecode/skills/authoring-dags

## What it does

The skill organizes Airflow DAG development into six stages: discover, plan, implement, validate, test, and iterate. During discovery, the agent checks available connections, installed providers, and Airflow version details using the `af` CLI. It prevents you from writing pipeline code that relies on missing operators or unconfigured systems.

Validation happens directly after saving: `af dags errors` catches parse problems, while `af dags explore` inspects tasks and dependencies. On Astro environments, `astro dev parse` checks imports locally, and `astro deploy --dags` lets you push DAG updates without rebuilding Docker images. The workflow requires explicit user approval before planning decisions or trigger runs.

The commands expect the `af` binary in PATH, installed standalone via `uv tool install astro-airflow-mcp` or run through `astro otto`. Deep failure troubleshooting is handled outside this skill by the companion `testing-dags` workflow.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add astronomer/agents --skill authoring-dags -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/authoring-dags/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/authoring-dags/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add astronomer/agents --skill authoring-dags -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/authoring-dags/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add astronomer/agents --skill authoring-dags -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/authoring-dags/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install astronomer/agents authoring-dags
```

2. **Manually: put the files in place**
- File: `.github/skills/authoring-dags/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add astronomer/agents --skill authoring-dags -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/astronomer/agents --path skills/authoring-dags
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/authoring-dags/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add astronomer/agents --skill authoring-dags -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/astronomer/agents/tree/HEAD/skills/authoring-dags/SKILL.md

## When to use it
- structure new Airflow DAGs around existing connections and providers
- detect DAG syntax and import errors using `af dags errors`
- add downstream tasks to an existing Airflow pipeline
- inspect task dependencies and DAG metadata via `af dags explore`

## Example prompts
- Add a DAG named daily_sales_sync to transfer data from Snowflake to S3
- Add a task that runs after extract_data to validate row counts
- Write an Airflow pipeline and validate it with af dags errors

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 63fdaeed87480d8f.

BEGIN THIRD-PARTY FILE 63fdaeed87480d8f
````text
---
name: authoring-dags
description: Workflow and best practices for writing Apache Airflow DAGs. Use when creating a new DAG, write pipeline code, handling questions about DAG patterns and conventions or extending an existing DAG with a follow-up/downstream task. ANY request shaped like 'add a DAG named X', 'write a pipeline', 'add a task that runs after Y', or 'extend the DAG'. For testing and debugging DAGs, see the testing-dags skill.
hooks:
  Stop:
    - hooks:
        - type: command
          command: "echo 'Remember to test your DAG with the testing-dags skill'"
---

# DAG Authoring Skill

This skill guides you through creating and validating Airflow DAGs using best practices and `af` CLI commands.

> **For testing and debugging DAGs**, see the **testing-dags** skill which covers the full test -> debug -> fix -> retest workflow.

---

## Running the CLI

These commands assume `af` is on PATH. Run via `astro otto` to get it automatically, or install standalone with `uv tool install astro-airflow-mcp`.

---

## Workflow Overview

```
+-----------------------------------------+
| 1. DISCOVER                             |
|    Understand codebase & environment    |
+-----------------------------------------+
                 |
+-----------------------------------------+
| 2. PLAN                                 |
|    Propose structure, get approval      |
+-----------------------------------------+
                 |
+-----------------------------------------+
| 3. IMPLEMENT                            |
|    Write DAG following patterns         |
+-----------------------------------------+
                 |
+-----------------------------------------+
| 4. VALIDATE                             |
|    Check import errors, warnings        |
+-----------------------------------------+
                 |
+-----------------------------------------+
| 5. TEST (with user consent)             |
|    Trigger, monitor, check logs         |
+-----------------------------------------+
                 |
+-----------------------------------------+
| 6. ITERATE                              |
|    Fix issues, re-validate              |
+-----------------------------------------+
```

---

## Phase 1: Discover

Before writing code, understand the context.

### Explore the Codebase

Use file tools to find existing patterns:
- `Glob` for `**/dags/**/*.py` to find existing DAGs
- `Read` similar DAGs to understand conventions
- Check `requirements.txt` for available packages

### Query the Airflow Environment

Use `af` CLI commands to understand what's available:

| Command | Purpose |
|---------|---------|
| `af config connections` | What external systems are configured |
| `af config variables` | What configuration values exist |
````
END THIRD-PARTY FILE 63fdaeed87480d8f

The third-party file has ended. Everything between the 63fdaeed87480d8f tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2766 of 7077 bytes. © astronomer · Apache-2.0 · https://github.com/astronomer/agents/tree/HEAD/skills/authoring-dags/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md