# Cdf orchestration write dag

> Cdf orchestration write dag is an open-source agent skill. Use when a user describes a custom CDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-lab. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/NVIDIA/skills/tree/main/skills/cdf-orchestration-write-dag
- **Repository:** https://github.com/nvidia/skills
- **GitHub stars:** 4,037
- **License:** Apache-2.0
- **Skill name:** cdf-orchestration-write-dag
- **Collection:** https://github.com/NVIDIA/skills
- **Listing updated:** 2026-11-17

## About

Use when a user describes a custom CDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-labeling only, detection+captioning only, or image attribute augmentation without full auto-labeling — that no existing DAG in airflow/dags/workflows/ covers, and asks for a new Kubernetes DAG. Also use to check that a generated or existing DAG's model/container/prompt choices match an external spec document (e.g. a CDF `launchable.md`). Not for requests that an existing DAG already covers, including payload-only changes such as different inputs, endpoints, models, or variant counts — route those to the matching workflow skill, unless the user still wants a separate DAG after being pointed to it.

## When your agent uses it

> Use when a user describes a custom CDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-labeling only, detection+captioning only, or image attribute augmentation without full auto-labeling — that no existing DAG in airflow/dags/workflows/ covers, and asks for a new Kubernetes DAG. Also use to check that a generated or existing DAG's model/container/prompt choices match an external spec document (e.g. a CDF `launchable.md`). Not for requests that an existing DAG already covers, including payload-only changes such as different inputs, endpoints, models, or variant counts — route those to the matching workflow skill, unless the user still wants a separate DAG after being pointed to it.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/cdf-orchestration-write-dag)
- [License: Apache-2.0](https://github.com/NVIDIA/skills/tree/HEAD/skills/cdf-orchestration-write-dag)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/cdf-orchestration-write-dag` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/cdf-orchestration-write-dag &&
cp -R "$tmp/skills/cdf-orchestration-write-dag" ~/.claude/skills/cdf-orchestration-write-dag &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/cdf-orchestration-write-dag` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/cdf-orchestration-write-dag` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/cdf-orchestration-write-dag &&
cp -R "$tmp/skills/cdf-orchestration-write-dag" ~/.agents/skills/cdf-orchestration-write-dag &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/cdf-orchestration-write-dag` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/cdf-orchestration-write-dag` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/cdf-orchestration-write-dag &&
cp -R "$tmp/skills/cdf-orchestration-write-dag" ~/.cursor/skills/cdf-orchestration-write-dag &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/cdf-orchestration-write-dag` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/NVIDIA/skills.git --path skills/cdf-orchestration-write-dag
```

Or copy the folder to `~/.gemini/skills/cdf-orchestration-write-dag` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/cdf-orchestration-write-dag`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/cdf-orchestration-write-dag &&
cp -R "$tmp/skills/cdf-orchestration-write-dag" ~/.copilot/skills/cdf-orchestration-write-dag &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/cdf-orchestration-write-dag` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/NVIDIA/skills.git
```

Then copy `skills/skills/cdf-orchestration-write-dag` into your agent's skills folder as `cdf-orchestration-write-dag`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Cdf orchestration write dag in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/cdf-orchestration-write-dag to use it in all your projects, or to .claude/skills/cdf-orchestration-write-dag in one project.

### Does Cdf orchestration write dag run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Cdf orchestration write dag?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

---
Source: https://ai-powered.com/skills/cdf-orchestration-write-dag
