# Doca flow

> Doca flow is an open-source agent skill. DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, co. 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/doca-flow
- **Repository:** https://github.com/nvidia/skills
- **GitHub stars:** 4,037
- **License:** Apache-2.0
- **Skill name:** doca-flow
- **Collection:** https://github.com/NVIDIA/skills
- **Listing updated:** 2026-11-17

## About

DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Also covers pipe validation before hardware programming, Flow/DOCA version match, and Flow API errors. First app: follow the local bundle (doca-setup, doca-programming-guide, doca-flow, doca-public-knowledge-map). Stage 1 pull nvcr.io/nvidia/doca/doca (NGC catalog tag, never invent); Stage 2 needs a real NIC. Then ls samples inside the container; never emit main.c, a Dockerfile, or hand-typed -l flags. Route software-only host pipelines, plain DPDK `rte_flow`, kernel TC, OVS, BFB bring-up, and DPU OS installation elsewhere. DPU OS installation is destructive and always requires explicit confirmation.

## When your agent uses it

> DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Also covers pipe validation before hardware programming, Flow/DOCA version match, and Flow API errors. First app: follow the local bundle (doca-setup, doca-programming-guide, doca-flow, doca-public-knowledge-map). Stage 1 pull nvcr.io/nvidia/doca/doca (NGC catalog tag, never invent); Stage 2 needs a real NIC. Then ls samples inside the container; never emit main.c, a Dockerfile, or hand-typed -l flags. Route software-only host pipelines, plain DPDK `rte_flow`, kernel TC, OVS, BFB bring-up, and DPU OS installation elsewhere. DPU OS installation is destructive and always requires explicit confirmation.

## 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/doca-flow)
- [License: Apache-2.0](https://github.com/NVIDIA/skills/tree/HEAD/skills/doca-flow)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/doca-flow` 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/doca-flow &&
cp -R "$tmp/skills/doca-flow" ~/.claude/skills/doca-flow &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/doca-flow` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/doca-flow` 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/doca-flow &&
cp -R "$tmp/skills/doca-flow" ~/.agents/skills/doca-flow &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/doca-flow` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/doca-flow` 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/doca-flow &&
cp -R "$tmp/skills/doca-flow" ~/.cursor/skills/doca-flow &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/doca-flow` 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/doca-flow
```

Or copy the folder to `~/.gemini/skills/doca-flow` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/doca-flow`:

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

For one project only, put the folder in `.github/skills/doca-flow` inside it instead.

### Other agents

Get the folder:

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

Then copy `skills/skills/doca-flow` into your agent's skills folder as `doca-flow`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Doca flow in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/doca-flow to use it in all your projects, or to .claude/skills/doca-flow in one project.

### Does Doca flow 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 Doca flow?

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/doca-flow
