# Doca gpunetio

> Doca gpunetio is an open-source agent skill. Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doc. 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-gpunetio
- **Repository:** https://github.com/nvidia/skills
- **GitHub stars:** 4,037
- **License:** Apache-2.0
- **Skill name:** doca-gpunetio
- **Collection:** https://github.com/NVIDIA/skills
- **Listing updated:** 2026-11-17

## About

Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the GPU-visible queue, running the dual capability check (DOCA cap-query plus cudaGetDeviceProperties), registering cudaMalloc pools via doca_buf_arr_create_*, or debugging DOCA_ERROR_* returns from the GPUNetIO API. Trigger even when the user does not explicitly mention "DOCA GPUNetIO" or "persistent kernel" — typical implicit phrasings include "CUDA kernel reading packets directly from the NIC", "GPU-initiated networking on BlueField", "DOCA_ERROR_DRIVER on doca_gpu_create", "nvidia_peermem not loaded", "kernel-per-packet is too slow", or "which GPU supports GPU-side packet I/O". Refuse and route elsewhere for general CUDA programming, DOCA Ethernet queue bring-up, DOCA DPA, or DOCA install — those belong to other skills.

## When your agent uses it

> Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the GPU-visible queue, running the dual capability check (DOCA cap-query plus cudaGetDeviceProperties), registering cudaMalloc pools via doca_buf_arr_create_*, or debugging DOCA_ERROR_* returns from the GPUNetIO API. Trigger even when the user does not explicitly mention "DOCA GPUNetIO" or "persistent kernel" — typical implicit phrasings include "CUDA kernel reading packets directly from the NIC", "GPU-initiated networking on BlueField", "DOCA_ERROR_DRIVER on doca_gpu_create", "nvidia_peermem not loaded", "kernel-per-packet is too slow", or "which GPU supports GPU-side packet I/O". Refuse and route elsewhere for general CUDA programming, DOCA Ethernet queue bring-up, DOCA DPA, or DOCA install — those belong to other skills.

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

## Install

### Claude Code

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

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

### Codex

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

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

### Cursor

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

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

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

### VS Code

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

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

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

### Other agents

Get the folder:

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

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

## FAQ

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

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

### Does Doca gpunetio 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 gpunetio?

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-gpunetio
