# doca-dpa

doca-dpa is a Claude Code skill for host-side DOCA DPA work on BlueField. It helps set up the context, launch kernels, inspect device capabilities, and troubleshoot errors.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 4106 repo stars
- Author: NVIDIA
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/NVIDIA/skills/tree/HEAD/skills/doca-dpa/SKILL.md
- Updated: 2026-10-23
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/doca-dpa

## What it does

doca-dpa guides host-side setup for a DOCA DPA application: creating its context, loading an application image, launching a kernel, and observing asynchronous completion. It also covers capability queries and `DOCA_ERROR_*` failures.

The host needs the DOCA SDK installed at `/opt/mellanox/doca` on Linux, a BlueField DPU whose DPA processor is visible to the host, and a DPACC compiler version compatible with that SDK. The listed systems are Ubuntu 22.04/24.04, RHEL, and SLES. Its validation steps depend on a live DOCA installation.

The skill helps distinguish a missing DPA processor from an unsupported hardware feature or a mismatch between the compiled image and host-side DOCA. Kernel-side DPA programming, DPACC internals, `doca-comch`, `doca-rdma`, and `doca-gpunetio` fall outside its scope.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill doca-dpa -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill doca-dpa -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill doca-dpa -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NVIDIA/skills skills/doca-dpa
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill doca-dpa -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NVIDIA/skills --path skills/doca-dpa
```

### Windsurf (Devin Desktop)

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

### 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/NVIDIA/skills/tree/HEAD/skills/doca-dpa/SKILL.md

## When to use it
- set up a `doca_dpa` context for a BlueField host
- load a `doca_dpa_app` image and launch a DPA kernel
- observe asynchronous work through `doca_dpa_completion`
- check device capabilities and diagnose `DOCA_ERROR_*` failures

## Example prompts
- Set up the host-side `doca_dpa` context and load the application image for BlueField.
- Find out why the DPA kernel launches but no completion arrives.
- Check whether this device exposes DPA and explain `DOCA_ERROR_DRIVER` on launch.

## 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: 649ab82e40ebf8c6.

BEGIN THIRD-PARTY FILE 649ab82e40ebf8c6
```text
---
license: Apache-2.0
name: doca-dpa
description: >
  Use this skill when the user is doing hands-on DOCA DPA host-side work
  on a BlueField — creating the `doca_dpa` Core context, loading a
  DPACC-compiled DPA app image (`doca_dpa_app`), creating DPA threads,
  launching kernels via `doca_dpa_kernel_launch_update_*`, draining
  `doca_dpa_completion`, running `doca_dpa_cap_*` discovery, choosing
  between the DPA comm component (inter-DPA messaging) and the DPA verbs
  component (in-kernel RDMA), or debugging `DOCA_ERROR_*` from
  `doca_dpa_*`. Trigger even without "DOCA DPA" or "Data-Path
  Accelerator": "run compute on the DPA from my host", "DPA kernel
  hangs, no completion", "DOCA_ERROR_DRIVER on launch", "DOCA/DPACC
  version skew", or "does this BlueField expose a DPA". Route elsewhere
  for DPA-side kernel programming itself, DPACC compiler internals,
  host↔DPU messaging (doca-comch), host-side RDMA (doca-rdma), and
  GPU-initiated networking (doca-gpunetio).
metadata:
  author: NVIDIA <doca-feedback@nvidia.com>
  kind: library
  doca_version: "3.5"
  tags:
    - doca
    - dpa
    - accelerator
compatibility: >
  Requires DOCA SDK installed at /opt/mellanox/doca on Linux (Ubuntu
  22.04/24.04 or RHEL/SLES) with a BlueField DPU whose generation
  exposes the DPA processor to the host, plus the matching DPACC
  compiler at a version listed compatible by the DOCA Compatibility
  Policy. Reads `pkg-config --modversion doca-dpa` and the installed
  `dpacc` version, and inspects
  /opt/mellanox/doca/{lib,include,samples/doca_dpa,applications}. The
  validation steps require a live DOCA install.
---

# DOCA DPA

## Examples

- **"Run compute on the DPA from my host."** — this is in scope.
  Stay on `doca_dpa` + a DPACC-built image; do not rewrite it as
  host-CPU or GPUNetIO.
- **"DPA kernel hangs, no completion."** — drain
  `doca_dpa_completion` and check DOCA/DPACC version skew before
  changing the kernel.

## Instructions

Follow Loading order below. Open the tasks companion for configure /
launch / debug. Open the capabilities companion for threads vs
kernels and the DPA cap query. Do not open every companion file.

**Where to start:** This skill assumes DOCA is already installed,
the user's BlueField has a DPA processor and the host can see it
through DOCA, and the user is doing **hands-on DPA work from the
host side** — i.e. using `doca-dpa` to load a DPA application
image, launch DPA kernels, and exchange data with the DPA
processor. Open the tasks companion if the user wants to *do*
something (configure / build / modify / run / test / debug); open
the capabilities companion when the question is *what
can the host-side DPA API express* on this version + this
BlueField generation. If the user has not installed DOCA yet,
route to `doca-setup/SKILL.md` first; if the
user is asking how to *write* the DPA-side kernel itself (the
code that runs on the DPA processor, compiled by `dpacc`), that
is a different scope — route via
`doca-public-knowledge-map/SKILL.md`
```
END THIRD-PARTY FILE 649ab82e40ebf8c6

The third-party file has ended. Everything between the 649ab82e40ebf8c6 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 3037 of 15911 bytes. © NVIDIA · Apache-2.0 · https://github.com/NVIDIA/skills/tree/HEAD/skills/doca-dpa/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
