NVIDIA/skills is a catalogue of portable instruction sets that teach coding agents how to use NVIDIA software for robotics, simulation, CUDA, retrieval-augmented generation, and related workflows. Developers install these skills in agents such as Claude Code or Codex, while the catalogue mirrors skills maintained in separate NVIDIA product repositories.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA/skills --skill doca-gpunetiogit clone --depth 1 https://github.com/NVIDIA/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia/skills/doca-gpunetio)<a href="https://agentmods.dev/skills/nvidia/skills/doca-gpunetio"><img src="https://agentmods.dev/badge/skills/nvidia/skills/doca-gpunetio.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00244 | $0.03896 |
| Opus 5 | $0.00122 | $0.01948 |
| Sonnet 5 | $0.00049 | $0.00779 |
| Haiku 4.5 | $0.00024 | $0.00390 |
Grade A, and why
doca-gpunetio scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DOCA GPUNetIO
Where to start: This skill assumes DOCA is already installed,
the CUDA toolkit is installed and matched to the DOCA install, and
the user is doing hands-on GPUNetIO work — i.e. wiring a DOCA
network queue into a CUDA kernel on an NVIDIA GPU. Open
TASKS.md if the user wants to do something
(configure / build / modify / run / test / debug); open
CAPABILITIES.md when the question is what
can GPUNetIO express on this version + this GPU. If the user has
not installed DOCA yet, route to
doca-setup first; if the user has
not set up the underlying Ethernet RX/TX queues yet, that is a
DOCA Ethernet question — route to
doca-eth.
Example questions this skill answers well
The CLASSES of GPUNetIO questions this skill is built to answer, each with one worked example. The agent should treat the class as the load-bearing piece — the worked example is a single instance.
- "How do I get a CUDA kernel to receive packets directly from
the NIC?" — worked example: "persistent kernel on one GPU
reads packets from a
doca_gpu_eth_rxqbuilt on top of a representordoca_eth_rxqand counts them per-flow". Answered by the persistent-kernel pattern inCAPABILITIES.md ## Capabilities and modes- the GPU-side bring-up workflow in
TASKS.md ## configure.
- the GPU-side bring-up workflow in
- "Can I run GPUNetIO on this GPU?" — worked example: "my
host has one Ampere card and one Turing card; which one
supports GPU-initiated networking?". Answered by the dual
capability-discovery rule (DOCA cap-query AND
cudaGetDevicePropertiesagainst the CUDA device ordinal) inCAPABILITIES.md ## Capabilities and modes- the device-enumeration step in
TASKS.md ## configure.
- the device-enumeration step in
- "Why does my GPUNetIO setup fail with
DOCA_ERROR_NOT_SUPPORTEDeven though doca-eth came up fine?" — worked example: "nvidia_peermemis not loaded so GPUDirect RDMA is unavailable". Answered by the env preconditions inCAPABILITIES.md ## Safety policy- the env checklist in
TASKS.md ## configurestep 1.
- the env checklist in
- "How do I move data between CUDA-allocated buffers and a DOCA
queue?" — worked example: "use
cudaMallocfor the receive buffer pool and register it with DOCA viadoca_buf_arr_create_*before starting the context". Answered by the CUDA-allocator- DOCA-registration overlay in
CAPABILITIES.md ## Safety policy - the buffer-prep step in
TASKS.md ## configurestep 4.
- DOCA-registration overlay in
- "Is the GPUNetIO API I'm reading about on my installed DOCA +
CUDA combination?" — worked example: "is the persistent-kernel
helper available with the CUDA toolkit version I have?".
Answered by the version-compatibility overlay in
CAPABILITIES.md ## Version compatibilitywhich cross-links the canonical detection chain indoca-versionand adds the GPUNetIO-specific DOCA must match CUDA overlay. - "What does this
DOCA_ERROR_*from a GPUNetIO call mean and which layer caused it?" — worked example: "DOCA_ERROR_DRIVERondoca_gpu_*_create— is it DOCA, CUDA, or the underlying doca-eth queue?". Answered by the GPUNetIO overlay on the cross-library taxonomy inCAPABILITIES.md ## Error taxonomy- the layered ladder in
TASKS.md ## debugthat escalates todoca-debug.
- the layered ladder in
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 299 lines · 244 tokens per session scan A 2fcc7b98f23b
doca-gpunetio is a skill published in the GitHub repository NVIDIA/skills (3,223 stars, last pushed today), licensed Apache-2.0. It adds 244 tokens to every session and 3,896 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
gpu-optimizer
GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile. Triggers on: "optimize GPU training", "speed up CUDA", "reduce OOM", "migrate NumPy to CuPy", "manage GPU memory", "benchmark PyTorch".