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 agentmods add skills/nvidia/skills/doca-programming-guidenpx skills add NVIDIA/skills --skill doca-programming-guidegit 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-programming-guide)<a href="https://agentmods.dev/skills/nvidia/skills/doca-programming-guide"><img src="https://agentmods.dev/badge/skills/nvidia/skills/doca-programming-guide.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 | $0.00246 | $0.03547 |
| Opus 5 | $0.00123 | $0.01774 |
| Sonnet 5 | $0.00049 | $0.00709 |
| Haiku 4.5 | $0.00025 | $0.00355 |
Grade A, and why
doca-programming-guide 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 2d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DOCA programming guide
Where to start: Read ## Audience to confirm the user
is consuming DOCA, not contributing to it. Then jump to the H2
that matches the verb (## modify for first-app derivation,
## build for the canonical build pattern, ## test for the test
loop, ## debug for the program-class debug ladder).
Example questions this skill answers well
These are the CLASSES of program-class questions the skill is built to answer, each with one worked example. Library-specific overlays (Flow / DMS / Caps / …) live in the matching library skill; this skill answers the library-agnostic shape.
- "How do I write my first DOCA program for <any library>?" —
worked example: "I want to write my first DOCA Flow application."
Answered by the modify-a-shipped-sample workflow in
TASKS.md ## modifyplus the canonical build pattern inTASKS.md ## build. - "What's the right build line for any DOCA library?" — worked
example: "How do I compile a program that calls
doca_rdma_*?" Answered by thepkg-config doca-<library>pattern inTASKS.md ## build(C/C++ Track 1) and the FFI/bindings pattern in Track 2. - "What's the lifecycle every DOCA object follows?" — worked
example: "What's the right order of
doca_flow_pipe_*calls in my program?" Answered by the cfg-create / init / start / use / stop / destroy template inCAPABILITIES.md ## Capabilities and modes. - "
DOCA_ERROR_*came back — what does it mean and what do I do?" — worked example: "My code gotDOCA_ERROR_BAD_STATE." Answered by the cross-librarydoca_error_get_descr()rule inCAPABILITIES.md ## Error taxonomy- the program-class debug order in
TASKS.md ## debug.
- the program-class debug order in
- "My program built and started, but does nothing on the wire." —
worked example: "My Flow program runs cleanly but no traffic is
matched." Answered by the validate-before-commit rule in
CAPABILITIES.md ## Safety policyand the layered program-class debug ladder inTASKS.md ## debug. - "What does <language> consumer of DOCA look like (FFI /
bindings)?" — worked example: "How do I call DOCA Comch from Rust
without writing C?" Answered by Track 2 of
TASKS.md ## build(FFI against the public C ABI) and the language-neutral lifecycle inCAPABILITIES.md ## Capabilities and modes. - "How should I classify and build all the shipped DOCA samples and
applications? What's the difference between a sample and an
application?" — worked example: "I tried to build all DOCA apps
and 20/159 failed — which ones are real regressions vs missing
optional stacks?" Answered by the sample-vs-application model and
the category / dependency / skip-vs-fail taxonomy in
TASKS.md ## sample-and-app-categorization, which separates "the SDK is broken" from "the optional GPU / RMAX / MPI stack is not on this BlueField".
What ships with it
6 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.
- 2d ago First seen · 262 lines · 246 tokens per session scan A a4d12cce6918
doca-programming-guide is a skill published in the GitHub repository NVIDIA/skills (3,211 stars, last pushed today), licensed Apache-2.0. It adds 246 tokens to every session and 3,547 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
html-ppt-zhangzara-daisy-days
A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.
html-ppt-zhangzara-retro-windows
An IT security-awareness training on spotting phishing — the tells, the drill, and what to do in the first 60 seconds. Built as a decision-grade professional training deck for all employees.
agent-challenges
Agent skill for challenges - invoke with $agent-challenges.
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.
onboarding-guide
Guides new users through a friendly onboarding experience.
tutorial
Interactive tutorial teaching Ouroboros hands-on.