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.
git 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/plugins/nvidia/skills/deepstream-dev)<a href="https://agentmods.dev/plugins/nvidia/skills/deepstream-dev"><img src="https://agentmods.dev/badge/plugins/nvidia/skills/deepstream-dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/nvidia/skills/deepstream-dev"><img src="https://agentmods.dev/badge/plugins/nvidia/skills/deepstream-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
deepstream-dev 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- deepstream-dev — 100% identical, 0 lines differ
What it actually says
{
"name": "deepstream-dev",
"description": "NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.",
"author": "NVIDIA CORPORATION",
"skills": "./"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 47 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 7 lines scan A 341b156f3d3c
deepstream-dev is a plugin published in the GitHub repository NVIDIA/skills (3,622 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
data-validation-suite
Schema validation, data quality monitoring, streaming validation pipelines, and input validation for backend APIs.
sagemaker-ai
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
concord-relay
Delivers Concord inter-agent messages into a running Claude Code session, whether it is mid-task or idle at the prompt.
odh-vllm
vLLM backport triage, cherry-pick automation, and requirements comparison.
mlops
For architects and platform engineers. Multi-agent systems, LangGraph 1.0, LLMOps, and production AI patterns. 20 skills total.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.