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.
/plugin marketplace add NVIDIA/skillsnpx agentmods add plugins/nvidia/skills/nvidia-skillsgit clone --depth 1 https://github.com/NVIDIA/skillsGrade A, and why
nvidia-skills 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.
What it actually says
{
"name": "nvidia-skills",
"version": "1.4.0",
"description": "Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered workflows.",
"displayName": "NVIDIA Skills",
"author": {
"name": "NVIDIA",
"url": "https://github.com/NVIDIA/skills"
},
"homepage": "https://build.nvidia.com/skills/",
"repository": "https://github.com/NVIDIA/skills",
"license": "Apache-2.0 AND CC-BY-4.0",
"keywords": [
"nvidia",
"gpu",
"cuda",
"ai-agents",
"data-loading",
"training",
"inference",
"llm-serving",
"robotics",
"simulation",
"omniverse",
"openusd",
"digital-twin",
"physical-ai",
"cad"
],
"skills": [
"./skills/"
]
}
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 · 34 lines scan A 9939db0d47e5
nvidia-skills is a plugin published in the GitHub repository NVIDIA/skills (3,172 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
arm-cortex-microcontrollers
ARM Cortex-M firmware development for Teensy, STM32, nRF52, and SAMD with peripheral drivers and memory safety patterns.
unifi-plugins
Plugin marketplace listing 3 plugins: unifi-network, unifi-protect, unifi-access.
unifi-access
UniFi Access MCP server — manage door locks, credentials, visitors, and access policies.
unifi-network
UniFi Network MCP server — manage network devices, clients, firewall, VPN, and more.
unifi-protect
UniFi Protect MCP server — manage security cameras, NVR, recordings, and smart detections.
claude-skill-homeassistant
Marketplace for the Home Assistant Manager Claude Code skill.