AI Agent Skills

NVIDIA-accelerated 3D scene reconstruction and Nav2 local costmap provider using nvblox

Deep learned, NVIDIA-accelerated 3D object pose estimation

NVIDIA-accelerated packages for arm motion planning and control

NVIDIA Isaac Transport for ROS package for hardware-acceleration friendly movement of messages

NVIDIA-accelerated, deep learned model support for image space object detection

NVIDIA-accelerated Apriltag detection and pose estimation.

GPU-ready Dockerfile to run Stability.AI stable-diffusion model v2 with a simple web interface. Includes multi-GPUs support.

Codebase for Kinova Gen3 training in Isaac Lab, sim2real transfer and ROS deployment.

Run agents like Hermes and OpenClaw more securely inside NVIDIA OpenShell with managed inference

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

NVIDIA GPU Operator creates, configures, and manages GPUs in Kubernetes

Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs

CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.

Workflow for generating synthetic data and training CV models.

NVIDIA Riva runnable tutorials

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.