Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
5813 skills
NVIDIAOfficial
A mandatory safety framework for applying hardware-level changes to DPU and NIC systems.
NVIDIAOfficial
A router skill that directs NVSHMEM performance tuning requests to specialized sub-skills.
NVIDIAOfficial
Optimize OpenUSD stages for improved loading, memory usage, and rendering performance while preserving asset integrity.
NVIDIAOfficial
A systematic, layered troubleshooting framework for diagnosing and resolving NVIDIA DOCA software issues.
NVIDIAOfficial
NVIDIA CDF curation and retrieval. Cosmos Curator video and image pipelines (split, dedup, shard, annotate) with filtering, captioning, and embedding. Cosmos Dataset Search ingest, search, and capability qualification. TAO data mining embeddings and neighbor matching. Ships domain event catalogs, including workplace employee conduct monitoring, which requires legal review before use. Use when a request names Cosmos Curator, Cosmos Dataset Search, CDF, or their Make and CLI surfaces. Not for model training, orchestration, or unrelated dataset questions.
NVIDIAOfficial
Control NVIDIA display and GPU settings directly through natural language commands.
NVIDIAOfficial
Reclaim DRAM on NVIDIA Jetson devices by disabling unused subsystems like display or camera hardware.
NVIDIAOfficial
Diffusion-based anomaly detection and fine-tuning for multivariate time series data.
NVIDIAOfficial
Configure and validate CUDA graph capture in Megatron Bridge to reduce host-driver overhead during model training.
NVIDIAOfficial
Orchestrates end-to-end conversion of CAD and source assets into simulation-ready USD packages.
NVIDIAOfficial
Measure Jetson video codec performance using official SDK samples or generate documented planning estimates.
NVIDIAOfficial
A workflow for tracing and interpreting the Pareto frontier to manage tradeoffs between competing objectives in optimization problems.
NVIDIAOfficial
Safely flash FPGA firmware on HSB Lattice boards and Leopard Imaging VB1940 cameras connected to NVIDIA devkits.
NVIDIAOfficial
Executes the DEFT embed-then-mine workflow to identify similar source images for augmenting VCN AOI training datasets.
NVIDIAOfficial
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.
NVIDIAOfficial
Automated deployment of the AutoMagicCalib microservice and web UI stack using Docker Compose.
NVIDIAOfficial
Manage and publish semantic definitions within the Auto Ontology framework.
NVIDIAOfficial
Recommend and customize Megatron Bridge training and benchmark recipes based on model, hardware, and training goals.
NVIDIAOfficial
Host-side library for offloading HPC remote memory operations to a BlueField DPU via DOCA UROM.
NVIDIAOfficial
Develop, configure, and manage training and evaluation recipes for NeMo AutoModel.
NVIDIAOfficial
A tool-integration skill for using the doca_bench CLI to measure performance metrics of DOCA libraries on NVIDIA BlueField DPU or ConnectX NIC environments.
NVIDIAOfficial
Run the CDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented dataset generation. Select for requests about image attribute augmentation, person attribute search, person re-identification data, clothing augmentation, attribute captions, augmentation payloads, run status, or result retrieval. Runs environment setup first when controller readiness is unknown. Not for video or defect-image generation.
NVIDIAOfficial
Use when accelerating existing genomics workflows with NVIDIA Parabricks, improving runtime or price/performance, converting pipeline steps to GPUs, or comparing CPU and GPU workflow outputs. Adds optional GPU steps in-place with runtime toggles (default off). Do NOT use for individual pbrun command routing — use parabricks.
NVIDIAOfficial
A developer assistant for modifying, building, testing, and contributing to the NVIDIA cuOpt codebase.