Search
AI & LLM Engineering · By NVIDIA
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 97 | Co-DETR (CoDINO) for object detection. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~4.8k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 98 | Deformable DETR for 2D object detection. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~3.9k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 99 | DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. | NVIDIA/ | 3.6k | — | ~2.8k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 100 | DINOv3 continual self-supervised pre-training. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~2.2k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 101 | Grounding DINO for open-set object detection. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~3.9k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 102 | PyTorch-based TAO image classification. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~3.6k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 103 | Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. | NVIDIA/ | 3.6k | — | ~2.9k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 104 | Mask Grounding DINO for grounded instance segmentation. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~3.5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 105 | Mask2Former for universal image segmentation (panoptic, instance, and semantic). | NVIDIA/ | 3.6k | — | ~5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 106 | Metric-learning recognition (ml-recog) for fine-grained visual recognition. | NVIDIA/ | 3.6k | — | ~2.9k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 107 | NVDINOv2 for self-supervised visual representation learning. | NVIDIA/ | 3.6k | — | ~3.1k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 108 | OneFormer for universal image segmentation. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 109 | PointPillars for 3D object detection from LiDAR point clouds. | NVIDIA/ | 3.6k | — | ~4k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 110 | Person re-identification (ReID). An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~3.6k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 111 | RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. | NVIDIA/ | 3.6k | — | ~4.5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 112 | SegFormer for semantic segmentation. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~3.7k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 113 | Integrate TileGym kernels into Hugging Face transformers models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load… | NVIDIA/ | 3.6k | — | ~741 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 114 | A skill your agent uses when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. | NVIDIA/ | 3.6k | — | ~3.7k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 115 | A skill your agent uses when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in — a versioned shared library with DOCAEXPERIMENTAL-marked C entry points that… | NVIDIA/ | 3.6k | — | ~4k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 116 | A skill your agent uses for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. | NVIDIA/ | 3.6k | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 117 | A skill your agent uses when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via docagpuethrxq / docagpuethtxq, standing up the… | NVIDIA/ | 3.6k | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 118 | A skill your agent uses when the user is building, running, or interpreting the doca/tools/gpunetioibwritebw client+server benchmark — a CUDA kernel on the client posts RDMA WRITE work requests… | NVIDIA/ | 3.6k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 119 | A skill your agent uses when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and running the gpunetioibwritelat client + server pair under… | NVIDIA/ | 3.6k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 120 | Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. | NVIDIA/ | 3.6k | — | ~1.6k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 121 | Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. | NVIDIA/ | 3.6k | — | ~2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 122 | Install Holoscan SDK natively on Ubuntu via apt. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~1.6k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 123 | Install Holoscan SDK Python wheel via pip into a venv. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~1.6k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 124 | A skill your agent uses when you need to add, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a Jetson/Tegra (Orin, Thor) target. | NVIDIA/ | 3.6k | — | ~4.3k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 125 | Enable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. | NVIDIA/ | 3.6k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 126 | A skill your agent uses when you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra (Orin, Thor) target. | NVIDIA/ | 3.6k | — | ~4.4k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 127 | Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, publicsources, x-tools, guides) for the active target. | NVIDIA/ | 3.6k | — | ~3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 128 | Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. | NVIDIA/ | 3.6k | — | ~2k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 129 | A skill your agent uses when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a LinuxforTegra root on the host PC. | NVIDIA/ | 3.6k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 130 | A skill your agent uses when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python SDK — translating the consumer's own… | NVIDIA/ | 3.6k | — | ~5.8k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 131 | Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. | NVIDIA/ | 3.6k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 132 | Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. | NVIDIA/ | 3.6k | — | ~1.3k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 133 | Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. | NVIDIA/ | 3.6k | — | ~3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 134 | Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI, or MRA data from a NIfTI datalist. | NVIDIA/ | 3.6k | — | ~3.9k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 135 | Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. | NVIDIA/ | 3.6k | — | ~3.1k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 136 | Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. | NVIDIA/ | 3.6k | — | ~3.9k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 137 | Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence. | NVIDIA/ | 3.6k | — | ~2.1k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 138 | Used for running NV-Segment-CTMR on CT or MRI NIfTI volumes and recording label-map evidence. | NVIDIA/ | 3.6k | — | ~2.3k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 139 | Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and job export; use only when the request names… | NVIDIA/ | 3.6k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 140 | Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job export; use when the user names plain PyTorch or… | NVIDIA/ | 3.6k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 141 | Compute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data (count, failurecount, pixel-intensity histogram) across… | NVIDIA/ | 3.6k | — | ~3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 142 | Add a new cuTile GPU kernel operator to TileGym. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 143 | A skill your agent uses to ask the VSS agent's videounderstanding tool a fresh visual question about a recorded clip. | NVIDIA/ | 3.6k | — | ~1.4k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 144 | A skill your agent uses when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, Hermes, or maintained framework integrations before runtime configuration or… | NVIDIA/ | 3.6k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
