NeVibeCode · repository · 312 items
skills: a set by nvidia
The nvidia/skills repository on GitHub: 312 cards with a description and an install command. Inside: 311 skills and 1 plugin. They install into Claude Code, Codex and Cursor.
About the repository
- GitHub
- nvidia/skills
- Stars
- ★ 4,106
- Installs across cards
- 334,469
- Licenses
- Apache-2.0, CC-BY-4.0, LicenseRef-Proprietary
- Source updated
- 2026-11-20
- In the catalog since
- 2026-10-25
tao-train-mask-grounding-dino skill tao-train-mask-grounding-dino is a Claude Code skill for training and running TAO Mask Grounding DINO for text-guided instance segmentation.
CX Codex +1
1,600installs
tao-train-bevfusion skill tao-train-bevfusion — a skill that drives training and inference for BEVFusion, the sensor-fusion model that detects objects in 3D from lidar and camera. Useful when you work with the TAO BEVFusion.
CX Codex +1
1,600installs
tao-mine-aoi-images skill tao-mine-aoi-images runs the DEFT embed-then-mine workflow for defect inspection. It finds nearest-neighbour images in a candidate pool to expand visual training datasets.
CX Codex +1
1,600installs
tao-train-ocdnet skill The tao-train-ocdnet skill guides TAO workflows for OCDNet, a model that finds text at arbitrary angles in natural images. Use it to train, evaluate, or run inference.
CX Codex +1
1,600installs
tao-train-pointpillars skill tao-train-pointpillars — a skill for training and running PointPillars, an object detector for LiDAR point clouds. Built for autonomous driving and robotics work.
CX Codex +1
1,600installs
tao-train-mask-auto-label skill tao-train-mask-auto-label runs training, evaluation, and inference for NVIDIA MAL segmentation models using ViT-MAE backbones. Helpful when creating segmentation masks from point or box annotations.
CX Codex +1
1,600installs
tao-train-segformer skill The tao-train-segformer skill guides an agent through TAO SegFormer training and inference for semantic segmentation. It also covers evaluation, export, and quantization.
CX Codex +1
1,600installs
tao-train-visual-changenet skill tao-train-visual-changenet is a Claude Code skill for training and running Visual ChangeNet in PCB AOI defect classification and segmentation.
CX Codex +1
1,600installs
tao-train-nvdinov2 skill tao-train-nvdinov2 trains Vision Transformers via self-distillation without labels using NVIDIA TAO. Useful for preparing visual backbone features without manual annotations.
CX Codex +1
1,600installs
tao-generate-referring-expressions skill The tao-generate-referring-expressions skill turns images and KITTI box labels into grounded object descriptions and scene captions. Use it to build referring-expression annotations with bbox links.
CX Codex +1
1,600installs
tao-train-rtdetr skill tao-train-rtdetr — a TAO skill that carries RT-DETR from training through quantization to evaluation and inference. Useful when you need a low-latency 2D detector and would rather not write spec files by hand.
CX Codex +1
1,600installs
tao-train-nvpanoptix3d skill tao-train-nvpanoptix3d automates training, evaluation, inference, and export for the NVPanoptix3D model using posed RGB images. Useful for 3D panoptic segmentation on Matterport and Front3D datasets.
CX Codex +1
1,600installs
tao-run-deft-aoi skill tao-run-deft-aoi runs an improvement cycle for NVIDIA TAO VisualChangeNet and ChangeNet PCB inspection models, from baseline evaluation to deployment checks against a target metric.
CX Codex +1
1,600installs
tao-train-mask2former skill tao-train-mask2former runs Mask2Former training and inference inside NVIDIA TAO: panoptic, instance and semantic segmentation. Fits when you drive segmentation work from an agent chat.
CX Codex +1
1,600installs
tao-train-dino skill tao-train-dino automates training and TensorRT export for DINO object detectors in NVIDIA TAO. Useful for managing 2D vision models via agent workflows.
CX Codex +1
1,600installs
tao-train-reid skill tao-train-reid is a Claude Code skill for training and running a TAO person re-identification model across camera views, with evaluation and export workflows.
CX Codex +1
1,600installs
tao-train-depth-anything-v2 skill tao-train-depth-anything-v2 — a skill that runs the TAO pipeline for monocular depth with Depth Anything v2. It predicts pixel depth from a single RGB frame and covers training through export.
CX Codex +1
1,600installs
tao-analyze-gaps-vlm-bcq skill tao-analyze-gaps-vlm-bcq extracts false-positive and false-negative errors from VLM binary classification predictions. It structures failure cases for root-cause analysis in NVIDIA TAO workflows.
CX Codex +1
1,600installs
tao-train-pose-classification skill tao-train-pose-classification is a Claude Code skill for training, evaluating, exporting, and running inference with a TAO ST-GCN classifier on pose-keypoint sequences.
CX Codex +1
1,600installs
tao-train-action-recognition skill tao-train-action-recognition — an NVIDIA skill that drives TAO ActionRecognition inside Docker. Train, evaluate, run inference, and export models that classify actions in video clips.
CX Codex +1
1,600installs
tao-analyze-gaps-visual-changenet skill tao-analyze-gaps-visual-changenet runs gap analysis on NVIDIA TAO VCN Classify results using the data-services container. It identifies weak boundary samples for downstream dataset augmentation.
CX Codex +1
1,600installs
tao-train-optical-inspection skill The tao-train-optical-inspection skill trains and runs a TAO optical-inspection model that finds manufacturing defects by comparing image pairs. It fits AOI and quality-control workflows.
CX Codex +1
1,600installs
tao-train-grounding-dino skill tao-train-grounding-dino — a skill for the TAO Grounding DINO model: train it, evaluate, export and run a detector that finds objects named in a text prompt.
CX Codex +1
1,600installs
tao-analyze-changenet-rca skill tao-analyze-changenet-rca performs Root Cause Analysis on NVIDIA TAO Visual ChangeNet experiments. It links classification dropouts directly to inspection image evidence.
CX Codex +1
1,600installs
tao-train-ocrnet skill tao-train-ocrnet is a Claude Code skill for training and running OCRNet to read text in cropped image regions. It supports CTC and attention-based decoders.
CX Codex +1
1,600installs
tao-generate-image-grounding skill tao-generate-image-grounding is a Claude Code skill that extracts referring phrases from image captions and assigns each phrase pixel bounding boxes for phrase-grounding data.
CX Codex +1
1,600installs
tao-train-image-classification skill tao-train-image-classification is a Claude Code skill that configures and runs PyTorch image classification in NVIDIA TAO. It supports training ResNet or EfficientNet backbones, distillation, and TensorRT export.
CX Codex +1
1,600installs
tao-port-huggingface-model skill The tao-port-huggingface-model skill ports a HuggingFace computer vision model into NVIDIA TAO Toolkit. Use it to build training, export, deployment, and container checks.
CX Codex +1
1,600installs
tao-finetune-clip skill tao-finetune-clip — a skill that walks an agent through CLIP training, zero-shot classification, embedding extraction and ONNX or TensorRT export in NVIDIA TAO.
CX Codex +1
1,600installs
tao-finetune-cosmos-embed skill tao-finetune-cosmos-embed — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that drives the full Cosmos-Embed1 lifecycle: training, inference, evaluation, and export.
CX Codex +1
1,600installs
tilegym-converting-cutile-to-julia skill tilegym-converting-cutile-to-julia converts Python cuTile GPU kernels into standalone cuTile.jl Julia code. It handles memory layout changes, 1-based indexing, and launch API differences.
CX Codex +1
1,500installs
tilegym-converting-cutile-to-triton skill tilegym-converting-cutile-to-triton turns cuTile GPU kernels into Triton ones through gated phases: analyze, convert, validate, test, benchmark. Debugging of failed ports included.
CX Codex +1
1,500installs
nemoclaw-user-guide skill nemoclaw-user-guide directs AI assistants to official NemoClaw docs via an MCP server or llms.txt. Useful when installing, running, or troubleshooting OpenClaw, Hermes, and Deep Agents.
CX Codex +1
1,300installs
cuopt-multi-objective-exploration skill cuopt-multi-objective-exploration traces Pareto frontiers for multi-objective optimization using NVIDIA cuOpt. It maps tradeoffs between competing goals when no single weighting exists.
CX Codex +1
1,300installs
jetson-diagnostic skill jetson-diagnostic collects a read-only Jetson snapshot covering device identity, memory, GPU, thermal state, power, storage, services and processes. Use it to inspect a live host.
CX Codex +1
1,300installs
nvidia-skill-finder skill nvidia-skill-finder — a skill for Claude Code discovers relevant NVIDIA ecosystem extensions from the live registry. Detects GPU, Jetson, and CUDA workflows to suggest matching tools.
CX Codex +1
1,200installs
cuopt-numerical-optimization-api skill cuopt-numerical-optimization-api — a skill for NVIDIA cuOpt: it walks the agent through modeling LP, MILP and QP problems and picking the right interface — Python, C or CLI.
CX Codex +1
1,200installs
jetson-customize-pinmux skill jetson-customize-pinmux parses a Jetson Orin or Thor pinmux XLSM and emits three BCT DTSIs, one entry per pin on a custom carrier.
CX Codex +1
1,200installs
jetson-print-device-info skill jetson-print-device-info — a skill for NVIDIA Jetson that captures device configuration: model, L4T release, kernel, OS version, and power mode. Runs on the Jetson target and is meant to record baseline state before performance testing.
CX Codex +1
1,200installs
jetson-customize-nvpmodel skill jetson-customize-nvpmodel is a Claude Code skill that edits nvpmodel configuration on Jetson Orin and Thor, including power modes, frequency caps and boot defaults.
CX Codex +1
1,200installs
121–160 of 312