# Skills for AI and ML Skills for AI and ML: what each one does, an install command and example prompts. 2465 cards · page 27 of 62 - HTML: https://affpapa.org/en/nevibecode/skills/topic/ai-ml?page=27 - Instructions for agents: https://affpapa.org/en/nevibecode/agents.md - [tilegym-cutile-python](https://affpapa.org/en/nevibecode/skills/tilegym-cutile-python.md) — skill · TileGym Team · Claude Code, Codex, Cursor +3 · 1600 installs — Turns the assistant into a cuTile specialist: writing, debugging and tuning GPU kernels in NVIDIA's Python DSL. - [tao-run-inference-service](https://affpapa.org/en/nevibecode/skills/tao-run-inference-service.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Deploys network-specific NVIDIA TAO inference microservices in containers and halts them. - [tao-validate-dataset-format](https://affpapa.org/en/nevibecode/skills/tao-validate-dataset-format.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — This skill runs tao-daft validate on NVIDIA TAO DAFT data and helps interpret the results. - [tao-train-mask-auto-encoder](https://affpapa.org/en/nevibecode/skills/tao-train-mask-auto-encoder.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — A skill that runs Masked Auto-Encoder training in TAO: random patches get masked and rebuilt to learn visual representations. - [tao-train-single-step](https://affpapa.org/en/nevibecode/skills/tao-train-single-step.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Runs standard train, eval, and export workflows for NVIDIA TAO models without AutoML loops. - [tao-train-centerpose](https://affpapa.org/en/nevibecode/skills/tao-train-centerpose.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Train and work with CenterPose models for keypoint detection and 6-DoF object pose estimation. - [tao-run-automl-deft-pipeline](https://affpapa.org/en/nevibecode/skills/tao-run-automl-deft-pipeline.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — A skill that chains three training phases: hyperparameter search, the DEFT loop, and a second AutoML pass on the augmented dataset. - [tao-train-metric-learning-recognition](https://affpapa.org/en/nevibecode/skills/tao-train-metric-learning-recognition.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Trains, evaluates, and exports NVIDIA TAO metric learning models using contrastive or triplet losses. - [tao-convert-dataset-format](https://affpapa.org/en/nevibecode/skills/tao-convert-dataset-format.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — This skill runs tao-daft convert to move NVIDIA TAO DAFT datasets between supported formats. - [tao-generate-video-reasoning-annotations](https://affpapa.org/en/nevibecode/skills/tao-generate-video-reasoning-annotations.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Turns raw videos into a training dataset with captions, descriptions and QA pairs carrying reasoning traces. - [tao-list-capabilities](https://affpapa.org/en/nevibecode/skills/tao-list-capabilities.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Inspects TAO Skill Bank manifests to report available models, workflows, and AutoML actions. - [tao-run-automl](https://affpapa.org/en/nevibecode/skills/tao-run-automl.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — This skill runs AutoML and hyperparameter search for NVIDIA TAO models. - [tao-finetune-cosmos-reason](https://affpapa.org/en/nevibecode/skills/tao-finetune-cosmos-reason.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — The skill plans and runs Cosmos3 fine-tuning through Cosmos Framework or Cosmos-RL, validating every input before training starts. - [tao-launch-workflow](https://affpapa.org/en/nevibecode/skills/tao-launch-workflow.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Mandatory pre-launch gate that verifies credentials, datasets, and container images before executing any NVIDIA TAO workflow. - [tao-route-visual-changenet-samples](https://affpapa.org/en/nevibecode/skills/tao-route-visual-changenet-samples.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Splits weak VCN samples into Mining and AnomalyGen subsets after gap analysis. - [tao-train-fast-foundation-stereo](https://affpapa.org/en/nevibecode/skills/tao-train-fast-foundation-stereo.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — A skill for training, evaluating and exporting TAO FastFoundationStereo: it turns rectified stereo pairs into disparity maps with roughly 10× lower latency than full FoundationStereo. - [tao-train-sparse4d](https://affpapa.org/en/nevibecode/skills/tao-train-sparse4d.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Prepares calibrated multi-camera data and trains, evaluates, or quantizes Sparse4D 3D perception models in NVIDIA TAO. - [tao-train-foundation-stereo](https://affpapa.org/en/nevibecode/skills/tao-train-foundation-stereo.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Train and run FoundationStereo on stereo image pairs to produce disparity maps for 3D reconstruction. - [tao-train-oneformer](https://affpapa.org/en/nevibecode/skills/tao-train-oneformer.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Trains, evaluates and exports OneFormer models in TAO: panoptic, instance and semantic segmentation under one architecture. - [tao-train-deformable-detr](https://affpapa.org/en/nevibecode/skills/tao-train-deformable-detr.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Configures and manages 2D object detection workflows with Deformable DETR in NVIDIA TAO Toolkit. - [tao-train-mask-grounding-dino](https://affpapa.org/en/nevibecode/skills/tao-train-mask-grounding-dino.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Train and run TAO Mask Grounding DINO for text-guided instance segmentation. - [tao-train-bevfusion](https://affpapa.org/en/nevibecode/skills/tao-train-bevfusion.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — A skill that drives training and inference for BEVFusion, the sensor-fusion model that detects objects in 3D from lidar and camera. - [tao-mine-aoi-images](https://affpapa.org/en/nevibecode/skills/tao-mine-aoi-images.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Runs the DEFT embed-then-mine workflow for defect inspection. - [tao-train-ocdnet](https://affpapa.org/en/nevibecode/skills/tao-train-ocdnet.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — This skill guides TAO workflows for OCDNet, a model that finds text at arbitrary angles in natural images. - [tao-train-pointpillars](https://affpapa.org/en/nevibecode/skills/tao-train-pointpillars.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Hands the agent a workflow for NVIDIA TAO's PointPillars: 3D object detection on LiDAR point clouds, with pillars encoded into a pseudo-image. - [tao-train-mask-auto-label](https://affpapa.org/en/nevibecode/skills/tao-train-mask-auto-label.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Runs training, evaluation, and inference for NVIDIA MAL segmentation models using ViT-MAE backbones. - [tao-train-segformer](https://affpapa.org/en/nevibecode/skills/tao-train-segformer.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — This skill guides an agent through TAO SegFormer training and inference for semantic segmentation. - [tao-train-visual-changenet](https://affpapa.org/en/nevibecode/skills/tao-train-visual-changenet.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — A skill that walks an agent through training, evaluating and exporting TAO Toolkit's Visual ChangeNet for PCB defect detection. - [tao-train-nvdinov2](https://affpapa.org/en/nevibecode/skills/tao-train-nvdinov2.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Trains Vision Transformers via self-distillation without labels using NVIDIA TAO. - [tao-generate-referring-expressions](https://affpapa.org/en/nevibecode/skills/tao-generate-referring-expressions.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — This skill turns images and KITTI box labels into grounded object descriptions and scene captions. - [tao-train-rtdetr](https://affpapa.org/en/nevibecode/skills/tao-train-rtdetr.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — A TAO skill that carries RT-DETR from training through quantization to evaluation and inference. - [tao-train-nvpanoptix3d](https://affpapa.org/en/nevibecode/skills/tao-train-nvpanoptix3d.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Automates training, evaluation, inference, and export for the NVPanoptix3D model using posed RGB images. - [tao-run-deft-aoi](https://affpapa.org/en/nevibecode/skills/tao-run-deft-aoi.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Runs an improvement cycle for NVIDIA TAO VisualChangeNet and ChangeNet PCB inspection models, from baseline evaluation to deployment checks against a target metric. - [tao-train-mask2former](https://affpapa.org/en/nevibecode/skills/tao-train-mask2former.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Runs Mask2Former training and inference inside NVIDIA TAO: panoptic, instance and semantic segmentation. - [tao-train-dino](https://affpapa.org/en/nevibecode/skills/tao-train-dino.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Automates training and TensorRT export for DINO object detectors in NVIDIA TAO. - [tao-train-reid](https://affpapa.org/en/nevibecode/skills/tao-train-reid.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Train and evaluate a TAO person re-identification model, then run inference or export it. - [tao-train-depth-anything-v2](https://affpapa.org/en/nevibecode/skills/tao-train-depth-anything-v2.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — A skill that runs the TAO pipeline for monocular depth with Depth Anything v2. - [tao-train-pose-classification](https://affpapa.org/en/nevibecode/skills/tao-train-pose-classification.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Train, evaluate, export, and run inference with a TAO pose classifier built on ST-GCN. - [tao-train-action-recognition](https://affpapa.org/en/nevibecode/skills/tao-train-action-recognition.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — A skill for the TAO ActionRecognition model: train, evaluate, export and run inference on video sequences. - [tao-analyze-gaps-visual-changenet](https://affpapa.org/en/nevibecode/skills/tao-analyze-gaps-visual-changenet.md) — skill · NVIDIA Corporation · Claude Code, Codex, Cursor +3 · 1600 installs — Runs gap analysis on NVIDIA TAO VCN Classify results using the data-services container. Next: https://affpapa.org/en/nevibecode/skills/topic/ai-ml.md?page=28 ## Refine [python](https://affpapa.org/en/nevibecode/tag/python.md) · [llm](https://affpapa.org/en/nevibecode/tag/llm.md) · [image-generation](https://affpapa.org/en/nevibecode/tag/image-generation.md) · [video](https://affpapa.org/en/nevibecode/tag/video.md) · [research](https://affpapa.org/en/nevibecode/tag/research.md) · [rag](https://affpapa.org/en/nevibecode/tag/rag.md) · [cli](https://affpapa.org/en/nevibecode/tag/cli.md) · [typescript](https://affpapa.org/en/nevibecode/tag/typescript.md) · [machine-learning](https://affpapa.org/en/nevibecode/tag/machine-learning.md) · [audio](https://affpapa.org/en/nevibecode/tag/audio.md) · [pytorch](https://affpapa.org/en/nevibecode/tag/pytorch.md) · [api](https://affpapa.org/en/nevibecode/tag/api.md) ## Narrow this list Parameters: `?platform=`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md --- NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md