OpenClaw · Skills: AI & machine learning

Skills from verified OpenClaw publishers, and official plugins. Each entry links to its ClawHub page, which shows the current security scan.

NVIDIA TAO skill for running training or eval scripts in a local virtualenv without containers.

NVIDIA TAO skill for verifying and installing GPU driver, CUDA, and toolkit versions.

NVIDIA TAO skill for training video action recognition on RGB, optical flow, or joint inputs.

NVIDIA TAO skill for training BEVFusion 3D detection from LiDAR and camera data.

NVIDIA TAO skill for training CenterPose keypoint and object pose estimation.

NVIDIA TAO skill for training Co-DETR (CoDINO) object detectors.

NVIDIA TAO skill for training Deformable DETR 2D object detectors.

NVIDIA TAO skill for training monocular depth estimation with Depth Anything v2.

NVIDIA TAO skill for training DINO transformer detectors with denoising anchor boxes.

NVIDIA TAO skill for continual self-supervised pretraining of DINOv3 backbones on unlabeled images.

NVIDIA TAO skill for training FastFoundationStereo real-time stereo depth models.

NVIDIA TAO skill for training FoundationStereo disparity models for 3D reconstruction.

NVIDIA TAO skill for training Grounding DINO text-prompted open-set detectors.

NVIDIA TAO skill for training PyTorch image classifiers with distillation and quantization.

NVIDIA TAO skill for MAE pretraining and fine-tuning on unlabeled images.

NVIDIA TAO skill for weakly supervised segmentation masks from points or boxes.

NVIDIA TAO skill for training Mask Grounding DINO text-guided instance segmentation.

NVIDIA TAO skill for training Mask2Former panoptic, instance, and semantic segmentation.

NVIDIA TAO skill for training embeddings for fine-grained recognition and matching.

NVIDIA TAO skill for training NVDINOv2 self-supervised visual features without labels.