OpenClaw · Skills: Media & design

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

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

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

NVIDIA TAO skill for training OneFormer universal segmentation with task-conditioned queries.

NVIDIA TAO skill for training Siamese-network defect detection on image pairs.

NVIDIA TAO skill for training PointPillars LiDAR 3D detectors.

NVIDIA TAO skill for Visual ChangeNet pass/fail classification and change segmentation in AOI.

AWS skill for threat-modeling spec and design documents with AWS Security Agent.

NVIDIA skill for adding, changing, or debugging autotuning in cuTile kernels.

AWS skill giving authoritative guidance on Timestream for InfluxDB across its editions.

Pulls still frames or brief clips out of video files using ffmpeg.

Downloads videos, audio, subtitles, and transcripts from YouTube and other supported sites.

NVIDIA skill for putting a new visual question about a clip to the VSS agent.

NVIDIA skill for deploying the standalone RT-VLM captioner and calling its REST API.

NVIDIA skill for deploying MV3DT 3D detection with BEV fusion across calibrated cameras.

NVIDIA skill for deploying and integrating the VSS video embedding microservice.

NVIDIA skill for running AutoMagicCalib camera calibration on videos or the sample data.

NVIDIA skill for producing VSS analysis reports from per-clip VLM or incident ranges.

NVIDIA skill for calling the VIOS REST API for sensors, timelines, clips, and snapshots.

NVIDIA skill for reading video analytics data through the VSS VA-MCP server.