MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE backbone. Use when training, evaluating, or running inference for a TAO MAL model. Trigger phrases include "train MAL", "Mask Auto-Label", "weakly-supervised segmentation", "box-prompted segmentation", "minimal-annotation mask prediction".
Install
npx skills add NVIDIA/skills --skill tao-train-mask-auto-labelnpx skills add NVIDIA/skills --skill tao-train-mask-auto-label -a claude-code -gnpx skills add NVIDIA/skills --skill tao-train-mask-auto-label -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-train-mask-auto-labelgh skill install NVIDIA/skills tao-train-mask-auto-labelgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/tao-train-mask-auto-label ~/.claude/skills/tao-train-mask-auto-label # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-train-mask-auto-label ~/.agents/skills/tao-train-mask-auto-label # Codex, Cursor, Gemini CLI, Copilot, OpenCode