Skip to content

Agent skills

Agent skills are folders of instructions and scripts that teach Claude Code, Codex, Cursor and other agents a task. Each one lists what it can run and how to install it.

Showing 2,281–2,310 of 3,419

  1. Run a binary industrial-inspection DEFT loop with TAO RT-DETR: measure on frozen KPI/test roles, mine gap-similar real and clean images with

    • Open source
    • 4K GitHub stars
  2. Run iterative improvement for NVIDIA TAO CLIP / SigLIP image-text retrieval on attribute-labelled data

    • Open source
    • 4K GitHub stars
  3. Run iterative DINOv3 SSL DEFT data selection and retraining from an unlabeled pool, using GRIT or multi-task weakness and fixed-encoder retr

    • Open source
    • 4K GitHub stars
  4. Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container executi

    • Open source
    • 4K GitHub stars
  5. Run a TAO training/evaluation/inference container on an NVIDIA Brev GPU instance

    • Open source
    • 4K GitHub stars
  6. The Docker execution platform for TAO jobs — a local daemon or a remote GPU box via DOCKER_HOST=ssh://user@host

    • Open source
    • 4K GitHub stars
    • Developer tools
  7. Kubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod

    • Open source
    • 4K GitHub stars
    • Developer tools
  8. Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed

    • Open source
    • 4K GitHub stars
  9. Run a Python training/eval script directly in an existing local virtualenv — no docker, no container

    • Open source
    • 4K GitHub stars
  10. One-time session setup and orchestration map for the TAO skill bank

    • Open source
    • 4K GitHub stars
  11. BEVFusion for multi-sensor 3D object detection

    • Open source
    • 4K GitHub stars
    • Design and media
  12. Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures

    • Open source
    • 4K GitHub stars
  13. DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection

    • Open source
    • 4K GitHub stars
  14. DINOv3 continual self-supervised pre-training

    • Open source
    • 4K GitHub stars
  15. Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of

    • Open source
    • 4K GitHub stars
  16. Mask2Former for universal image segmentation (panoptic, instance, and semantic)

    • Open source
    • 4K GitHub stars
  17. NVDINOv2 for self-supervised visual representation learning

    • Open source
    • 4K GitHub stars