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.
  1. Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation

    • Open source
    • 4K GitHub stars
  2. Routes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted

    • Open source
    • 4K GitHub stars
    • Design and media
  3. Guide an agent through GPU-accelerating a codebase: setup interview, flavor-specific translation (Fortran OpenACC, Fortran OpenMP, C++ CUDA,

    • Open source
    • 4K GitHub stars
  4. Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct

    • Open source
    • 4K GitHub stars
  5. Used for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr

    • Open source
    • 4K GitHub stars
  6. Used for generating synthetic T1, T2, FLAIR, SWI, or MRA brain MRI volumes with NV-Generate-CTMR MR-Brain v1

    • Open source
    • 4K GitHub stars
  7. Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI, or MRA data from a NIfTI datalist

    • Open source
    • 4K GitHub stars
  8. Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists

    • Open source
    • 4K GitHub stars
  9. Run NV-Reason-CT inference on user-provided 3D NIfTI chest or abdominal CT volumes for engineering and research workflows

    • Open source
    • 4K GitHub stars
  10. Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests

    • Open source
    • 4K GitHub stars
  11. Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.

    • Open source
    • 4K GitHub stars
  12. Runs standard or fixed-channel softmax finetuning of NV-Segment-CT VISTA3D on CT NIfTI image/label datasets, with optional MONAI-native MLfl

    • Open source
    • 4K GitHub stars
  13. Used for running NV-Segment-CTMR on CT or MRI NIfTI volumes and recording label-map evidence

    • Open source
    • 4K GitHub stars
  14. Build and change NVIDIA ALCHEMI Toolkit (nvalchemi) workflows for atomistic simulation and machine-learned interatomic potentials (MLIPs)

    • Open source
    • 4K GitHub stars
  15. Use for agent-assisted Auto-FL optimization of an existing NVFLARE job in simulation, POC, or production

    • Open source
    • 4K GitHub stars
  16. Generate a reproducible final report, literature-outcome synthesis, JSON summary, and refreshed progress plot for a stopped or interrupted N

    • Open source
    • 4K GitHub stars
  17. Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer),

    • Open source
    • 4K GitHub stars
    • AI models and LLM tooling
  18. Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and j

    • Open source
    • 4K GitHub stars
  19. Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and

    • Open source
    • 4K GitHub stars
  20. Compute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data

    • Open source
    • 4K GitHub stars
  21. Internal NVFLARE conversion references and templates

    • Open source
    • 4K GitHub stars
  22. Use when controlling NVIDIA Broadcast through MCP to apply effects, process local media, select devices, or change camera resolution, or whe

    • Open source
    • 4K GitHub stars
  23. Collect and package NVSHMEM put/get bandwidth, latency, and other perftest results with system and topology evidence for performance sanity

    • Open source
    • 4K GitHub stars
  24. Plan and validate NVSHMEM and NVSHMEM4Py installations

    • Open source
    • 4K GitHub stars
  25. Diagnose and optimize USD stages for slow loading, high memory, low FPS or validation; preserve asset boundaries and reuse shared definition

    • Open source
    • 4K GitHub stars
  26. Prepare and run PAIDF Cosmos Predict video generation for DEFT media samples.

    • Open source
    • 4K GitHub stars
  27. Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, met

    • Open source
    • 4K GitHub stars
    • Design and media