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. Pretrain a fresh KERMT model from scratch on a user-provided corpus

    • Open source
    • 4K GitHub stars
  2. Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfi

    • Open source
    • 4K GitHub stars
  3. Generate multiple sequence alignments (MSAs) for protein sequences using the ColabFold MSA-Search NIM

    • Open source
    • 4K GitHub stars
  4. Plan NVIDIA Parabricks pbrun commands, translate CPU options and check runtime readiness

    • Open source
    • 4K GitHub stars
  5. Run ProteinMPNN inverse folding via NVIDIA NIM to design protein sequences for a target backbone

    • Open source
    • 4K GitHub stars
  6. Run RFD4-Proteina NIM for joint protein structure and sequence design, conditioned generation, and reward-guided search using the NVIDIA hos

    • Open source
    • 4K GitHub stars
  7. Generate synthetic PCB inspection images on Kubernetes with the SMT Defect Image Generation (DIG) DAG in CDF Orchestration

    • Open source
    • 4K GitHub stars
    • Design and media
  8. Run the CDF Orchestration Event Video Generation DAG on Kubernetes or OSMO - image-to-video anomaly generation, auto-labeling, and anomaly d

    • Open source
    • 4K GitHub stars
    • Design and media
  9. Run the CDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmente

    • Open source
    • 4K GitHub stars
    • Design and media
  10. Set up missing Linux prerequisites and audit whether a Cosmos Data Factory (CDF) Orchestration checkout and its Kubernetes or OSMO environme

    • Open source
    • 4K GitHub stars
  11. Run the CDF Video Data Augmentation Airflow workflow on Kubernetes or OSMO to create Cosmos video-to-video variants and auto-label both sour

    • Open source
    • 4K GitHub stars
    • Design and media
  12. Build the first native, single-GPU cuDF path in a query engine, or complete its initial adapter

    • Open source
    • 4K GitHub stars
  13. Use when writing, running, debugging or upgrading Python code that uses NVIDIA cuML (GPU machine learning), cuml.accel (zero-code-change GPU

    • Open source
    • 4K GitHub stars
  14. cuOpt REST server — start server, endpoints, Python/curl client examples

    • Open source
    • 4K GitHub stars
  15. DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-o

    • Open source
    • 4K GitHub stars
  16. Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline

    • Open source
    • 4K GitHub stars
  17. Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end

    • Open source
    • 4K GitHub stars
  18. Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement

    • Open source
    • 4K GitHub stars
  19. Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT

    • Open source
    • 4K GitHub stars
  20. Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-a

    • Open source
    • 4K GitHub stars
  21. Use for NVIDIA DGX Spark and related GB10 system identification, capacity, troubleshooting, known issues, updates, recovery, playbooks, exam

    • Open source
    • 4K GitHub stars
  22. Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence

    • Open source
    • 4K GitHub stars
  23. Used for header-only preflight of one DICOM series folder before conversion or inference

    • Open source
    • 4K GitHub stars
  24. Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence

    • Open source
    • 4K GitHub stars
  25. Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink

    • Open source
    • 4K GitHub stars
  26. Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes

    • Open source
    • 4K GitHub stars
  27. Start or patch Dynamo router modes and run router endpoint smoke checks

    • Open source
    • 4K GitHub stars