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 1,891–1,920 of 3,419

  1. Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, null

    • Open source
    • 4K GitHub stars
  2. Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API

    • Open source
    • 4K GitHub stars
  3. Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API

    • Open source
    • 4K GitHub stars
    • Design and media
  4. Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose

    • Open source
    • 4K GitHub stars
  5. Use Boltz2 NIM for biomolecular structure prediction and binding affinity

    • Open source
    • 4K GitHub stars
  6. Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.

    • Open source
    • 4K GitHub stars
  7. Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning

    • Open source
    • 4K GitHub stars
  8. Validate, prepare, or run public CodonFM Encodon masked-codon variant scoring and review compatibility of its scoring workflows

    • Open source
    • 4K GitHub stars
  9. Set up the public CodonFM v1 repository and download public Encodon checkpoints

    • Open source
    • 4K GitHub stars
  10. Agent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI

    • Open source
    • 4K GitHub stars
  11. Agent runbook for Proteina-Complexa parameter sweeps through the separately installed first-party CLI and config generator

    • Open source
    • 4K GitHub stars
  12. Add, edit, inspect, or validate Proteina-Complexa target definitions for protein binders, ligand binders, and AME motif scaffolding

    • Open source
    • 4K GitHub stars
  13. Use when defining cuEquivariance groups and irreps, building equivariant tensor products, or validating segmented polynomials with NumPy.

    • Open source
    • 4K GitHub stars
  14. Use when writing or debugging cuEquivariance JAX polynomials, irrep dictionaries, Flax NNX layers, or CPU/CUDA execution and layouts.

    • Open source
    • 4K GitHub stars
  15. Use when building or debugging cuEquivariance PyTorch tensor products or equivariant GNNs, especially CPU references, layouts, indexing, and

    • Open source
    • 4K GitHub stars
  16. Run DiffDock molecular docking via NVIDIA NIM to predict small-molecule binding poses against protein targets

    • Open source
    • 4K GitHub stars
  17. NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call

    • Open source
    • 4K GitHub stars
    • Health and science
  18. Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice

    • Open source
    • 4K GitHub stars
  19. Generate novel drug-like molecules using the GenMol NIM microservice

    • Open source
    • 4K GitHub stars
  20. Use when accelerating existing genomics workflows with NVIDIA Parabricks, improving runtime or price/performance, converting pipeline steps

    • Open source
    • 4K GitHub stars
    • Health and science
  21. Convert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM deco

    • Open source
    • 4K GitHub stars
  22. Continue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint

    • Open source
    • 4K GitHub stars
  23. Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint

    • Open source
    • 4K GitHub stars
  24. Finetune a pretrained KERMT encoder on a labeled CSV

    • Open source
    • 4K GitHub stars
  25. Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV

    • Open source
    • 4K GitHub stars
  26. Check progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation)

    • Open source
    • 4K GitHub stars
  27. Pretrain a fresh KERMT model from scratch on a user-provided corpus

    • Open source
    • 4K GitHub stars
  28. 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
  29. Use this skill for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization

    • Open source
    • 4K GitHub stars