Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
327 skills
NVIDIAOfficial
Provides foundational primitives and lifecycle management for NVIDIA DOCA applications on BlueField DPUs and ConnectX NICs.
NVIDIAOfficial
A guide for configuring distributed training strategies and parallelism in NeMo AutoModel.
NVIDIAOfficial
Convert standard PyTorch training scripts into NVFLARE federated learning jobs using the Client API.
NVIDIAOfficial
Guides users through Holoscan SDK 5.x installation options when Conda packages are unavailable or unsupported.
NVIDIAOfficial
A tool-integration skill for finetuning the NV-Generate-CTMR MAISI VAE model using NIfTI CT or MRI volumes.
NVIDIAOfficial
Numerical optimization API for solving LP, MILP, and QP problems using NVIDIA cuOpt.
NVIDIAOfficial
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.
NVIDIAOfficial
Upgrades a grover_base checkpoint to a hybrid cMIM-vocab model and continues pretraining on a custom corpus.
NVIDIAOfficial
A structured workflow for porting quantum circuits from frameworks like Qiskit into CUDA-Q kernels while maintaining algorithmic integrity.
NVIDIAOfficial
Fine-tune HuggingFace models on local NVIDIA GPUs using a standardized, reproducible NGC-based workflow.
NVIDIAOfficial
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
NVIDIAOfficial
A guide for installing Earth2Studio, managing optional model dependencies, and configuring environment variables.
NVIDIAOfficial
Convert PyTorch Lightning training code into an NVFLARE federated learning job.
NVIDIAOfficial
Install Holoscan SDK 5.x native C++ Debian packages on Ubuntu 24.04.
NVIDIAOfficial
GPU-accelerated, batched implementations of common RDKit cheminformatics operations.
NVIDIAOfficial
Automates the creation of prognostic model wrappers for the Earth2Studio framework.
NVIDIAOfficial
Automated installation and configuration of the NVIDIA PVA SDK, NVVPU compiler, and L4T target runtime.
NVIDIAOfficial
Manage and execute public Nemotron embedding and reranking retrieval recipes.
NVIDIAOfficial
A guide for building and debugging equivariant neural networks using cuEquivariance and PyTorch.
NVIDIAOfficial
A standard workflow for training, evaluating, and exporting NVIDIA TAO models in a single, non-iterative execution.
NVIDIAOfficial
Guidelines for selecting Jetson-compatible containers, Python packages, and GPU-native ML stacks.
NVIDIAOfficial
A structured workflow for creating Earth2Studio diagnostic model wrappers for single-step data transformations.
NVIDIAOfficial
Integrate HuggingFace Computer Vision models into the NVIDIA TAO Toolkit ecosystem.
NVIDIAOfficial
Develop, test, and package external Holoscan Modules using the Holoscan CLI.