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.
1928 skills
NVIDIAOfficial
Provides guidance for using doca_flow_tune to analyze, visualize, and optimize DOCA Flow pipelines.
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
Automated mining-based improvement workflow for ITS Cosmos-Reason binary video classification models.
NVIDIAOfficial
A guide for installing Earth2Studio, managing optional model dependencies, and configuring environment variables.
NVIDIAOfficial
Performs gap analysis on NVIDIA TAO VCN Classify experiments to identify weak samples for model improvement.
NVIDIAOfficial
Configure resiliency features for Megatron Bridge training, including fault tolerance, straggler detection, and in-process restarts.
NVIDIAOfficial
Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to benchmark, tune, or measure FPS.
NVIDIAOfficial
Guide for managing DOCA DPA host-side operations on NVIDIA BlueField DPUs.
NVIDIAOfficial
Automates the multi-camera calibration process for pre-recorded video datasets using the AutoMagicCalib REST API.
NVIDIAOfficial
Provides guidance for running the doca_perftest RDMA benchmark tool to measure network performance metrics.
NVIDIAOfficial
Guidance for integrating NVIDIA DOCA Rivermax to handle timing-precise media-over-IP streams on BlueField DPUs.
NVIDIAOfficial
Evaluate if a code bottleneck is a suitable candidate for NVIDIA Warp acceleration.
NVIDIAOfficial
Inspect, install, and verify NVIDIA Video Codec SDK and PyNvVideoCodec readiness on Jetson devices.
NVIDIAOfficial
Read hardware-counter snapshots from NVIDIA DOCA-enabled devices using per-domain telemetry reader libraries.
NVIDIAOfficial
A three-phase pipeline chaining AutoML hyperparameter optimization with the DEFT iterative data-improvement loop for model refinement.
NVIDIAOfficial
Convert PyTorch Lightning training code into an NVFLARE federated learning job.
NVIDIAOfficial
Automated end-to-end calibration validation for the AutoMagicCalib microservice using a provided sample dataset.
NVIDIAOfficial
Authoritative JSON schemas and structural contracts for TAO execution pipeline artifacts.
NVIDIAOfficial
Install Holoscan SDK 5.x native C++ Debian packages on Ubuntu 24.04.
NVIDIAOfficial
Automated optimization campaign runner for NVFLARE federated learning jobs.
NVIDIAOfficial
GPU-accelerated, batched implementations of common RDKit cheminformatics operations.
NVIDIAOfficial
Automates the creation of prognostic model wrappers for the Earth2Studio framework.
NVIDIAOfficial
Bootstrap a custom Jetson carrier board by forking reference files and scaffolding a device tree overlay.