Nvshmem Docs
NVIDIAOfficial
Retrieve and summarize version-specific official NVSHMEM and NVSHMEM4Py documentation.
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.
5813 skills
NVIDIAOfficial
Retrieve and summarize version-specific official NVSHMEM and NVSHMEM4Py documentation.
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
Train, evaluate, and deploy TAO action recognition models for video sequences using RGB, optical flow, or joint inputs.
NVIDIAOfficial
Use this skill for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization. Invoke for MolMIM, molecular embeddings, hidden states, latent decoding, sampling around a seed SMILES, CMA-ES guided molecule generation, QED or plogP optimization, hosted NVIDIA API calls, or local Docker deployment.
NVIDIAOfficial
Train, evaluate, and deploy OCDNet models for arbitrary-oriented scene text detection.
NVIDIAOfficial
A guide for installing Earth2Studio, managing optional model dependencies, and configuring environment variables.
NVIDIAOfficial
Operational guidance for deploying and managing the DOCA Argus Service container for runtime security on NVIDIA BlueField DPUs.
NVIDIAOfficial
Run RFDiffusion protein backbone design via NVIDIA NIM. Use for de novo protein backbones, motif scaffolding, binder design, hotspot residues, contigs syntax, diffusion steps, hosted NVIDIA API calls, local Docker deployment, and PDB backbone outputs for ProteinMPNN sequence design.
NVIDIAOfficial
Performs gap analysis on NVIDIA TAO VCN Classify experiments to identify weak samples for model improvement.
NVIDIAOfficial
Deploy vLLM or SGLang inference servers on NVIDIA Jetson hardware using optimized container runtimes.
NVIDIAOfficial
Generate image embeddings from file paths using CLIP, SigLIP, or TAO checkpoints for downstream data mining.
NVIDIAOfficial
Configure resiliency features for Megatron Bridge training, including fault tolerance, straggler detection, and in-process restarts.
NVIDIAOfficial
Generates and maintains a durable ethos.md file to document an AI agent's purpose, constraints, and success criteria.
NVIDIAOfficial
Convert NVIDIA TAO DAFT datasets between supported formats using the tao-daft CLI.
NVIDIAOfficial
Fine-tunes clinical ASR models using NeMo and validates performance via offline evaluation.
NVIDIAOfficial
Manage the full lifecycle of NVIDIA TAO OCRNet models for scene text recognition.
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
Not for writing library code (name that library skill). Use this skill whenever another DOCA skill says "prefer the structured tool per doca-structured-tools-contract", or when the user wants a one-shot answer consolidating what multiple manual commands would produce — DOCA env / version / devices / capabilities / validate / host vs DPU state. Trigger even without the phrases "structured tool" or "doca-env --json" — typical phrasings include "is there one command that tells me everything about my DOCA install", "what version is X capability available since", "every PF/VF/SF visible on this BlueField with PCIe address", or "will this pipe pass validate before commit". Refuse and route elsewhere for general DOCA orientation, library API how-to, or install-from-scratch guidance — those belong to the per-library skill, doca-public-knowledge-map, or doca-setup.
NVIDIAOfficial
Automates the multi-camera calibration process for pre-recorded video datasets using the AutoMagicCalib REST API.
NVIDIAOfficial
Operator-side CLI tool for discovering DOCA telemetry counter schemas, translating Data IDs, and validating per-device counter support.
NVIDIAOfficial
A guide for fetching weather and climate data using Earth2Studio data source APIs.