Kermt Pretrain Scratch
NVIDIAOfficial
Pretrain a new KERMT chemistry model from scratch using a custom corpus.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Agent Skills
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.
Results
5813 skills
Tao Analyze Changenet Rca
NVIDIAOfficial
Performs deep, image-evidence-driven root cause analysis for NVIDIA TAO Visual ChangeNet classification experiments.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Nemo Retriever
NVIDIAOfficial
A CLI tool for ingesting, indexing, and querying document collections using NeMo Retriever.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Dicom Series Preflight
NVIDIAOfficial
Performs header-only preflight validation on DICOM series folders to assess data integrity before processing.
Science and researchClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Cdf Orchestration Write Dag
NVIDIAOfficial
Use when a user describes a custom CDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-labeling only, detection+captioning only, or image attribute augmentation without full auto-labeling — that no existing DAG in airflow/dags/workflows/ covers, and asks for a new Kubernetes DAG. Also use to check that a generated or existing DAG's model/container/prompt choices match an external spec document (e.g. a CDF `launchable.md`). Not for requests that an existing DAG already covers, including payload-only changes such as different inputs, endpoints, models, or variant counts — route those to the matching workflow skill, unless the user still wants a separate DAG after being pointed to it.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreLink-onlyMedium riskGitHub stars of the source repository3.9k
Earth2studio Create Diagnostic
NVIDIAOfficial
A structured workflow for creating Earth2Studio diagnostic model wrappers for single-step data transformations.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Genmol Nim
NVIDIAOfficial
Generate novel drug-like molecules using the GenMol NIM microservice. Use for de novo generation, scaffold decoration, motif extension, lead optimization, SAFE notation, QED or LogP ranking, hosted NVIDIA API calls, or local Docker deployment. GenMol takes SAFE notation in the smiles field, not ordinary SMILES.
Science and researchClaude CodeClaude appsOpenAI Codex+14 moreLink-onlyMedium riskGitHub stars of the source repository3.9k
Tao Route Visual Changenet Samples
NVIDIAOfficial
Routes Visual ChangeNet gap analysis samples into specific augmentation modules based on label eligibility.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Tao Train Rtdetr
NVIDIAOfficial
A comprehensive workflow for training, optimizing, and deploying RT-DETR real-time object detection models.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Pva Build Test
NVIDIAOfficial
Automated build and verification workflow for NVIDIA PVA operators on Tegra hardware.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Tao Train Oneformer
NVIDIAOfficial
Train, evaluate, and deploy OneFormer models for universal image segmentation using NVIDIA TAO.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Doca Devemu
NVIDIAOfficial
Provides guidance for developing custom emulated PCIe devices on NVIDIA BlueField DPUs using the DOCA Device Emulation library.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Physical AI Defect Image Generation
NVIDIAOfficial
Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreLink-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k
Doca Ngauge
NVIDIAOfficial
Analyze and debug network performance on NVIDIA hardware using the DOCA ngauge tool.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Runai Audit Assigned Quota
NVIDIAOfficial
Audit GPU quota fairness in Run:ai clusters to identify starved projects, over-borrowing, and reclaimable capacity.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Ambient Healthcare Agent With Nemotron Voice Agent
NVIDIAOfficial
Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 moreLink-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k
Tao Train Bevfusion
NVIDIAOfficial
Train and evaluate BEVFusion models for multi-sensor 3D object detection in autonomous driving.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Nvshmem Configure Nic Pe Mapping
NVIDIAOfficial
Recommend NVSHMEM NIC-to-PE mappings and environment exports. Use for HCA selection, multi-NIC configuration, or topology-based mapping diagnostics.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Nv Generate Mr Brain Finetune
NVIDIAOfficial
A workflow for finetuning NV-Generate-CTMR MR-Brain diffusion models using NIfTI training volumes.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Pva Debug
NVIDIAOfficial
Diagnose and repair specific NVIDIA PVA operator failures using evidence-based debugging workflows.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Rtvi Cv Scaffold Vss Service
NVIDIAOfficial
Scaffold a standalone RTVI CV microservice that plugs into VSS Search and Alerts profiles via Kafka mdx-raw. The shipped scaffold script is a YOLO26 reference implementation (ONNX, labels, custom parser required). Use when building a new perception microservice repo, validating the VSS integration contract, extending that scaffold for segmentation frame-mask payloads, or scaffolding with placeholders before customer YOLO26 assets exist. For swapping the detector in the stock vss-rt-cv container, use rtvi-cv-customize-model instead. Live DeepStream integration cannot run until the customer-supplied ONNX, labels file, and parser library exist.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreLink-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k
Doca Comch
NVIDIAOfficial
Expert guidance for developing host-to-DPU control-plane messaging applications using the NVIDIA DOCA Comch library.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Jetson Print Device Info
NVIDIAOfficial
Captures a baseline snapshot of Jetson hardware, software, and power configuration for diagnostic and testing purposes.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Deepstream Import Vision Model
NVIDIAOfficial
Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreLink-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k