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.
912 skills
NVIDIAOfficial
Operator-side CLI tool for discovering DOCA telemetry counter schemas, translating Data IDs, and validating per-device counter support.
NVIDIAOfficial
A playbook for managing NeMo-RL training jobs and RayClusters on Kubernetes using the nrl-k8s CLI.
NVIDIAOfficial
Configure Jetson CPU, GPU, and EMC clock ceilings and DVFS behavior by modifying BPMP DTB and nvpower.sh before flashing.
NVIDIAOfficial
Operating guidelines for managing storage and environment secrets on Brev instances for NeMo-RL agents.
NVIDIAOfficial
Measure Jetson memory usage and verify reclamation with live audit data and cache management.
NVIDIAOfficial
Procedures for deploying and supervising DOCA-linked binaries directly on bare-metal hardware.
NVIDIAOfficial
Bootstrap the KERMT agent environment by verifying host requirements, building the container image, and running a GPU smoke test.
NVIDIAOfficial
Analyze GPU utilization across Run:ai clusters to identify idle or underutilized resources.
NVIDIAOfficial
Configure Jetson UPHY lane allocation for Orin and Thor custom carrier boards.
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.
NVIDIAOfficial
Audit GPU quota fairness in Run:ai clusters to identify starved projects, over-borrowing, and reclaimable capacity.
NVIDIAOfficial
Captures a baseline snapshot of Jetson hardware, software, and power configuration for diagnostic and testing purposes.
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.
NVIDIAOfficial
Provides health summaries for Run:ai workloads, including status overviews and drill-down snapshots.
NVIDIAOfficial
Automated setup and verification of NVIDIA GPU host environments for TAO backends.
NVIDIAOfficial
Safely reclaim memory on NVIDIA Jetson devices by disabling GUI components and non-essential background services.
NVIDIAOfficial
Deploy, configure, and debug the NVIDIA DOCA Telemetry Service (DTS) across BlueField, host, and DPF environments.
NVIDIAOfficial
Set up missing Linux prerequisites and audit whether a Cosmos Data Factory (CDF) Orchestration checkout and its Kubernetes or OSMO environment are ready to install the controller and run every packaged DAG. Use for prerequisite, pre-setup, Kubernetes, GPU, RWX/NFS, credential, controller-readiness, and quick-start checks. Not for deploying the controller (use cdf-orchestration-setup, which calls this audit first), authoring payloads, or running workflows.
NVIDIAOfficial
A guide for converting single-node scripts to multi-node Slurm jobs and troubleshooting distributed training failures.
NVIDIAOfficial
Execute TAO container jobs on Kubernetes clusters using native Jobs and GPU scheduling.
NVIDIAOfficial
Generate synthetic PCB inspection images on Kubernetes with the SMT Defect Image Generation (DIG) DAG in CDF Orchestration. The DAG renders components in simulation, turns the renders into realistic golden images (sim2real), and uses AnomalyGen to add texture defects such as solder bridges, excess solder or missing components. Simulation can also render shift, tombstone and sideflip pose defects. Use it to build DIG payloads, pick a pipeline mode (full, simulation, sim2real or defect-only), check GPU readiness, follow a run, and match each defect image to its golden and simulated source. Not for running Simulation, Augmentation or AnomalyGen on their own.
NVIDIAOfficial
Configure observability, telemetry, and event export for NeMo Relay applications.
NVIDIAOfficial
Automate the selection, validation, and deployment of NVIDIA Dynamo Kubernetes recipes.
NVIDIAOfficial
Configure NeMo AutoModel job execution for interactive, Slurm, and SkyPilot environments.