Cloud, CI/CD, monitoring, and deployment (6.8K skills)
Choose an NVSHMEM transport, the communication path between compute nodes, from installed plugins, network evidence, and optional workload analysis. Receive a recommended configuration with minimal environment variables, compatibility evidence, alternatives, and clearly stated unknowns.
Plan and validate NVSHMEM and NVSHMEM4Py installations on individual machines, clusters, or containers. Checks system facts against version-specific documentation, selects a suitable installation method, and prepares commands and runtime validation steps for review.
Recommends network-port assignments and environment settings for NVSHMEM using the compute node’s actual GPU and network topology. Helps select adapters, evaluate multiple-port options, and identify missing evidence before producing an exact configuration.
Set up Auto Ontology with Helm or Docker Compose, or connect an agent to an existing deployment through MCP, an agent connection protocol. Guides database connections, readiness checks, and troubleshooting for startup and sign-in problems.
Set up NVIDIA infrastructure for synthetic data generation on MicroK8s or Azure AKS. Coordinate Kubernetes, inference services, and OSMO workflow execution, with prerequisite checks, deployment validation, capacity planning, and failure investigation before workloads are retried.
Switch the vision-language model, which handles images and text, in VSS Alerts Blueprint. Configure alert generation, verification, and agent queries separately, choose an external endpoint or bundled vLLM deployment, and verify an actual inference response.
Configure observability in NeMo Relay 0.6 or 0.7 to inspect recorded activity. Choose raw events, execution histories, or traces that show how calls unfold, then verify the selected output before adding more destinations.
Helps an AI coding assistant answer NemoClaw installation, configuration, operation, and troubleshooting questions using official documentation. It finds relevant pages through MCP, a documentation connection, or Markdown files, then tailors guidance to the selected agent and environment.
Organize NeMo-RL experiments on Brev by placing large outputs and shared caches on /ephemeral, loading credentials without exposing them, checking disk capacity, and keeping concise reproduction records in the source checkout.
Choose containers and Python package sources that match a Jetson device's GPU architecture, JetPack, and CUDA environment. Get compatibility hints for PyTorch, vLLM, and related stacks before installation, using NVIDIA catalogs and Jetson AI Lab indexes.
Start Jetson or IGX board software customization by selecting a setup mode, platform, release, and carrier-board intent in a questionnaire. It passes those choices to the appropriate setup skills and reports workspace readiness and remaining steps.
Inspect live Jetson memory usage, identify major consumers, and compare measurements before and after changes. It also supports checking whether approved cache clearing makes reclaimed memory visible in the device's reported free and available memory.
Write a prepared board support package image to a Jetson device in recovery mode. The skill checks device identity and image readiness, selects the flashing tool for the boot storage, and presents the resolved plan for approval.
Prepare a staged Jetson BSP image, the device software package, by copying customized files and built artifacts. Skip identical files and refresh startup files when kernels or modules change, without building or flashing the device.
Reclaim application memory on Jetson deployments without displays or cameras. Guides changes to boot settings, kernel memory reservations, and the DMA transfer buffer, then checks compiled settings and memory usage on the running device.
Switch the active Jetson target to an existing YAML profile before customization, building, or flashing. Review profile names and configuration summaries, choose a target, and update the pointer used by downstream skills without creating new profiles.
Prepare kernel device-tree overlays, files describing hardware settings, for PCIe controllers on Jetson Thor or Orin custom carrier boards. Set lane counts and link speeds from documented plans, and check consistency with existing ODMDATA configuration.
Customize Jetson and Tegra power modes in BSP files, the device's system software configuration. Adds, removes, or edits nvpmodel profiles, adjusts frequency limits, changes the boot default, and guides deployment of the updated configuration.
Install, repair, or inspect NVIDIA Video Codec SDK and PyNvVideoCodec on Jetson. Verify readiness with official samples that encode and independently decode one frame, and report what passed, what failed, and the next action.
Prepare the runtime for Isaac for Healthcare workflows by checking host requirements and setting up dependencies. Verify that workflows can be listed and their definitions pass checks, and identify the first setup failure requiring attention.
Configure Jetson CPU, GPU, and memory-controller clock frequencies before flashing an image. Edit firmware settings and the boot script to fix or limit frequencies, change frequency-control policies, and enable or disable automatic frequency scaling.
Manage nvfancontrol fan profiles for Jetson and Tegra boards. Add, remove, or edit temperature-based fan curves and boot defaults in board support files, while tracking changes and preserving configuration differences between related carrier boards.
Collects a read-only health snapshot of a Jetson device, covering its model, memory, GPU, temperatures, power mode, storage, services, and processes. Helps investigate slowdowns, overheating, and memory pressure using observed device data.
Collect a short, read-only report from a running Jetson device, covering its model, L4T release, kernel, OS, power mode, and uptime. Use it to record the environment before performance, regression, or compatibility tests.