Latest Agent Skills

Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit.

Configure Jetson UPHY lane allocation on Orin/Thor custom carriers by editing ODMDATA tokens and dispatching per-controller kernel-DT overlay skills.

Generates kernel device-tree overlay fragments to enable or disable individual PCIe controllers and configure lane count and link speed on Jetson Thor/Orin custom carriers.

Generates kernel-DT overlay fragments to enable 25G/10G/1G MGBE QSFP interfaces on Jetson Thor, verifying pinmux and integrating with the BSP customization workflow.

Find Earth2Studio models, data sources, and examples for weather/climate use cases by consulting live documentation and verifying compatibility via the lexicon system.

Start or patch Dynamo router modes and run router endpoint smoke checks for round-robin, KV-aware, least-loaded, or device-aware routing.

Detects generalizable learnings from problem-solving interactions and proposes skill updates to improve future performance.

Train, evaluate, export, and run inference for CenterPose models used in 6-DoF object pose estimation with keypoint regression.

Generates or updates a governance skill card for an existing agent skill directory by analyzing source signals, building a grounded JSON context, and rendering a deterministic markdown card.

Navigate the PhysicsNeMo repository by discovering model families, datapipes, and examples through live file search, without writing training code.

Generates synthetic brain MRI volumes using NVIDIA's NV-Generate-CTMR workflow, with configurable modality and random seed.

Generates synthetic CT volumes and masks using NVIDIA's rectified-flow pipeline for medical imaging research.

Copies overlay files and built artifacts into a staged BSP image for NVIDIA Jetson platforms, preparing it for flashing without modifying the workspace.

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

Plan and apply safe, reversible headless-mode changes on Jetson devices to reclaim memory from the GUI and non-essential daemons.

Enable, disable, or change the role of USB2/USB3 SS ports on Jetson custom carriers by generating kernel-DT overlays that flip lane, port, and host xHCI phys in lockstep.

Add, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a Jetson/Tegra target.

Guides installing Earth2Studio via uv or pip, selecting model extras, and configuring environment variables.

Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes for model serving with GPU support.

Summarize recorded video clips using the LVS microservice with a VLM fallback, producing a narrative summary with timestamped events.

Queries video analytics incidents, alerts, metrics, and sensor data from Elasticsearch via the VA-MCP server.

Trains, evaluates, exports, quantizes, and runs inference for SegFormer semantic segmentation models using NVIDIA TAO.

Train, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.

Trains, evaluates, and runs inference for BEVFusion multi-sensor 3D object detection models that fuse LiDAR and camera data in bird's-eye-view space for autonomous driving.

Embeds target and source image parquets, then mines nearest-neighbour source images for augmentation in VCN AOI workflows.

Collects launch inputs and runs preflight checks before executing TAO workflows such as AutoML, training, evaluation, inference, export, TensorRT engine generation, or DEFT jobs on supported platforms.

Guides AI coding assistants to the official NemoClaw documentation via MCP server or Markdown files for installation, configuration, operation, and troubleshooting.

Measure Jetson DRAM and NvMap usage, capture before/after baselines, and verify memory reclamation with live audit data.

Downloads NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Used for Auto Setup; does not extract or edit profiles.

Rebuild kernel-side artifacts (DTBs, OOT modules, kernel Image) from source changes under bsp_sources/ and produce a manifest for staging into a BSP image.

Diagnose failed or unhealthy Dynamo deployments by collecting a read-only debug bundle, classifying failures, and providing step-by-step remediation guidance.

Install and verify cuPyNumeric for Python using conda or pip, including GPU usage checks.

Explains the domain concepts of the cuOpt REST server, including supported problem types, request flow, and key endpoints, without deployment or client code.

Search archived video using natural language, ingest video files or RTSP streams, and manage ingested sources.

Selects, configures, deploys, verifies, debugs, or tears down a VSS profile (base, search, lvs, warehouse, edge) for NVIDIA's video search and summarization stack.

Trains, evaluates, exports, quantizes, and runs inference for Sparse4D multi-camera temporal 3D object detection and tracking models using TAO.

Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.

Plan, configure, and chain Nemotron model customization steps into single-step or multi-step pipelines for curation, translation, fine-tuning, RL alignment, benchmarking, checkpoint conversion, optimization, and evaluation.

Launch distributed Megatron-LM training jobs on a SLURM cluster with a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules, container conventions, monitoring, and per-rank failure diagnosis.

Investigate a failing GitHub Actions job, extract the root cause, and file a well-structured bug issue against NVIDIA/Megatron-LM.

Dispatches Jetson BSP customization by presenting a click-to-select setup questionnaire and passing prefilled answers to downstream setup skills.

Creates a new Jetson target-platform profile YAML by selecting a reference devkit and optional custom carrier, then updates the active target pointer.

Bootstraps a BSP customization workspace for NVIDIA Jetson, including the Linux_for_Tegra overlay tracker, bsp_sources mono-tree, and Crosstool-NG toolchain.

Generates a per-target knowledge-base markdown file by walking the BSP root and source tree, documenting image layout, source tree structure, and document references.

Flash a promoted BSP image to a Jetson device in RCM mode using NVIDIA's flash.sh or l4t_initrd_flash.sh toolchain.

Operate the VSS alert pipeline for real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, and camera onboarding.

Submit TAO jobs to Lepton managed GPU compute on DGX Cloud, with run/status/cancel interface and multi-node distributed training support.

Fine-tune and deploy CLIP vision-language models for zero-shot classification, image-text retrieval, and embedding extraction with ONNX and TensorRT support.

Switch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target; not for authoring profiles — use jetson-init-target instead.

Extract Jetson Linux BSP and sample-rootfs tarballs, run apply_binaries.sh with the correct GPU stack flag, and record the image metadata in the active target profile.

Captures a read-only health snapshot from a Jetson device, reporting identity, memory, GPU, thermal, power, storage, services, and top processes.

Write, review, and migrate code using NVIDIA DALI's imperative dynamic-mode API for efficient data loading and preprocessing.

Train, evaluate, distill, quantize, export, and run inference for RT-DETR object detection models using NVIDIA TAO.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for TAO OCRNet models for scene text recognition from cropped text-region images, supporting CTC and attention-based decoders.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for OCDNet scene text detection models using TAO, detecting arbitrary-oriented text regions in natural images.

Submit and monitor GPU training jobs on Brev, SLURM, Docker, or Kubernetes using the TAO Execution SDK, with job handles, S3 I/O wrapping, and multi-node distributed training.

Submit and manage TAO training, evaluation, and inference jobs on SLURM GPU clusters over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed storage.

Automates the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models, including baseline evaluation, RCA, synthetic defect generation, data mining, retraining, and deployment gating until KPI targets are met.

Serve LLMs and VLMs on NVIDIA Jetson devices using vLLM or SGLang with optimized Docker containers and quantization presets.

Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs on disk; not for downloading.