Interactive config wizard for NeMo Evaluator Launcher (NEL). Use when the user wants to create a new evaluation config from scratch, set up an evaluation from existing configs, or…
Detect and fix drift across agent-first infrastructure files. Ensures skill inventories, workflow chains, architecture tables, issue/PR templates, and cross-references stay…
Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree. Use after init-image / init-source; not for editing profile fields.
Use to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.
Identify and eliminate host-device synchronizations in PyTorch code. Detects sync points (.item(), .cpu(), boolean indexing, torch.tensor on CUDA), classifies false vs true…
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review.
Run `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data.
Validate and analyze TensorRT performance data from paired layer-info JSON and profile/latency JSON files.
Use when you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra (Orin, Thor) target.
Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for
Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.
Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.
Use to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp image.
Build and verify a TensorRT engine from a Hugging Face model ID or ONNX file, with numerical parity checked against ONNX Runtime.
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container set — from…
Domain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.
Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting.
Verify host/GPU requirements and PYTHONPATH for the catheter navigation workflow. Use when asked to set up, install, or bootstrap catheter_navigation, or when hitting…
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.
Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.
Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors,…
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism config — from…
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism config — from…
Edit an env's scene in place — objects, cameras, task, success bounds, randomization. Use when asked to edit a scene or launch/run/open an env in edit mode (`--bridge`), incl.
Runs the end-of-day maintainer handoff for NemoClaw. Checks version target progress, bumps stragglers to the next patch version, generates a QA handoff summary, and cuts the…
Attempt to fix a security issue tracked in <tracker> by implementing the change in a public <upstream> PR.
Deploy, operate, and integrate the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file…
Create GitHub pull requests using the gh CLI. Use when the user wants to create a new PR, submit code for review, or open a pull request.
Use only to generate or update a governance skill card for a specified existing agent skill directory.
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper.
Validate, evaluate, or run i4h envs. Use for policy/checkpoint rollouts and scripted state-machine smoke runs.
Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout.
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization.
Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module
Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.
Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for live RTSP captioning or incident-range reports.
Enable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.
Enterprise AI security - OWASP LLM Top 10, prompt injection defense, guardrails, PII protection
Brev managed GPU instances with Docker support. Use when running TAO training, evaluation, or inference on
Use when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker capacity with authenticated samples and…
Overview of `workflows/agentic/` (IsaacLab-Arena + GR00T/openpi). Use when the user asks what i4h workflow is, what's supported, or where to start.
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying th — from…
NVIDIA copyright header requirements for NeMo-RL. Covers which files need headers and the exact header text.
Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes,…
Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of
Compile TensorRT-LLM on a SLURM cluster. Covers submitting a batch job with a container image, monitoring the job, and verifying the build.
Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Vehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface. — from NVIDIA/skills
Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use for gateway health failures, Docker/Podman runtime issues, Helm failures,…
Use to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Not for ad-hoc Q&A or live captioning.
Set up the BSP source workspace: Linux_for_Tegra overlay tracker, bsp_sources, Crosstool-NG toolchain. Use after jetson-init-image; not for fetching inputs.
Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choices.
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper.
Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors.
Author a new Jetson target-platform profile (reference_devkit + optional custom_carrier) and update the active pointer. Use to create a target; not for switching existing profiles.
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame…
Code style and quality rules for Megatron Bridge — ruff configuration, naming conventions, type hints, mypy rules, docstrings, copyright headers, logging, and the code review…