Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.
Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.
Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages and refresh generated user skills for release…
Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain cla — from…
Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp stall analysis,…
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper.
Performs a comprehensive security review of code changes in a GitHub PR or issue. Checks out the branch, analyzes changed files against a 9-category security checklist, and…
Vehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface. — from NVIDIA/skills
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.
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill.
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage.
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…
Generate video summary reports using the VSS video_search_frag extension with Long Video Summarization (LVS), Enterprise RAG knowledge retrieval, and human-in-the-loop parameter…
Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain cla — from…
After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment.
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism config — from…
OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a
LP, MILP, and QP (beta) with cuOpt — CLI only (MPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from MPS via command line.
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
Local Docker execution for TAO SDK job containers using the host Docker daemon and NVIDIA GPU runtime. Use
Runs the daytime maintainer loop for NemoClaw, prioritizing items labeled with the current version target.
Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region
Run `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data.
Use to help users get started with Nemo Gym reward profiling. Covers the basic ng_run, ng_collect_rollouts, and ng_reward_profile workflow, repeated rollouts, materialized inputs,…
Cut a new semver release — bump all version strings via bump-version.ts, open a release PR, and after merge tag main and push.
Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task.
Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing,
Cosmos-Reason2-8B video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video
AI-assisted label triage for NVIDIA/NemoClaw issues and PRs. Reads triage-instructions.md at runtime for consistent label guidance.
Solve Linear Programming (LP), Mixed-Integer Linear Programming (MILP), and Quadratic Programming (QP, beta) with the Python API.
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.
Cherry-pick merged PRs labeled for a release branch into that branch, then open a PR and apply the cherry-pick-done label.
Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset
Configuration conventions for NeMo-RL. YAML is the single source of truth for defaults. Covers TypedDict usage, exemplar YAML updates, and forbidden default patterns.
Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them
Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.
Person re-identification (ReID). Learns discriminative embeddings to match the same person across different
Deploy Halos Outside-In Safety (HOISA) closed-loop testing by PROFILE (base / sil / hil) on top of the VSS Warehouse 3.2 perception backend.
Install cuOpt for Python, C, or as a server (pip, conda, Docker) — system requirements, install commands, and verification.
NVIDIA copyright header requirements for NeMo-RL. Covers which files need headers and the exact header text.
Guide for adding a new sink to PhysicsNeMo Curator. Covers discovery questions, implementation patterns (simple writer, append-based, split-based), output naming, parallel…
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM f — from…
Deploy and operate the RTVI-CV-3D stack (also known as MV3DT, Multi-View 3D Tracking, or RTVI-CV-MV3DT) — per-camera DeepStream perception plus BEV Fusion over multiple calibrated…
Per-pin SFIO / direction / initial-state configurator for a Jetson Orin or Thor custom carrier from the pinmux XLSM. Do NOT use for kernel-DT overlay or ODMDATA edits.
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVIC — from…
Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
Guide for adding support for new LLM or VLM models in Megatron-Bridge. Covers bridge, provider, recipe, tests, docs, and examples.
Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or assessing control…
Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time.
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.
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.