Manually dispatch and iterate on the Release Canary workflow that smoke-tests published OpenShell artifacts (install.sh on macOS/Ubuntu/Fedora, Helm chart on kind) after each…
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data without review.
Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env — from…
Create GitHub pull requests that follow the NemoClaw PR template. Use when the user wants to create a new PR, submit code for review, open a pull request, or push changes for…
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…
Bump the NVIDIA PyTorch base image (`nvcr.io/nvidia/pytorch:<YY.MM>-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker/.ngc_version.dev` and GitLab CI in…
Guides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.
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…
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature
Watch and monitor GitHub Actions workflow runs using the gh CLI. Use when the user wants to check workflow status, watch a running workflow, view CI/CD jobs, or monitor build…
LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.
Compile TensorRT-LLM on a compute node inside a Docker container. Use this when already on a compute node with GPUs visible.
Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. — from NVIDIA/skills
Launch and supervise OpenShell gator agents. Use when starting gator on issues or PRs, checking gator sandboxes, building the gator sandbox image, restarting stuck gators,…
Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this…
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage.
Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability.
Used for running NV-Segment-CTMR on CT or MRI NIfTI volumes and recording label-map evidence. Not for clinical interpretation.
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config.
Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env — from…
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…
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.
Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, efficient frontiers, scenario generation, or NVIDIA cuOpt.
Use when working on the Evaluator plugin CLI, jobs, SDK-backed specs, or plugin-owned Evaluator skills.
Record episodes for an agentic env via teleoperation (keyboard, SO-ARM leader, or VR) into HDF5. Use when the user wants to teleop or record human demos.
Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.
Cosmos-Reason2-8B video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video
External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron…
Runs the morning maintainer standup for NemoClaw. Triages the backlog, determines the day's target version, labels selected items, surfaces stragglers from previous versions, and…
Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task.
Probe a model or agent stack with adversarial test suites so safety failures show up before deployment or review.
Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).
Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to…
Create a new agentic env by forking an existing env. Use for new env/task scaffolding, not scene edits or baking.
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task…
Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds,…
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time.
Scaffold a standalone RTVI CV microservice that plugs into VSS Search and Alerts profiles via Kafka mdx-raw.
Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice.
Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and search per-sample (guidance,…
Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval.
Configure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or PCIe-only edits.
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples. — from NVIDIA/skills
Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine. — from NVIDIA/skills
Use when running image attribute augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval.
Solve Linear Programming (LP), Mixed-Integer Linear Programming (MILP), and Quadratic Programming (QP, beta) with the Python API.
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…
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety.
Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS,…
Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed