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,…
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…
Vehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface. — from NVIDIA/skills
Use for agent-assisted Auto-FL optimization of an existing NVFLARE job in simulation, POC, or production. Do not use for code conversion, diagnosis-only work, or deployment setup.
Run TAO Data Services TMM nearest-neighbor mining from embedding parquet files. Use when a workflow needs to mine source samples closest to target samples.
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps.
Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. Use for Evo2/Evo 2, DNA generation, genomic sequence generation, hosted generation, local Docker…
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,…
Summarizes scoped Run:ai workload health or one workload. Not for root cause, quota, cluster health, fleet utilization, history, or mutations.
Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint.
Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access.
Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment.
DINOv3 continual self-supervised pre-training. Domain-adapts public DINOv3 ViT backbones
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service…
Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region
Convert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latent_dist, then continue…
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical misma — from…
Run and interpret SkillEvaluator for agent skills. Use for any skill benchmark or eval - validating or scoring a SKILL.md, writing evals.json test cases or evals config,…
Generate, change, or repair a complete vectorized NVIDIA PVA operator from a validated pva-spec handoff.
Shared launch intake for any TAO workflow or action. Use when the user wants to run TAO AutoML, train, evaluate, infer, export, generate TensorRT engines, or launch DEFT/workflow…
Model and publish semantic definitions in Auto Ontology. Use for terms, relationships, measures, imports, and governed results—not deployment or querying.
OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a
Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.
Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches…
Diagnose and narrowly repair one reproduced NVIDIA PVA operator failure. Use from OpGen or manually for compile, link, cuPVA lifecycle, dataflow, DMA, numerical,…
Used for generating synthetic brain MRI volumes with NV-Generate-CTMR rflow-mr-brain. Not for production training data.
Inspect and interpret gradient attribution (including requests called radiant attribution), column analysis and sampled explanation subgraphs from a Kumo model trained in a…
Enterprise AI security - OWASP LLM Top 10, prompt injection defense, guardrails, PII protection
Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow.
NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation
Use when controlling NVIDIA Broadcast through MCP to apply effects, process local media, select devices, or change camera resolution, or when Broadcast is missing or too old to…
InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment.
Query and analyze logs using Grafana Loki for the Kagenti platform, search for errors, and investigate issues
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
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…
Use a VLM to verify whether each episode satisfies the env's task description. Use when the user asks to annotate, label episodes, filter demos, or gate finetuning on a success…
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
Person re-identification (ReID). Learns discriminative embeddings to match the same person across different
Agent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI.
Guide for adding a new data source to PhysicsNeMo Curator. Use when adding a remote dataset (HuggingFace, S3, etc.) or local file-based source.
Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill.
Run TAO Data Services KPI analysis for object detection, comparing inference annotations against ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP…
Review PR code changes against UI catalog conventions. Use when reviewing PRs that touch components, stories, or tests in kumo-ui-catalog.
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling. — from NVIDIA/skills
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in cod — from…
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.
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 enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
Find version-aware official NVSHMEM and NVSHMEM4Py documentation for releases, installation, APIs, runtime settings, transports, containers, and troubleshooting.
Use when you need to add, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a Jetson/Tegra (Orin, Thor) target.
Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and job export; use only when the request…
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode…
Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D
Detect and fix drift across agent-first infrastructure files. Ensures skill inventories, workflow chains, architecture tables, issue/PR templates, and cross-references stay…
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
Design, implement, calibrate, and run deterministic TensorRT-LLM VisualGen L1 operation tests and L2 component-by-feature parity tests.
Audit GPU quota fairness across a Run:ai cluster — find which projects are starved and which are borrowing over their deserved quota in each node pool, and where GPUs can be…
Normalizes GitHub issue and PR titles by removing any bracketed [NemoClaw] tag case-insensitively, even when the tag appears later in the title.
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,…