N

Skills Nvidia

ego lite browser

ผู้สนับสนุน

ego lite is the fastest browser for AI agents to run web automation, sharing your logged-in state with Codex or Claude Code, zero cost, zero config.

Alpha Vantage MCP Server

ผู้สนับสนุน

Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more

Webotee Amazon MCP

ผู้สนับสนุน

Amazon brand, seller & niche intelligence in your own Claude or ChatGPT — buy-box history, competing sellers, and under-competed niches. Research built for sellers.

accelerated-computing-cudf

Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and…

accessing-mlflow

Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts…

add-binding-feature

Add or change a public NeMo Relay API surface across the core runtime and every affected binding

Add a new guardrail or intercept type to the NeMo Relay middleware pipeline

Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

amc-run-sample-calibration

Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample…

amc-run-video-calibration

Calibrate a new dataset from pre-recorded video files via the AutoMagicCalib REST API. Use when user has local MP4s and says 'calibrate my videos', 'run AMC on…

amc-setup-calibration-stack

Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto…

analysis-methods

Teaches the analyst agent how to write correct, robust Python analysis code for FHIR clinical data using pandas, matplotlib, and scipy.

asset-harvester

Use to install and run NVIDIA Asset Harvester (Apache-2.0) to extract per-object 3D Gaussian Splat assets (`gaussians.ply`) from AV NCore V4 clips or masked…

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle:…

benchmark-isaaclab

Run Isaac Lab benchmark scripts and interpret their outputs. Covers RL training throughput, non-RL environment step FPS, camera/load/startup benchmarks, batch…

benchmark-isaacsim

Run Isaac Sim benchmark scripts and interpret benchmark outputs. Covers camera, SDG, scene-loading, robot, lidar/radar/sensor benchmark scripts, common…

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional…

build-and-dependency

Container-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and…

build-from-issue

Given a GitHub issue number, plan and implement the work described in the issue. Operates iteratively - creates an implementation plan, responds to feedback,…

Prepare a complete clinical case summary for a patient from FHIR endpoints. Use when asked to summarize a patient, compile a case, or prepare for tumor board.

changelog-audit

Audit Warp CHANGELOG.md before a release: recover lost entries, sort by user impact, refine entry language, line-wrap, and (release-branch mode) bump compare…

Use when cooking or planning meals, troubleshooting recipes, learning culinary techniques

CI/CD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI, and CI failure investigation.

clinical-delegation

How to delegate clinical tasks to specialist agents. Always use sub-agent runtime with explicit agentId — never ACP. Never call FHIR via web_fetch.

clinical-knowledge

Teaches agents clinical reference ranges, condition codes, quality measure definitions, drug classifications, and regulatory context so they can flag abnormal…

cmake-structure

IsaacTeleop CMake target layout and #include conventions. Use whenever you create or edit a CMakeLists.txt, add or move a module/library/executable/test…

Formats Python code using the black formatter

Reviews code changes and suggests improvements

Analyze a cohort of patients from FHIR endpoints to find care gaps and patterns. Use when asked to compare patients, find quality gaps, or analyze a population.

compare-results

Establish baseline-vs-candidate evaluation plans, delegate missing evaluations, compare validated results, and decide quantization feasibility. Use when the…

compileiq-author-objective

Use when writing the objective_function= passed to Search(). Covers the two legal signatures (compiler-only str vs mixed list), the baseline-knockout branch,…

compileiq-booster-pack

Use BEFORE running a full CompileIQ search. Walks through downloading a Booster Pack from NVIDIA/CompileIQ GitHub Releases, applying ACF candidates one at a…

compileiq-bootstrap

Use when starting a fresh CompileIQ project, hitting a socket timeout, or before running any other compileiq-* skill. Verifies CUDA 13.3+, ptxas, GPU access,…

compileiq-debug

Use when something is wrong: Search() hangs, all evaluations return INVALID_SCORE, scores aren't improving, every config returns the same number, ptxas errors…

compileiq-run-search

Use when composing the Search(...) call and calling .start(). Covers the four worker classes (MultiProcessWorker / IsoMultiProcessWorker / RayWorker /…

compileiq-search-space

Use when picking the search_space= argument for Search(). Covers the three provider classes (PtxasSearchSpace, NvccSearchSpace, LocalSearchSpaceBin), how to…

compileiq-validate-result

Use AFTER a Search has completed and BEFORE claiming any speedup or shipping an ACF. Loads the dump_results CSV, extracts top-K candidates (single-objective)…

Reads and displays configuration files

Contribute a new NeMo Relay public API surface safely, with binding parity and docs in mind

contribute-docs

Contribute documentation or example changes that stay aligned with NeMo Relay public behavior

contribute-integration

Contribute a new or updated third-party framework integration for NeMo Relay

create-github-issue

Create GitHub issues using the gh CLI. Use when the user wants to create a new issue, report a bug, request a feature, or create a task in GitHub. Trigger…

create-github-pr

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. Trigger keywords -…

Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

Create OpenShell RFC proposals in rfc/ from a design request. Use when the user asks to write, draft, start, create, or update an RFC, Request for Comments,…

Investigate a plain-language problem description by deeply exploring the codebase, then create a structured GitHub issue with technical findings. Prequel to…

creative-writing-coach

ช่วยเหลือผู้ใช้ในการเขียนเชิงสร้างสรรค์และการเล่าเรื่อง

CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.

Define custom groups (Irrep subclasses), build segmented tensor products with CG coefficients, create equivariant polynomials and IrDictPolynomials, and use…

cuequivariance-jax

Execute equivariant polynomials in JAX using segmented_polynomial (naive/uniform_1d), the ir_dict workflow with IrDictPolynomial and dict[Irrep, Array], and…

cuequivariance-torch

Execute equivariant tensor products in PyTorch using SegmentedPolynomial (naive/uniform_1d/fused_tp/indexed_linear), high-level operations…

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-debugging

Troubleshoot cuOpt LP/MILP problems including errors, wrong results, infeasible solutions, performance issues, and status codes. Use when the user says…

cuopt-developer

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

cuopt-developer

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.

Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.

cuopt-installation-api-c

Install cuOpt for C — conda, locate lib/headers, verification. Use when the user is installing or verifying the C API. Standalone; no common skill.

cuopt-installation-api-python

Install cuOpt for Python — pip, conda, Docker, verification. Use when the user is installing or verifying the Python API. Standalone; no common skill.

cuopt-installation-common

Install cuOpt — system and environment requirements only. Domain concepts; no install commands or interface guidance.

cuopt-installation-developer

Developer installation — build cuOpt from source, run tests. Use when the user wants to set up a dev environment to contribute or modify cuOpt.

cuopt-lp-milp-api-c

LP and MILP with cuOpt — C API only. Use when the user is embedding LP/MILP in C/C++.

cuopt-lp-milp-api-cli

LP and MILP with cuOpt — CLI only (MPS files, cuopt_cli). Use when the user is solving from MPS via command line.

cuopt-lp-milp-api-python

Solve Linear Programming (LP) and Mixed-Integer Linear Programming (MILP) with the Python API. Use when the user asks about optimization with linear…

cuopt-model-mapper

Map interpreted optimization problems into cuOpt-native models for the fast path with minimal clarifying questions.

cuopt-multi-objective-exploration

Trace and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).

cuopt-multi-objective-exploration

Trace and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).

cuopt-numerical-optimization-api

LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.

cuopt-numerical-optimization-api

LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.

cuopt-numerical-optimization-api-c

LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.

cuopt-numerical-optimization-api-c

LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.

cuopt-numerical-optimization-api-cli

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.

cuopt-numerical-optimization-api-cli

LP, MILP, and QP (beta) with cuOpt — CLI only (MPS/LP/QPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from an MPS or LP file via command…

cuopt-numerical-optimization-api-python

Solve LP, MILP, QP (beta) with cuOpt Python API — linear/quadratic objectives, integer variables, scheduling, portfolio, least squares.

cuopt-numerical-optimization-api-python

Solve LP, MILP, QP (beta) with cuOpt Python API — linear/quadratic objectives, integer variables, scheduling, portfolio, least squares.

cuopt-numerical-optimization-formulation

LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.

cuopt-numerical-optimization-formulation

LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.

Quadratic Programming (QP) with cuOpt — C API. Use when the user is embedding QP in C/C++.

cuopt-qp-api-cli

QP with cuOpt — CLI (e.g. cuopt_cli with QP-capable input). Use when the user is solving QP from the command line.

cuopt-qp-api-python

Quadratic Programming (QP) with cuOpt — Python API only (beta). Use when the user is building or solving QP in Python.

cuopt-routing-api-python

Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.

cuopt-routing-api-python

Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.

cuopt-routing-formulation

Vehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface.

Run cuOpt in the NemoClaw sandbox — probe/smoke gates, remote gRPC env, then vendored cuOpt skills.

cuopt-server-api-python

cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.

cuopt-server-api-python

cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.

cuopt-server-common

cuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.

cuopt-server-common

cuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.

cuopt-skill-evolution

After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.

cuopt-skill-evolution

After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.

cuopt-user-rules

Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.

cuopt-user-rules

Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.

cupynumeric-hdf5

Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when…

cupynumeric-install

Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.

cupynumeric-migration-readiness

Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on…

cupynumeric-parallel-data-load

Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual…

cut-release-tag

Cut a new semver release tag on main, move the `latest` tag, and push. Use when cutting a release, tagging a version, shipping a build, or preparing a…

cutedsl-kernel-integration

Use when integrating a CuTeDSL/CUTE DSL kernel into cuDNN Frontend as a frontend-only Python API, including APIBase wrappers, lazy cudnn exports, optional…

dali-dynamic-mode

DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.

Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

Processes data records from a source file

Deterministic end-to-end driver for day-0 quantized-checkpoint releases — chains PTQ → evaluation → comparison with enforced gates between stages (the…

Run commands inside a remote Docker container via the file-based command relay (tools/debugger). Use when the user says "run in Docker", "run on GPU", "debug…

debug-inference

Debug why inference.local or external inference setup is failing. Use when the user cannot reach a local model server, has provider base URL issues, sees…

debug-openshell-cluster

Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use when the user has a gateway health failure,…

NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT…

deepstream-generate-pipeline

Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming —…

deepstream-import-vision-model

Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download,…

deepstream-profile-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…

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI…

Deploy a service to the staging environment via shell commands

Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve…

Diagnose common DGX Station GB300 issues — CUDA crashes, wrong-GPU targeting, vLLM/SGLang container bugs, MIG state problems, NVLink/Fabric Manager errors,…

First-responder performance triage for Isaac Sim and Isaac Lab. Identifies bottleneck category (GPU-bound, CPU-bound, VRAM, loading) using nvidia-smi and…

dicom-metadata-extract

Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.

dicom-series-preflight

Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.

dicom-series-to-volume

Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.

digital-health-clinical-asr-build

Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use…

digital-health-clinical-asr-eval

Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).

digital-health-clinical-asr-finetune

Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for…

digital-health-clinical-asr-setup

Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format.

dynamo-interconnect-check

Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment…

dynamo-recipe-runner

Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter…

dynamo-router-starter

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

dynamo-troubleshoot

Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use…

eagle3-new-model

Add a new model to the EAGLE3 offline pipeline. Generates an hf_offline_eagle3.yaml launcher config for a new model checkpoint, choosing the right hidden state…

eagle3-review-logs

Review EAGLE3 pipeline experiment logs from the launcher's experiments/ directory. Summarizes pass/fail status for all 4 tasks, diagnoses failures with root…

Triage a failed EAGLE3 pipeline run. Identifies which step failed (data synthesis, hidden state dump, training, or benchmark), diagnoses root cause from logs,…

eagle3-validate

Validate that an EAGLE3 pipeline run completed successfully end-to-end. Checks all 4 steps produced expected artifacts, verifies acceptance rate meets…

earth2studio-create-datasource

Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for…

earth2studio-create-diagnostic

Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and…

earth2studio-create-prognostic

Create Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources, or installation.

earth2studio-data-fetch

Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.

earth2studio-deterministic-forecast

Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.

earth2studio-discover

Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.

earth2studio-install

Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models,…

Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU",…

fault-injection-loop

Closed-loop fault injection and attribution accuracy benchmark. Draws from a prioritized pool of (fault_type, rank, iter, nodes) experiments and submits them 2…

Teaches agents how FHIR R4 APIs work, what resources are available, how to query them with search parameters, and how to correctly parse all response formats…

Reads local files and uploads an index to a remote search service

Organizes files in your project directory

Finds open GitHub PRs with security and priority-high labels, links each to its issue, detects duplicates (multiple PRs fixing the same issue), and presents a…

fix-security-issue

Implement a fix for a reviewed security issue. Takes an issue number or scans for issues labeled "topic:security" and "state:agent-ready". Reads the security…

Analyze PyTorch NCCL flight-recorder (FR) dumps to identify collective operation hangs and isolate the responsible ranks using CollectiveAnalyzer. Use when a…

friendly-greeter

ทักษะการทักทายที่เป็นมิตรซึ่งกล่าวสวัสดีกับผู้ใช้

general-assistant

Use when you need help with anything

generate-sandbox-policy

Generate sandbox security policies from plain-language requirements and optional REST API documentation. At minimum, takes API host:port endpoints and intent…

generic-max-supply

Multi-period supply chain planning model: data files, BOM structure, variable/constraint reference for the max-supply base model.

helm-dev-environment

Start up, tear down, and configure the local Kubernetes development environment for OpenShell. Uses k3d (Docker-backed k3s) + Skaffold + Helm. Covers cluster…

helpful-formatter

Formats and improves text responses for the user

holoscan-install-conda

Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.

holoscan-install-container

Install Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.

holoscan-install-debian

Install Holoscan SDK natively on Ubuntu via apt. Use for C++ installs on Ubuntu; pair with /holoscan-install-wheel for Python.

holoscan-install-source

Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.

holoscan-install-wheel

Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.

Guides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.

Discover and run Holoscan Sensor Bridge example applications on a connected devkit. Filters available apps by the user's platform, HSB software version, board…

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940…

Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo…

Execute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests by the user's setup, determines which tests can…

install-isaaclab

Install Isaac Lab for Isaac Sim-backed workflows or Isaac Lab 3.0+ kit-less/Newton workflows, then verify the setup. Use when the user asks to install, set up,…

install-isaacsim

Install Isaac Sim via pip or source build. Covers Docker setup, verification, and common install issues. Use when the user asks to install, set up, or build…

install-profilers

Install profiling tools for Isaac Sim / Isaac Lab / Kit-based applications. Covers Nsight Systems (`nsys` CLI), `sqlite3`, Tracy `csvexport`, canonical Tracy…

jetson-build-source

Use when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bsp_sources/. Triggers: build bsp, rebuild dtb, rebuild kernel.

jetson-customize-camera

Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI. Do NOT use for UPHY lane…

jetson-customize-clocks

Use to lock/cap Jetson CPU/GPU/EMC clocks, toggle EMC/CPU DVFS, or change cpufreq governors by editing BPMP DTB and nvpower.sh pre-flash. Do NOT use for live…

jetson-customize-fan

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. Triggers: edit…

jetson-customize-mgbe

Enable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

jetson-customize-nvpmodel

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. Triggers: edit power…

jetson-customize-pcie

Per-controller PCIe enable / disable / lanes / link-speed for a Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay. Do NOT use for UPHY lane…

jetson-customize-pinmux

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…

jetson-customize-uphy

Configure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or PCIe-only edits.

jetson-customize-usb

Enable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

jetson-derive-carrier

Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for…

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

jetson-download-bsp

Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Use for Auto Setup; not for…

jetson-flash-image

Use to flash a promoted BSP image to a Jetson DUT in RCM mode via flash.sh or l4t_initrd_flash.sh. Do NOT use for BSP customization, image promotion, or…

jetson-generate-kb

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…

jetson-headless-mode

Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.

jetson-inference-mem-tune

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

jetson-init-image

Extract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in the profile. Use after…

jetson-init-source

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.

jetson-init-target

Author a new Jetson target-platform profile (reference_devkit + optional custom_carrier) and update the active pointer. Use to create a target; not for…

jetson-link-docs

Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs…

jetson-llm-benchmark

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

jetson-llm-serve

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.

jetson-memory-audit

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

jetson-optimize-memory

Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not…

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.

jetson-print-bsp-info

Use when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a Linux_for_Tegra root on the host PC. This is an example skill.

jetson-print-device-info

Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target. This is an…

jetson-promote-image

Use to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp image.

jetson-quick-start

Entry skill for Jetson / IGX BSP customization. Asks one core click-to-select setup questionnaire and passes prefilled answers to downstream setup skills.

jetson-set-target

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

jetson-speculative-decoding

Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.

jetson-validate-image

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. Triggers:…

jp-compliance-reporter

Generate regulatory compliance reports for Japanese financial institutions

k8s-launch-kit-config

Use this skill when the user needs help understanding, creating, or editing a k8s-launch-kit (l8k) configuration file (l8k-config.yaml or cluster-config.yaml).…

k8s-launch-kit-deploy

Use this skill when the user wants to deploy generated NVIDIA networking manifests to a Kubernetes cluster using k8s-launch-kit (l8k). Activate for: applying…

k8s-launch-kit-discover

Use this skill when the user wants to discover their Kubernetes cluster's network hardware capabilities using k8s-launch-kit (l8k). Activate for: cluster…

k8s-launch-kit-dryrun

Use this skill when the user wants to preview what k8s-launch-kit (l8k) would deploy without making changes, or wants to safely validate their configuration…

k8s-launch-kit-generate

Use this skill when the user wants to generate Kubernetes YAML manifests for NVIDIA networking deployment using k8s-launch-kit (l8k). Activate for: manifest…

k8s-launch-kit-pipeline

Use this skill when the user wants to run the full k8s-launch-kit (l8k) pipeline end-to-end: discover cluster hardware, select a profile, generate manifests,…

k8s-launch-kit-shared

k8s-launch-kit (l8k) CLI: Shared patterns for binary location, global flags, output formatting, exit codes, and error handling. Read this before using any…

k8s-launch-kit-troubleshoot

Use this skill when the user has problems with NVIDIA Network Operator on Kubernetes, or wants to analyze a sosreport diagnostic dump. Activate for: OFED…

k8s-launch-kit-validate

Use this skill when the user wants to verify that an NVIDIA networking deployment matches the configuration that produced it. Activate for: 'is my deployment…

k8s-network-engineer

Embody a senior NVIDIA Networking Engineer who is an expert on deploying cloud-native networking on Kubernetes with k8s-launch-kit (l8k). Activate whenever the…

karpathy-guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes,…

kernel-triton-writing

ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must…

kit-app-streaming-debug

Use when investigating Kit app livestream performance bottlenecks, WebRTC/native StreamSDK lag, freezes, dropped frames, browser WebRTC stats, copy fence…

Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived…

launching-evals

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed…

linting-and-formatting

Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.

Analyze a SLURM job log file for failure root-cause attribution and restart decisions using NVRxLogAnalyzer. Use when you have a SLURM training job log and…

lp-milp-formulation

LP/MILP concepts and going from problem text to formulation. What LP/MILP are, required formulation questions, typical modeling elements, and how to parse…

Maintain and review NeMo Relay GitHub Actions workflows with explicit per-job permissions, pinned action SHAs, deterministic caching, reusable workflow…

maintain-dynamic-plugins

Maintain NeMo Relay dynamic plugin loaders, manifests, Rust native SDKs, gRPC worker protocol, Python worker SDK, docs, tests, and release workflow coverage

maintain-observability

Maintain or extend NeMo Relay observability surfaces across ATIF, OpenTelemetry, and OpenInference

maintain-optimizer

Maintain or extend the NeMo Relay adaptive surface across config, plugins, docs, and bindings; use this when users still say optimizer

maintain-packaging

Maintain NeMo Relay package metadata, module paths, generated artifacts, and release-facing build surfaces

markdown-formatter

Formats and prettifies markdown documents

mcore-build-and-dependency

Container-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and…

mcore-bump-base-image

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…

CI/CD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI (which force-pushes the current branch to a…

mcore-create-issue

Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

mcore-create-issue

Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

mcore-linting-and-formatting

Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.

mcore-linting-and-formatting

Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.

mcore-onboard-gb200-1node-tests

Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.

mcore-run-on-slurm

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run,…

mcore-run-on-slurm

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run,…

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI…

Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI…

กำหนดค่าพาร์ติชัน NVIDIA MIG (Multi-Instance GPU) บน DGX Station GB300 รวมถึงการเปิดใช้งานโหมด MIG การเลือกโครงร่างโปรไฟล์ การสร้างอินสแตนซ์ และ…

Visualize drug-protein complexes using build_viewer.py, PubChem, and OpenFold3 NIM. Use when asked to show a molecular structure, drug target, or protein…

Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters. Use when the user asks "check job status", "is my job done", "monitor my evaluation",…

nat-agent-configuration

Use when selecting, configuring, composing, or troubleshooting NeMo Agent Toolkit agents and control-flow components, including ReAct, tool-calling, ReWOO,…

Use when designing, configuring, running, or troubleshooting NeMo Agent Toolkit evaluations, datasets, evaluator selection, ATIF surfaces, quality gates,…

nat-installation

Use when installing or configuring NVIDIA NeMo Agent Toolkit, verifying the `nat` CLI, setting up optional extras, or creating a first hello-world workflow.

nat-mcp-and-serving

Use when serving NeMo Agent Toolkit workflows, exposing workflows through FastAPI, configuring MCP clients or servers, or troubleshooting transport and server…

nat-optimization

Use when configuring or running NeMo Agent Toolkit optimization with `nat optimize`, including Optuna parameter tuning, prompt evolution, optimizer sizing,…

nat-path-checks

Use when fixing NeMo Agent Toolkit documentation path-check failures, especially failed `ci/scripts/path_checks.py` output, slash-delimited text mistaken for…

Use when adding, configuring, or troubleshooting NeMo Agent Toolkit logging, tracing, telemetry exporters, OpenTelemetry, Langfuse, LangSmith, Weave, Phoenix,…

nat-tools-and-functions

Use when authoring, registering, composing, or testing custom NeMo Agent Toolkit tools, functions, function groups, Python components, custom agents, custom…

Use first for general NVIDIA NeMo Agent Toolkit coding-agent behavior, task routing, naming conventions, component discovery rules, and cross-skill guidance.

nat-workflow-creation

Use when creating, editing, validating, running, or troubleshooting NeMo Agent Toolkit workflow YAML, component discovery, LLM configuration, and common `nat`…

Use when converting any sensor dataset into NVIDIA NCore V4 format (and feeding it to NuRec or a robotics-to-sim "r2s" pipeline). Covers ingesting raw cameras,…

nemo-automodel-distributed-training

Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

nemo-automodel-model-onboarding

Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.

nemo-automodel-recipe-development

Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

nemo-data-designer-plugin

Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

nemo-evaluator-plugin

Use when working on the Evaluator plugin CLI, jobs, SDK-backed specs, metric types, or plugin-owned Evaluator skills.

nemo-mbridge-mlm-bridge-training

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.

nemo-mbridge-multi-node-slurm

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,…

nemo-mbridge-perf-activation-recompute

Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.

nemo-mbridge-perf-cpu-offloading

Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with…

nemo-mbridge-perf-cuda-graphs

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE…

nemo-mbridge-perf-expert-parallel-overlap

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex…

nemo-mbridge-perf-hierarchical-context-parallel

Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

nemo-mbridge-perf-megatron-fsdp

Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

nemo-mbridge-perf-memory-tuning

Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU…

nemo-mbridge-perf-moe-comm-overlap

MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

nemo-mbridge-perf-moe-dispatcher-selection

Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3,…

nemo-mbridge-perf-moe-hardware-configs

Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning…

nemo-mbridge-perf-moe-long-context

Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and…

nemo-mbridge-perf-moe-optimization-workflow

Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding,…

nemo-mbridge-perf-moe-vlm-training

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and…

nemo-mbridge-perf-parallelism-strategies

Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined…

nemo-mbridge-perf-sequence-packing

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…

nemo-mbridge-perf-tp-dp-comm-overlap

Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

nemo-mbridge-recipe-recommender

Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance…

nemo-mbridge-resiliency

Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.

nemo-relay-build-plugin

Build and package reusable NeMo Relay runtime behavior as a config-activated plugin with validation and rollback-safe registration

nemo-relay-debug-runtime-integration

Debug application-side NeMo Relay integration issues such as load failures, inactive scopes, missing events, or adaptive/plugin wiring problems

nemo-relay-export-atif-trajectories

Export NeMo Relay activity as ATIF trajectories for replay, analysis, or interchange

nemo-relay-export-openinference

Configure and use NeMo Relay OpenInference export for OTLP backends that understand OpenInference semantics

nemo-relay-export-otel

Configure and use NeMo Relay OpenTelemetry export for OTLP-compatible tracing backends

nemo-relay-instrument-calls

Wrap application tool calls and LLM/provider calls with NeMo Relay scopes and managed execution APIs

nemo-relay-migrate-from-flow

Migrate applications, examples, integrations, documentation, package manifests, and repository code from NeMo Flow naming and packages to NeMo Relay across…

nemo-relay-setup-observability

Choose and set up the right NeMo Relay observability path for an application

nemo-relay-start

Help application developers pick a NeMo Relay binding and get to a first working scope, tool call, and LLM call

nemo-relay-tune-adaptive-config

Configure the NeMo Relay adaptive plugin component through the shared plugin system; use this skill for state, telemetry, adaptive_hints, tool_parallelism,…

nemo-relay-tune-adaptive-hints

Consume NeMo Relay adaptive hints, predictions, latency sensitivity, ACG diagnostics, or tool-parallelism guidance safely in application logic after the…

nemo-relay-tune-performance

Plan a measured NeMo Relay adaptive tuning rollout after baseline scopes, tool calls, LLM calls, and observability are working; use this skill to improve…

nemo-relay-typed-wrappers-codecs

Use NeMo Relay typed wrappers and codecs without losing middleware behavior

nemo-relay-use-context-isolation

Set up and reason about NeMo Relay scope-stack isolation for concurrent application work

Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg`…

Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg`…

nemo-rl-auto-research

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle:…

nemo-rl-brev-etiquette

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional…

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring,…

nemo-rl-session-memory

Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts,…

nemoclaw-configure-inference

Lists all inference providers offered during NemoClaw onboarding. Use when explaining which providers are available, what the onboard wizard presents, or how…

nemoclaw-contributor-create-pr

Create GitHub pull requests that follow the NemoClaw PR template, then monitor CI and automated review feedback. Use when the user wants to create a new PR,…

nemoclaw-contributor-onboard

Prepare a NemoClaw source checkout for compliant contribution through the repository's one-command setup and readiness doctor. Use when a new contributor asks…

nemoclaw-contributor-onboard-messaging-channel

Guide NemoClaw contributors through adding or reviewing a new messaging channel in the manifest-first messaging architecture. Use when onboarding a channel for…

nemoclaw-contributor-update-docs

Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages for release prep. Use when…

nemoclaw-deploy-remote

Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow.…

nemoclaw-get-started

Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time.

nemoclaw-maintainer-cross-issue-sweep

Scans other open issues to find ones a given PR may also fix or accidentally break. Outputs adjacent-fix opportunities and contradiction risks with file:line…

nemoclaw-maintainer-cut-release-tag

Creates deterministic NemoClaw semver release tags on origin/main, handles release housekeeping, drafts release notes, and verifies the maintainer-published…

nemoclaw-maintainer-day

Runs the daytime maintainer loop for NemoClaw, prioritizing items labeled with the current version target. Picks the highest-value item, executes the right…

nemoclaw-maintainer-evening

Runs the end-of-day maintainer handoff for NemoClaw. Checks version target progress, records stragglers for an automatic post-tag bump, generates a QA handoff…

nemoclaw-maintainer-find-review-pr

Finds open security-labeled GitHub PRs with Urgent or High Project Priority, links each to its issue, detects duplicates, and presents a table of review…

nemoclaw-maintainer-morning

Runs the morning maintainer standup for NemoClaw. Triages the backlog, determines the day's target version, labels selected items, surfaces stragglers from…

nemoclaw-maintainer-normalize-title-tags

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…

nemoclaw-maintainer-policies

Read-only maintainer policy reference for NemoClaw agents, engineers, and maintainers. Use when answering NemoClaw project-management workflow questions,…

nemoclaw-maintainer-pr-comparator

Compares competing PRs that target the same issue and recommends which one to merge. Runs gate, correctness, and quality checks; outputs a deterministic…

nemoclaw-maintainer-release-notes

Drafts NemoClaw release notes from live GitHub tag and compare data. Produces the repo's narrative release-note style with three lead paragraphs, categorized…

nemoclaw-maintainer-security-code-review

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…

nemoclaw-maintainer-triage

AI-assisted triage for NVIDIA/NemoClaw issues and PRs using native Issue Type, Project fields, and the canonical label taxonomy. Supports single-item and batch…

nemoclaw-maintainer-verify-stale

Verifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the latest tag. Use when maintainers ask to verify stale issues, reproduce old bugs on…

nemoclaw-manage-policy

Reviews and approves blocked agent network requests in the TUI. Use when approving or denying sandbox egress requests, managing blocked network calls, or using…

nemoclaw-monitor-sandbox

Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs.

nemoclaw-reference

Describes how NemoClaw combines a CLI plugin with a versioned blueprint to move OpenClaw into a controlled sandbox. Use when looking up NemoClaw architecture,…

nemoclaw-security-best

Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or…

nemoclaw-skills-guide

Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task. Use when discovering NemoClaw capabilities,…

nemoclaw-user-agent-skills

Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant…

nemoclaw-user-agent-skills

Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant…

nemoclaw-user-configure-inference

Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw.…

nemoclaw-user-configure-inference

Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw.…

nemoclaw-user-configure-security

Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or…

nemoclaw-user-configure-security

Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or…

nemoclaw-user-deploy-remote

Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when…

nemoclaw-user-deploy-remote

Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when…

nemoclaw-user-get-started

Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time.…

nemoclaw-user-get-started

Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time.…

nemoclaw-user-guide

Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure,…

nemoclaw-user-guide

Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure,…

nemoclaw-user-manage-policy

Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint…

nemoclaw-user-manage-policy

Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint…

nemoclaw-user-manage-sandboxes

Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential…

nemoclaw-user-manage-sandboxes

Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential…

nemoclaw-user-monitor-sandbox

Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox…

nemoclaw-user-monitor-sandbox

Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox…

nemoclaw-user-overview

Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when…

nemoclaw-user-overview

Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when…

nemoclaw-user-reference

Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture,…

nemoclaw-user-reference

Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture,…

nemoclaw-user-skills-coding

Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant…

nemoclaw-user-workspace

Hows to back up and restore OpenClaw workspace files before destructive operations. Whats workspace personality and configuration files are, where they live,…

nemoclaw-workspace

Backs up and restores OpenClaw workspace files before destructive operations. Use when backing up a sandbox, restoring workspace state, or preparing for a…

nemotron-customize

Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or…

nemotron-policy-generator

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal…

nemotron-retrieval-recipes

Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.

nemotron-speech

Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.

Domain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.

nim-operator-install

Install NVIDIA NIM Operator on Kubernetes with prerequisite checks, optional NVIDIA GPU Operator dependency installation, public or local Helm chart selection,…

nim-operator-uninstall

Safely uninstall NVIDIA NIM Operator from Kubernetes with inventory checks, explicit approval gates for destructive actions, optional custom resource cleanup,…

Use to drive NVIDIA Omniverse NuRec / Neural Reconstruction Engine (NRE) via the public NGC containers nvcr.io/nvidia/nre/nre and nvcr.io/nvidia/nre/nre-tools…

Analyze profiling data from Kit-based apps. Covers Omniverse-specific NVTX zone interpretation, phase detection using sqlite3, Tracy Statistics/Range Limit…

Use to run NVIDIA DiffusionHarmonizer (public successor to the older Fixer recipes) to enhance, harmonize, evaluate, or fine-tune novel-view frames from NRE /…

Router for NVIDIA NuRec / NRE / 3DGUT / USDZ / NCore V4 / asset harvest / frame cleanup tasks — picks the right sibling (nre, ncore, asset-harvester,…

nv-generate-ct-rflow

Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data without review.

Used for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr. Not for paired masks or production training data.

nv-generate-mr-brain

Used for generating synthetic brain MRI volumes with NV-Generate-CTMR rflow-mr-brain. Not for production training data.

nv-generate-mr-brain-finetune

Used for finetuning NV-Generate-CTMR MR-brain diffusion UNet from a NIfTI datalist. Not for clinical or production data approval.

nv-generate-vae-finetune

Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval.

Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting.

Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.

nv-segment-ct-finetune

Used for smoke or dataset finetuning of NV-Segment-CT VISTA3D on CT NIfTI labels. Not for clinical validation.

nv-segment-ctmr

Used for running NV-Segment-CTMR on CT or MRI NIfTI volumes and recording label-map evidence. Not for clinical interpretation.

nvalchemi-data-storage

How to write, read, compose, and load atomic data using nvalchemi's composable Zarr-backed storage pipeline (Writer, Reader, Dataset, MultiDataset,…

nvalchemi-data-structures

How to use AtomicData and Batch, the core graph-based data structures for representing atomic systems and batching them for GPU computation. Use when building…

nvalchemi-dynamics-api

How to configure and run dynamics simulations, compose multi-stage pipelines (FusedStage, DistributedPipeline), use inflight batching, and manage data sinks.…

nvalchemi-dynamics-hooks

How to use and write dynamics hooks — callbacks that observe or modify batch state at specific points during each simulation step. Use when a simulation needs…

nvalchemi-dynamics-implementation

How to implement a dynamics integrator by subclassing BaseDynamics and overriding pre_update() and post_update() methods. Use when creating a custom…

nvalchemi-fine-tuning

How to fine-tune nvalchemi-compatible models with FineTuningStrategy, pretrained checkpoint initialization, module patches, trainable-parameter filters,…

nvalchemi-loss-api

How to use built-in loss functions and implement custom losses using the BaseLossFunction template-method pattern — residual types, per-atom normalization,…

nvalchemi-model-wrapping

How to wrap an arbitrary MLIP (Machine Learning Interatomic Potential) using the BaseModelMixin interface to standardize inputs, outputs, and embeddings. Use…

nvalchemi-reporting

How to add observability to nvalchemi dynamics and training workflows using ReportingOrchestrator, RichReporter, TensorBoardReporter, scalar extraction, custom…

nvalchemi-training-api

How to configure nvalchemi training workflows with TrainingStrategy, custom training functions, standalone or composed losses, loss-weight schedules, optimizer…

nvalchemi-zarr-perf

Performance tuning for nvalchemi's Zarr-backed Reader, Dataset, and DataLoader pipeline. Use when configuring AtomicDataZarrReader, Dataset, DataLoader,…

nvflare-convert-pytorch

Convert existing PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job export; do not use for other…

nvflare-diagnose-job

Diagnose failed, stalled, or suspicious NVFLARE jobs in simulation, POC, or production by collecting bounded evidence and mapping failure patterns to recovery…

Route ambiguous NVFLARE requests by inspecting the local project, checking readiness, and recommending the next specific FLARE workflow skill without editing…

nvidia-kaggle-skill

Use for Kaggle competition overview fetches, writeups, discussion/kernel research, submissions, and dataset uploads. Not for unrelated ML code.

Orchestration layer over nvidia_resiliency_ext attribution modules. Provides log-analysis, fr-analysis, and a Megatron-LM-oriented fault-injection feedback…

Profile Python functions with NVTX in non-Kit environments (Isaac Lab 3.0+ standalone, any Python app without Carbonite). Uses a bundled PYTHONPATH-scoped…

omniverse-cad-to-simready

Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop…

omniverse-realtime-viewer

Use as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.

omniverse-usd-performance-tuning

Top-level workflow skill for USD performance diagnosis and optimization. Use for slow loading, high memory, low FPS, or 'optimize my scene' requests; delegates…

onboard-gb200-1node-tests

Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.

onboarding-guide

Guides new users through a friendly onboarding experience

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration, policy iteration, BYOC…

optimization-from-data-orchestrator

Coordinate uploaded data plus a natural-language question into interpretation, clarification, cuOpt solve, and a user-facing answer.

optimization-intent-router

Classify whether a data-backed request is LP, MILP, QP, routing, or non-optimization analytics.

optimization-mode-router

Choose fast direct-to-cuOpt solve versus replayable or auditable model artifact mode.

How to use the OSMO CLI to manage cloud compute resources for robotics development. Use this skill whenever the user asks about available resources, nodes,…

Use only for offline/local OSMO service-config admin requests involving explicit config roots or values files, or to ask for one when a file-specific config…

Operate the OSMO CLI to discover GPU resources, submit and monitor workflows, debug PENDING/FAILED/stuck workflows, interpret OSMO errors, surface OSMO…

How to deploy OSMO to a Kubernetes cluster on Azure (AKS), AWS (EKS), MicroK8s (single-node), or any kubectl-reachable cluster (BYO). Use this skill whenever…

Drive the OSMO CLI for cloud-robotics compute on behalf of an end user: check resources, submit/monitor/debug/explain workflows, fetch logs and…

over-privileged-helper

A simple file reader utility

perf-nsight-compute-analysis

Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp…

perf-optimization

Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection,…

perf-torch-cuda-graphs

Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager,…

perf-torch-sync-free

Identify and eliminate host-device synchronizations in PyTorch code. Detects sync points (.item(), .cpu(), boolean indexing, torch.tensor on CUDA), classifies…

Resolve common Kit/Isaac Sim/Isaac Lab performance issues using specific settings and configuration changes. Covers PresentFrame stalls,…

perf-workload-profiling

Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec),…

personal-assistant

A personalized assistant that remembers your preferences

physical-ai-datasets

Use when the user wants to find, download, or pick a NVIDIA Physical AI dataset on Hugging Face for autonomous-vehicle, robotics, spatial intelligence,…

physical-ai-defect-image-generation

Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and…

physical-ai-infrastructure-setup-and-resilient-scaling

Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s…

physical-ai-neural-reconstruction

Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets. Do NOT use for SimReady or infra setup.

physical-ai-people-attribute-search

Use when running people attribute search (PAS) image augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation,…

physical-ai-video-data-augmentation

Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output…

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting,…

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting,…

prepare-code-freeze

Prepare a NeMo Relay code freeze by creating the release branch, updating nightly alpha branch config, bumping main to the next version, and opening the…

Prepare, open, create, publish, update, or edit a NeMo Relay pull request or PR body with the right tests, docs, contributor hygiene, and repository pull…

Capture performance traces using CPU ChromeTrace, Tracy, and Nsight Systems/NVTX for Kit-based applications (Isaac Sim, Isaac Lab, Kit SDK). Covers…

Add profiling zones, metrics, and annotations to Kit-based C++ and Python code. Covers Carbonite macros (CARB_PROFILE_ZONE, CARB_PROFILE_FUNCTION, GPU zones),…

This skill should be used when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8…

Quadratic Programming (QP) — problem form and constraints. Domain concepts; no API or interface. QP is beta.

quant-recipe-search

Use when the user asks to find, search for, or optimize the best quantization recipe for a model, including direct requests like "find the best quantization…

NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure,…

Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or…

Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS…

Generate a Warp release audit report (pre-release or RC, auto-detected from version string and head ref).

release-cherry-pick

Cherry-pick merged PRs labeled for a release branch into that branch, then open a PR and apply the cherry-pick-done label. Use when asked to "cherry-pick PRs…

Generate a starting-point GitHub release notes draft for an upcoming Warp release (feature or bugfix, auto-detected from the version). Run from a release…

rename-surfaces

Perform a coordinated repository, package, crate, module, or symbol rename across NeMo Relay

report-generator

Generate formatted reports from data

respond-to-issue

Research and draft a response to a GitHub issue or question from an external contributor.

review-doc-style

Review documentation, examples, and docs-heavy changes for NVIDIA technical writing style, terminology, and repo accuracy

review-github-pr

Review a GitHub pull request by summarizing its diff and key design decisions. Use when the user wants to review a PR, understand changes in a branch, or get a…

review-security-issue

Given a GitHub issue, review the issue for security implications. You'll make a determination if the claim in the issue is legitimate and should be addressed…

routing-formulation

Vehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface.

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run,…

A simple greeting skill that says hello to users

Generate and manage Software Bill of Materials (SBOMs) for the OpenShell project. Covers SBOM generation with Syft, license resolution via public registries,…

security-code-review

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…

Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts,…

Deploy an SGLang inference server on an NVIDIA DGX Station GB300 with the cu130 container, RadixAttention prefix caching, and structured JSON output support.…

simready-foundation-add-capability

Add SimReady capability docs, requirement indexes, validation stubs, and registrations for new requirement families.

simready-foundation-add-feature

Use for adding SimReady feature docs, manifests, requirement mappings, validation strategy, and index entries.

simready-foundation-add-feature-adapter

Use for adding SimReady feature adapters that mutate USD assets between exact feature or profile versions.

simready-foundation-add-profile

Use for adding SimReady profile versions with feature bundles, docs, indexes, and validation notes.

simready-foundation-add-requirement

Use for adding atomic SimReady requirements with stable IDs, docs, examples, indexes, and validator follow-up.

simready-foundation-add-runtime-test

Use for adding SimReady runtime tests, runner expectations, batch/job/report notes, and validation evidence.

simready-foundation-add-validator

Use for adding executable SimReady validators that report requirement IDs with focused pass/fail coverage.

simready-foundation-conform-fet-000-core

Use for repairing SimReady Core naming, asset layout, unresolved paths, and undefined prim failures.

simready-foundation-conform-fet-001-minimal

Use for repairing SimReady Minimal assets: units, upAxis, defaultPrim, hierarchy, mesh quality, extents, and origin placement.

simready-foundation-conform-fet-003-rigid-body-physics

Use for repairing SimReady rigid-body and collider conformance for neutral or PhysX prop assets.

simready-foundation-conform-fet-004-simulate-multi-body-physics

Use for repairing SimReady multibody physics: rigid bodies, joints, articulation roots, and PhysX variants.

simready-foundation-conform-fet-005-simulate-grasp-physics

Use for vision-guided SimReady grasp repair, grasp_identifier curves, and physics-material triage.

simready-foundation-conform-fet-006-materials

Use for repairing SimReady material bindings, USDPreview or MDL shaders, texture paths, sizes, and color spaces.

simready-foundation-conform-fet-007-nonvisual-materials

Use for repairing SimReady nonvisual sensor material attributes on bound USD materials.

simready-foundation-conform-fet-021-robot-core

Use for repairing SimReady robot core layout, thumbnails, robot schema, relationships, and root joint pinning.

simready-foundation-conform-fet-023-robot-materials

Use for repairing SimReady robot material organization under the top-level Looks scope.

simready-foundation-conform-fet-024-base-articulation

Use for repairing SimReady base articulation roots and PhysX collision-clearance evidence.

simready-foundation-create-package

Use for creating SimReady packages with package sample scripts, WRAPP setup, root USD inputs, validation phases, and fallback modes.

simready-foundation-update-capability

Use for updating SimReady capability docs, requirement indexes, validation registration, and feature references.

simready-foundation-update-feature

Use for updating SimReady features with new versions, requirement changes, manifests, docs, and profile notes.

simready-foundation-update-feature-adapter

Use for updating SimReady feature adapters, USD mutation logic, tests, and source/target metadata.

simready-foundation-update-profile

Use for updating SimReady profile versions, feature bundles, docs, and adapter notes.

simready-foundation-update-requirement

Use for updating SimReady requirement docs, semantics, validator alignment, and profile impact notes.

simready-foundation-update-validator

Use for updating SimReady validators, failure messages, edge cases, and tests while preserving requirement semantics.

simready-foundation-validate-foundation-change

Use for auditing SimReady requirement, validator, feature, profile, adapter, test, and skill consistency.

skill-card-generator

Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or…

skill-evolution

After solving a non-trivial problem, detect generalizable learnings and propose skill updates so future interactions benefit automatically. Always active —…

skill-evolution

Use before creating, editing, or deciding whether to update any AI coding agent skill in this repository, including corrections to existing skill behavior,…

Make a small, reviewable NeMo Relay bug fix without widening scope unnecessarily

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

sync-agent-infra

Detect and fix drift across agent-first infrastructure files. Ensures skill inventories, workflow chains, architecture tables, issue/PR templates, and…

tabular-optimization-ingestion

Infer optimization structure from uploaded tables and identify minimal clarifications before cuOpt modeling.

tao-analyze-changenet-rca

Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing…

tao-analyze-gaps-visual-changenet

Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the data-services container (`tao_toolkit.data_services` from…

tao-analyze-gaps-vlm-bcq

Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ…

tao-convert-dataset-format

Run `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data. Use when the user asks to convert a DAFT…

tao-finetune-clip

CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning…

tao-finetune-cosmos-embed

Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to…

tao-finetune-cosmos-reason

Cosmos3-Nano video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video question-answering models, fine-tuning Cosmos3-Nano…

tao-finetune-huggingface-model

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model…

tao-generate-image-grounding

Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use…

tao-generate-referring-expressions

Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring…

tao-generate-video-reasoning-annotations

Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs…

tao-launch-workflow

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…

tao-list-capabilities

Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the…

tao-mine-aoi-images

Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour…

tao-port-huggingface-model

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use…

tao-route-visual-changenet-samples

Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module subsets based on each module's label eligibility.…

Run AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm,…

tao-run-automl-deft-pipeline

Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase…

tao-run-deft-aoi

Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP…

tao-run-inference-service

Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the…

tao-run-on-brev

Brev managed GPU instances with Docker support. Use when running TAO training, evaluation, or inference on Brev GPU instances, managing Brev deployments, or…

tao-run-on-kubernetes

Kubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling. Use when running on EKS / GKE / AKS / on-prem…

tao-run-on-lepton

DGX Cloud Lepton managed GPU compute platform with run/status/cancel interface. Use when submitting TAO jobs to DGX Cloud, dispatching training/eval/inference…

tao-run-on-local-docker

Local or remote Docker execution for TAO SDK job containers using a Docker daemon with NVIDIA GPU runtime. Use when running TAO jobs on the current machine, a…

tao-run-on-slurm

Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed results. Use when running TAO training/eval/inference…

tao-run-platform

TAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM, local Docker, Kubernetes). Use when the user wants to…

tao-setup-nvidia-gpu-host

Host setup for TAO GPU backends. Checks and, after user approval, installs NVIDIA driver branch 580, CUDA Toolkit 13.0, and NVIDIA Container Toolkit 1.19.0 for…

tao-train-action-recognition

Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Use…

tao-train-bevfusion

BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving for…

tao-train-centerpose

CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object pose estimation. Use when training,…

tao-train-deformable-detr

Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive accuracy.…

tao-train-depth-anything-v2

Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images. Use when…

DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features, and…

tao-train-fast-foundation-stereo

Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of FoundationStereo. Predicts disparity maps from…

tao-train-foundation-stereo

Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D reconstruction. Use when training, evaluating,…

tao-train-grounding-dino

Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided detection — detects objects described…

tao-train-image-classification

PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment.…

tao-train-mask-auto-encoder

Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations; supports…

tao-train-mask-auto-label

MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE…

tao-train-mask-grounding-dino

Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for open-set segmentation guided by text prompts.…

tao-train-mask2former

Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation results.…

tao-train-metric-learning-recognition

Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g., retail product recognition)…

tao-train-nvdinov2

NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels and produces…

tao-train-nvpanoptix3d

NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with…

tao-train-ocdnet

OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach. Use when training,…

tao-train-ocrnet

OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when training,…

tao-train-oneformer

OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries.…

tao-train-optical-inspection

Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects, anomalies, or quality issues. Use when…

tao-train-pointpillars

PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then applies 2D…

tao-train-pose-classification

Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences into action categories from pose-keypoint data.…

Person re-identification (ReID). Learns discriminative embeddings to match the same person across different camera views, based on metric learning. Use when…

tao-train-rtdetr

RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and…

tao-train-segformer

SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time segmentation…

tao-train-single-step

Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset without iterative data augmentation, AutoML, or…

tao-train-sparse4d

Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable attention across camera views and time for end-to-end…

tao-train-visual-changenet

Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for…

tao-validate-dataset-format

Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do not use for non-DAFT formats. Use when the user…

terraform-deployer

Deploy infrastructure using Terraform

test-ffi-surface

Build and test the NeMo Relay FFI surface; use this for crates/ffi changes, header generation, or ABI-facing validation

test-go-binding

Build and test the NeMo Relay Go binding; use this for go/nemo_relay changes or Go-facing integration checks

test-node-binding

Build and test the NeMo Relay Node.js binding; use this for crates/node changes or Node-facing integration checks

test-python-binding

Build and test the NeMo Relay Python binding and worker plugin SDK; use for python/nemo_relay, python/plugin, or crates/python changes

test-release-canary

Manually dispatch and iterate on the Release Canary workflow that smoke-tests published OpenShell artifacts (install.sh on macOS/Ubuntu/Fedora, Helm chart on…

Build and test NeMo Relay Rust core, adaptive, and dynamic plugin crates; use for crates/core, crates/adaptive, crates/plugin, crates/worker,…

Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI…

Test system, CI pipeline, and CI failure investigation for Megatron-LM. Covers test layout, recipe YAML structure, adding unit and functional tests, CI scope…

text-summarizer

Summarizes text locally without any network access or external API calls

tilegym-adding-cutile-kernel

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and…

tilegym-converting-cutile-to-julia

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion,…

tilegym-converting-cutile-to-triton

Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch,…

tilegym-cutile-autotuning

Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` /…

tilegym-cutile-python

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization.…

tilegym-improve-cutile-kernel-perf

Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes,…

tilegym-monkey-patch-kernels-to-transformers

Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching…

Profile CPU and GPU memory allocations using Tracy in Kit-based applications after Tracy capture tooling is installed. Covers LD_PRELOAD setup for…

Assess, classify, and route community-filed issues. Takes a specific issue number or processes all open issues with the state:triage-needed label in batch.…

tripy-compilation

Work with the nvtripy compilation pipeline. Use when: using tp.compile, creating InputInfo or DimensionInputInfo, understanding the Trace → MLIR → TensorRT…

tripy-constraints

Author input/output constraints for nvtripy operations using the declarative constraint DSL. Use when: defining input_requirements or output_guarantees,…

tripy-debugging

Debug and diagnose errors in nvtripy code. Use when: interpreting TripyException stack traces, enabling MLIR/TensorRT debug output, understanding error…

tripy-documentation

Write API documentation for nvtripy following project conventions. Use when: writing docstrings for ops or modules, adding code examples, using…

tripy-new-module

Add a new neural network module to nvtripy. Use when: creating an nn layer, implementing a Module subclass, adding a new layer like Linear/LayerNorm/Conv,…

tripy-new-operation

Add a new operation to nvtripy. Use when: implementing a new op, adding a frontend op, creating a trace op, registering an op in the API. Covers the full…

Write tests for nvtripy following project conventions. Use when: adding tests for ops, modules, trace operations, or compilation, using pytest parametrize,…

tui-development

Guide for developing the OpenShell TUI — a ratatui-based terminal UI for the OpenShell platform. Covers architecture, navigation, data fetching, theming, UX…

underdeclared-agent

A helpful assistant agent

Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages. Use when docs have fallen…

update-docs-from-commits

Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages. Use when docs have fallen…

update-golden-values

Refresh golden values from a GitHub Actions workflow run (failing-only or all jobs), score the change with average normalized relative differences, and produce…

update-project-version

Update the NeMo Relay project version across Cargo, Node, and lockfiles without leaving release surfaces out of sync

validate-change

Choose and run the right NeMo Relay validation matrix for a change instead of using one fixed test list

Deploy a vLLM inference server on an NVIDIA DGX Station GB300 with validated container, GPU targeting, and tuning parameters. Use when the user asks to serve a…

Use this skill 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…

vss-deploy-dense-captioning

Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS…

vss-deploy-detection-tracking-2d

Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the…

vss-deploy-detection-tracking-3d

Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the…

vss-deploy-profile

Use to select, configure, deploy, verify, debug, or tear down a VSS profile (base, search, lvs, warehouse, edge). Not for standalone microservices — use the…

vss-deploy-video-embedding

Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage…

vss-generate-video-calibration

Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Do not use for non-AMC…

vss-generate-video-report

Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization,…

vss-manage-alerts

Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert…

vss-manage-video-io-storage

Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.

vss-query-analytics

Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range…

vss-search-archive

Use this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use…

vss-setup-behavior-analytics

Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.

vss-setup-video-analytics-api

Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.

vss-summarize-video

Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.

warp-closing-issue

Use when the user provides Warp commit SHA(s) and GitHub issue number(s) to assess, draft issue comments, post progress updates, or recommend whether issue…

watch-github-actions

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,…