NVIDIA.

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 updating uv.lock.

cicd

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

create-issue

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

linting-and-formatting

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

nightly-sync

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

onboard-gb200-1node-tests

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

respond-to-issue

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

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, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.

split-pr

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

testing

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

aiq-deploy

|

aiq-research

|

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.

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 up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.

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 recipe-runner for recipe deployment and troubleshoot for failure diagnosis.

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. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.

nvidia-skill-finder

>-

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 packaging that require conversion, material/physics assignment, SimReady conformance, validation, and optional package creation; deploy or verify Content Agents services first when property assignment is enabled; route single-stage work through nested references.

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 auth/runtime setup to Phase 0 owners.

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

>-

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.

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 (configs, logs, results), or set up the MLflow MCP server. ALWAYS triggers on mentions of MLflow, experiment results, run comparison, invocation IDs in the context of results, or MLflow MCP setup.

ad-add-fusion-transformation

>

ad-conf-check

>

ad-graph-dump

>

ad-model-onboard

>

ad-pipeline-failure-pr

>

add-benchmark

>

byob

Create custom LLM evaluation benchmarks using the BYOB decorator framework. Use when the user wants to (1) create a new benchmark from a dataset, (2) pick or write a scorer, (3) compile and run a BYOB benchmark, (4) containerize a benchmark, or (5) use LLM-as-Judge evaluation. Triggers on mentions of BYOB, custom benchmark, bring your own benchmark, scorer, or benchmark compilation.

ci-failure-retrieval

Retrieve and diagnose CI test failures from TensorRT-LLM pull requests using the GitHub API and Jenkins testReport API. Use when the user asks about CI failures on a PR, wants to see failed test details, or needs stdout/stderr from a CI run.

cudaq-guide

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

cuopt-developer

Contribute to NVIDIA cuOpt codebase including C++/CUDA, Python, server, docs, and CI. Use when the user wants to modify solver internals, add features, submit PRs, or understand the codebase architecture.

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 constraints, integer variables, scheduling, resource allocation, facility location, or production planning.

cuopt-qp-api-c

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-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-user-rules

Base behavior rules for using NVIDIA cuOpt. Read this FIRST before any cuOpt user task (routing, LP/MILP, QP, installation, server). Covers handling incomplete questions, clarifying data requirements, verifying understanding, and running commands safely.

exec-local-compile

Compile TensorRT-LLM on a compute node inside a Docker container. Use this when already on a compute node with GPUs visible.

exec-slurm-compile

Compile TensorRT-LLM on a SLURM cluster. Covers submitting a batch job with a container image, monitoring the job, and verifying the build. Use when the user wants to compile TRT-LLM remotely via SLURM rather than on a local compute node.

flashinfer-upgrade

>-

kernel-cute-writing

>

kernel-tileir-optimization

>

kernel-triton-writing

>

launching-evals

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.

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 problem statements (parameters, constraints, decisions, objective).

nel-assistant

Interactive config wizard for NeMo Evaluator Launcher (NEL). Use when the user wants to create a new evaluation config from scratch, set up an evaluation from existing configs, or modify a NEL config (deployment, tasks, multi-node, interceptors). ALWAYS triggers on mentions of creating configs, setting up evaluations, configuring models for evaluation, or modifying NEL YAML files. Do NOT use for monitoring, debugging, or analyzing already-running evaluations.

nemo-gym-docs

>

nemoclaw-contributor-create-pr

Create GitHub pull requests that follow the NemoClaw PR template. Use when the user wants to create a new PR, submit code for review, open a pull request, or push changes for review. Trigger keywords - create PR, pull request, new PR, submit for review, open PR, push for review.

nemoclaw-contributor-update-docs

Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages. Use when docs have fallen behind code changes, after a batch of features lands, or when preparing a release. Trigger keywords - update docs, draft docs, docs from commits, sync docs, catch up docs, doc debt, docs behind, docs drift.

nemoclaw-maintainer-cut-release-tag

Cut a new semver release — bump all version strings via bump-version.ts, open a release PR, and after merge tag main and push. Use when cutting a release, tagging a version, shipping a build, or preparing a deployment. Trigger keywords - cut tag, release tag, new tag, cut release, tag version, ship it.

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 workflow (merge gate, salvage, security sweep, test gaps, hotspot cooling, or sequencing), and reports progress. Use during the workday to land PRs and close issues. Designed for /loop (e.g. /loop 10m /nemoclaw-maintainer-day). Trigger keywords - maintainer day, work on PRs, land PRs, make progress, what's next, keep going, maintainer loop.

nemoclaw-maintainer-evening

Runs the end-of-day maintainer handoff for NemoClaw. Checks version target progress, bumps stragglers to the next patch version, generates a QA handoff summary, and cuts the release tag. Use at the end of the workday. Trigger keywords - evening, end of day, EOD, wrap up, ship it, cut tag, handoff, done for the day.

nemoclaw-maintainer-find-review-pr

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 table of review candidates. Use when looking for the next PR to review. Trigger keywords - find pr, find review, next pr, pr to review, duplicate pr, security pr.

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 previous versions, and outputs the daily plan. Use at the start of the workday. Trigger keywords - morning, standup, start of day, daily plan, what are we shipping today.

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 cleaning issue tags, bulk-renaming titles, or normalizing repo title hygiene.

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 checklist, and produces PASS/WARNING/FAIL verdicts. Use when reviewing pull requests for security vulnerabilities, hardcoded secrets, injection flaws, auth bypasses, or insecure configurations. Trigger keywords - security review, code review, appsec, vulnerability assessment, security audit, review PR security.

nemoclaw-maintainer-triage

AI-assisted label triage for NVIDIA/NemoClaw issues and PRs. Reads triage-instructions.md at runtime for consistent label guidance. Supports single-item mode (give it a number) and batch mode (fetches up to 50 unlabeled open items). On approval, applies labels and an optional triage comment via gh CLI, then logs the session to the daily-rhythm activity folder. Trigger keywords - triage, label issues, suggest labels, batch triage, triage issue, triage PR, label this, what labels.

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, choosing the right skill, or orienting in the project. Trigger keywords - skills, capabilities, what can I do, help, guide, index, overview, start here.

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 integration, or the .agents/skills/ directory. Trigger keywords - nemoclaw agent skills, ai coding assistant, cursor, claude code, copilot.

nemoclaw-user-configure-inference

Shows the NemoClaw-specific file paths and update flow for adding an auxiliary OpenClaw sub-agent model. Use when users ask how to add a second model, configure a sub-agent model, use Omni for vision tasks, configure agents.list, or use sessions_spawn in NemoClaw. Trigger keywords - nemoclaw additional model, nemoclaw sub-agent model, openclaw sub-agent, agents.list, sessions_spawn, vlm-demo, switch nemoclaw inference model, change inference runtime, nemoclaw local inference, ollama nemoclaw, vllm nemoclaw, local model server, openai compatible endpoint, nemoclaw inference options, nemoclaw onboarding providers, nemoclaw inference routing.

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 assessing control trade-offs. Trigger keywords - nemoclaw security best practices, sandbox security controls risk framework, nemoclaw credential storage, openshell provider, api key security, openclaw security controls, nemoclaw security boundary, prompt injection, tool access control.

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 deploying NemoClaw to a remote VM, onboarding a Brev instance, or migrating away from the legacy `nemoclaw deploy` wrapper. Trigger keywords - deploy nemoclaw remote gpu, nemoclaw brev cloud deployment, nemoclaw plugins, openclaw plugins, install openclaw plugin, nemoclaw onboard from dockerfile, nemoclaw telegram, telegram bot openclaw agent, openshell channel messaging, nemoclaw sandbox hardening, container security, docker capabilities, process limits.

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. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.

nemoclaw-user-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 the approval TUI. Trigger keywords - nemoclaw approve network requests, sandbox egress approval tui, customize nemoclaw network policy, sandbox egress policy configuration.

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 logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.

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 to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.

nemoclaw-user-reference

Describes the NemoClaw plugin and blueprint architecture and how they orchestrate the OpenClaw sandbox. Use when looking up architecture, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw plugin blueprint structure, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.

nemoclaw-user-workspace

Backs up and restores OpenClaw workspace files before destructive operations such as sandbox rebuilds. Use when downloading workspace files from a sandbox, uploading restored files into a new sandbox, or preserving sandbox state across rebuilds. Trigger keywords - nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.

nemotron-voice-agent-deploy

Deploy Nemotron Voice Agent on Workstation (x86), Jetson Thor, or Cloud NIMs. Real-time speech-to-speech using NVIDIA ASR, TTS, LLM with WebRTC/WebSocket transport.

perf-analysis

>

perf-host-analysis

>

perf-host-optimization

Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.

perf-nsight-compute-analysis

>

perf-nsight-systems

>-

perf-optimization

>

perf-torch-cuda-graphs

>-

perf-torch-sync-free

>-

perf-workload-profiling

>

ptq

This skill should be used when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4 AWQ", "quantize LLM", "quantize MoE", "quantize VLM", or needs to produce a quantized HuggingFace or TensorRT-LLM checkpoint from a pretrained model using ModelOpt.

qp-formulation

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

rag-blueprint

NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, and more).

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 for release/X.Y.Z", "pick PRs to release branch", or "cherry-pick labeled PRs".

routing-formulation

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

serve-config-guide

Generate a source-backed starting `trtllm-serve --config` YAML for

trtllm-code-contribution

>

trtllm-codebase-exploration

>