Nvidia Skills

skills/skills/mcore-create-issue

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

megatron-lm/skills/mcore-linting-and-formatting

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

skills/skills/mcore-linting-and-formatting

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

megatron-lm/skills/mcore-migrate-gpt-to-hybrid

Migration guide for moving Megatron Core GPTModel checkpoints, model providers, training commands, and layer mappings to HybridModel.

megatron-lm/skills/mcore-onboard-gb200-1node-tests

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

megatron-lm/skills/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,…

skills/skills/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,…

megatron-lm/skills/mcore-split-pr

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

skills/skills/mcore-split-pr

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

megatron-lm/skills/mcore-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…

skills/skills/mcore-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…

dgx-spark-playbooks/nvidia/station-ai-skills/assets/skills/mig-configure

Configure NVIDIA MIG (Multi-Instance GPU) partitions on the DGX Station GB300, including enabling MIG mode, choosing a profile layout, creating instances, and…

dgx-spark-playbooks/nvidia/station-healthcare-agent/assets/skills/molecular-viz

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

model-optimizer/plugins/modelopt/skills/monitor

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

nemo-agent-toolkit/skills/nat-agent-configuration

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

nemo-agent-toolkit/skills/nat-evaluation

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

nemo-agent-toolkit/skills/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.

nemo-agent-toolkit/skills/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…

nemo-agent-toolkit/skills/nat-optimization

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

nemo-agent-toolkit/skills/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…

nemo-agent-toolkit/skills/nat-telemetry

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

nemo-agent-toolkit/skills/nat-tools-and-functions

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

nemo-agent-toolkit/skills/nat-user-rules

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

nemo-agent-toolkit/skills/nat-workflow-creation

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

nurec-skills/skills/ncore

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,…

skills/skills/nemo-automodel-distributed-training

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

skills/skills/nemo-automodel-launcher-config

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

skills/skills/nemo-automodel-model-onboarding

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

skills/skills/nemo-automodel-recipe-development

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

skills/skills/nemo-data-designer-plugin

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