- Jetson Derive CarrierBootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for module-level or kernel-DTB changes.NVIDIA/skills3,503
- Jetson DiagnosticRead-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.NVIDIA/skills3,503
- Jetson Download BspDownload NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Use for Auto Setup; not for extraction or profile edits.NVIDIA/skills3,503
- Jetson Flash ImageUse 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 carrier derivation.NVIDIA/skills3,503
- Jetson Generate KbBuild 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 editing profile fields.NVIDIA/skills3,503
- Jetson Headless ModePlan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.NVIDIA/skills3,503
- Jetson Inference Mem TunePick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.NVIDIA/skills3,503
- Jetson Init ImageExtract 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-target; not for source-tree setup.NVIDIA/skills3,503
- Jetson Init SourceSet up the BSP source workspace: Linux_for_Tegra overlay tracker, bsp_sources, Crosstool-NG toolchain. Use after jetson-init-image; not for fetching inputs.NVIDIA/skills3,503
- Jetson Init TargetAuthor a new Jetson target-platform profile (reference_devkit + optional custom_carrier) and update the active pointer. Use to create a target; not for switching existing profiles.NVIDIA/skills3,503
- Jetson Link DocsBind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs on disk; not for downloading.NVIDIA/skills3,503
- Jetson Llm BenchmarkBenchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.NVIDIA/skills3,503
- Jetson Llm ServeStand 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.NVIDIA/skills3,503
- Jetson Memory AuditMeasure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.NVIDIA/skills3,503
- Jetson Optimize MemoryReclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not for CPU/GPU frequency tuning.NVIDIA/skills3,503
- Jetson PackagePick 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.NVIDIA/skills3,503
- Jetson Print Bsp InfoUse 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.NVIDIA/skills3,503
- Jetson Print Device InfoUse 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 example skill.NVIDIA/skills3,503
- Jetson Promote ImageUse to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp image.NVIDIA/skills3,503
- Jetson Quick StartEntry skill for Jetson / IGX BSP customization. Asks one core click-to-select setup questionnaire and passes prefilled answers to downstream setup skills.NVIDIA/skills3,503
- Jetson Set TargetSwitch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target; not for authoring profiles — use jetson-init-target instead.NVIDIA/skills3,503
- Jetson Speculative DecodingAdd EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.NVIDIA/skills3,503
- Jetson Validate ImageUse 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: validate bsp, on-target validation.NVIDIA/skills3,503
- Jetson Video BenchmarkUse when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker capacity with authenticated samples and user media, or producing a clearly labeled documentation-derived planning estimate when representative media is absent. Also use for a video request limited to PSNR or SSIM, to apply the terminal scope response.NVIDIA/skills3,503
- Jetson Video CapabilityUse when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled from live APIs, authenticated NVIDIA samples, and NVIDIA documentation; also applies the content-DRM scope.NVIDIA/skills3,503
- Jetson Video PipelineUse when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise acceptance workflows.NVIDIA/skills3,503
- Jetson Video RecipeUse when turning a Jetson encoder use case into one surface-neutral recipe with native Video Codec SDK and PyNvVideoCodec projections.NVIDIA/skills3,503
- Jetson Video SetupUse when installing, repairing, reusing, inspecting, or verifying readiness of the native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson, including the one-frame encode/decode smoke test with official samples, and when interpreting what those readiness results, including CPU-buffer and device-memory sample modes, do and do not establish.NVIDIA/skills3,503
- Kermt Add Cmim PretrainConvert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latent_dist, then continue pretraining on the user's corpus as hybrid (vocab + contrast). Effectively kermt-continue-pretrain with a one-time ckpt-conversion step prepended.NVIDIA/skills3,503
- Kermt Continue PretrainContinue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized training and write model bundles, prepared data, logs, and checkpoints to user-selected host directories.NVIDIA/skills3,503
- Kermt EmbedExtract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized embedding extraction and write model bundles, per-readout .npy embeddings, canonical SMILES, and validity arrays to user-selected host directories.NVIDIA/skills3,503
- Kermt FinetuneFinetune a pretrained KERMT encoder on a labeled CSV. Validate the checkpoint and data, prepare features, and run containerized training. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Write model bundles, prepared data, logs, and trained models to user-selected host directories.NVIDIA/skills3,503
- Kermt InferRun predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to kermt-finetune), validates the CSV, prepares the data (clean + rdkit_2d features), then launches main.py predict inside the kermt container (blocking, minutes-scale).NVIDIA/skills3,503
- Kermt MonitorCheck progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation). Reads run.json, queries docker for container state, tails the pretrain/finetune log, and parses progress lines (epoch, step, val loss).NVIDIA/skills3,503
- Kermt Pretrain ScratchPretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrain_ddp.py inside the kermt container (detached for long runs). Unlike kermt-continue-pretrain, no starting checkpoint is loaded — the model is randomly initialized.NVIDIA/skills3,503
- Kermt SetupBootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn't yet exist, and run a GPU smoke test inside the container. Every other kermt-* skill depends on this; invoke it first.NVIDIA/skills3,503
- Launch Nemo RlPlaybook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.NVIDIA/skills3,503
- Mcore Create IssueInvestigate a failing GitHub Actions run or job and create a GitHub issue for the failure.NVIDIA/skills3,503
- Mcore Linting And FormattingLinting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.NVIDIA/skills3,503
- Mcore Run On SlurmHow 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.NVIDIA/skills3,503
- Mcore Split PrSplit a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.NVIDIA/skills3,503
- Mcore TestingTest system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.NVIDIA/skills3,503
- Medtech Model Evidence ExportExports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evidence packs to MLflow. Use after inference, including NV-Generate runs; not for live training tracking, model registration, or clinical use.NVIDIA/skills3,503
- Molmim NimUse this skill for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization. Invoke for MolMIM, molecular embeddings, hidden states, latent decoding, sampling around a seed SMILES, CMA-ES guided molecule generation, QED or plogP optimization, hosted NVIDIA API calls, or local Docker deployment.NVIDIA/skills3,503
- Msa Search NimGenerate multiple sequence alignments (MSAs) for protein sequences using the ColabFold MSA-Search NIM. Use for homolog search, UniRef30/ColabFold env searches, A3M or FASTA alignments, paired MSA search for complexes, PDB70 structural templates, hosted NVIDIA API calls, or local Docker deployment. For local deployment, download the databases in parallel with aria2c and launch via NIM_MODEL_NAME (the recommended default fast path, ~14 min vs over 80 min for the built-in downloader); a plain dockeNVIDIA/skills3,503
- Msa Structure Prediction PipelineNOTE: your protein sequence and the retrieved MSA alignment are transmitted to external NVIDIA-hosted APIs (health.api.nvidia.com) on every call. Use local NIM containers for confidential or proprietary sequences. Run a complete protein structure prediction pipeline using NVIDIA BioNeMo NIMs: search for MSA alignments with MSA-Search (ColabFold), then predict the structure with OpenFold3 using the retrieved alignments. Use this skill whenever the user wants to predict a protein structure with maNVIDIA/skills3,503
- Nemo Automodel Distributed TrainingGuide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.NVIDIA/skills3,503
- Nemo Automodel Launcher ConfigConfigure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.NVIDIA/skills3,503
- Nemo Automodel Model OnboardingGuide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.NVIDIA/skills3,503
- Nemo Automodel Recipe DevelopmentCreate and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.NVIDIA/skills3,503
- Nemo Fabric Build AdapterBuild, migrate, review, and maintain third-party NVIDIA NeMo Fabric adapters against the public adapter contract. Use when creating adapter or target descriptors, mapping AgentConfig into an agent harness or custom-agent runtime, implementing start/invoke/stop, declaring schemas and capabilities, packaging discovery metadata, or assessing adapter conformance. Do not use for consumer applications that only call the NVIDIA NeMo Fabric SDK.NVIDIA/skills3,503
- Nemo Fabric IntegrateUse this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python SDK — translating the consumer's own application, job, or deployment config into an in-memory FabricConfig, choosing the single-invocation convenience API or an explicitly started runtime, validating with plan and doctor, and consuming normalized results, artifacts, and telemetry.NVIDIA/skills3,503
- Nemo Mbridge Mlm Bridge TrainingRun Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.NVIDIA/skills3,503
- Nemo Mbridge Multi Node SlurmConvert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocation.NVIDIA/skills3,503
- Nemo Mbridge Perf Activation RecomputeValidate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for activation memory OOMs or regressions involving recompute_granularity, recompute_num_layers, recompute_modules, recompute_method, selective recompute, full recompute, or activation checkpointing.NVIDIA/skills3,503
- Nemo Mbridge Perf Cpu OffloadingValidate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.NVIDIA/skills3,503
- Nemo Mbridge Perf Cuda GraphsValidate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.NVIDIA/skills3,503
- Nemo Mbridge Perf Expert Parallel OverlapValidate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.NVIDIA/skills3,503
- Nemo Mbridge Perf Hierarchical Context ParallelOperational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.NVIDIA/skills3,503
- Nemo Mbridge Perf Megatron FsdpOperational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.NVIDIA/skills3,503