Agent skills by NVIDIA, page 4

Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink.

NVIDIA/skills

Generate novel drug-like molecules using the GenMol NIM microservice.

NVIDIA/skills

Orient users to the i4h workflow runtime and route them to the correct stage skill.

NVIDIA/skills

Edit an existing workflow Scene or task contract. An agent skill from NVIDIA/skills.

NVIDIA/skills

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

NVIDIA/skills

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

NVIDIA/skills

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.

NVIDIA/skills

Continue KERMT pretraining on a custom SMILES corpus with a groverbase, cmim, or hybrid checkpoint.

NVIDIA/skills

Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint.

NVIDIA/skills

Finetune a pretrained KERMT encoder on a labeled CSV. An agent skill from NVIDIA/skills.

NVIDIA/skills

A skill your agent uses for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization.

NVIDIA/skills

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

NVIDIA/skills

A skill your agent uses when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.

NVIDIA/skills

A skill your agent uses when writing or debugging nvMolKit Python code for GPU-accelerated RDKit fingerprints, similarity, conformers, clustering, and molecular searches.

NVIDIA/skills

A skill your agent uses for OpenFold2, NVIDIA's BioNeMo NIM microservice for monomer protein structure prediction.

NVIDIA/skills

A skill your agent uses for OpenFold3, NVIDIA's BioNeMo NIM microservice for biomolecular structure prediction.

NVIDIA/skills

Run RFDiffusion protein backbone design via NVIDIA NIM. An agent skill from NVIDIA/skills.

NVIDIA/skills

Person re-identification (ReID). An agent skill from NVIDIA/skills.

NVIDIA/skills

A skill your agent uses when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka).

NVIDIA/skills

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.

NVIDIA/skills

Run the full DEFT smart-data-augmentation loop for NVIDIA TAO Grounding DINO object detection: zero-shot baseline inference, KPI analysis, per-class gap analysis, SigLIP embedding of weak images…

NVIDIA/skills

Port a published computer vision paper's official code and training recipe onto a customer's own dataset, or diagnose why such a transfer produced bad numbers.

NVIDIA/skills

Evaluate whether an existing hot path is a credible NVIDIA Warp candidate.

NVIDIA/skills

NOTE: molecule and target inputs and your NGCAPIKEY are transmitted to external NVIDIA-hosted API endpoints on every call.

NVIDIA/skills

Serve and visually inspect a converted LeRobot dataset in the browser.

NVIDIA/skills

Create a minimal blank Workflow scaffold with a Scene containing ground and light plus an idle run mode.

NVIDIA/skills

Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model.

NVIDIA/skills

Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection.

NVIDIA/skills

Expand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments.

NVIDIA/skills

Replay a workflow HDF5 episode through its original Scene. An agent skill from NVIDIA/skills.

NVIDIA/skills

Record demonstrations through a workflow's teleop Task into workflow HDF5.

NVIDIA/skills

Run the maintained workflow data-to-policy pipeline from recording through checkpoint validation.

NVIDIA/skills

Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data.

NVIDIA/skills

Preflight and set up the root-level workflow runtime. An agent skill from NVIDIA/skills.

NVIDIA/skills

A skill your agent uses when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.

NVIDIA/skills

Run the root-level workflow runtime policy or rule-based rollouts and verify simulator success.

NVIDIA/skills

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.

NVIDIA/skills

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

NVIDIA/skills

A skill your agent uses when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target.

NVIDIA/skills

Convert a groverbase checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latentdist, then continue pretraining on the user's…

NVIDIA/skills

Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV.

NVIDIA/skills

Pretrain a fresh KERMT model from scratch on a user-provided corpus.

NVIDIA/skills

Bootstrap 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…

NVIDIA/skills

NOTE: your protein sequence and the retrieved MSA alignment are transmitted to external NVIDIA-hosted APIs (health.api.nvidia.com) on every call.

NVIDIA/skills

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety.

NVIDIA/skills

A skill your agent uses when first-time NeMo Relay users want to try Relay, choose the least-complex supported quick start, or verify initial value through the CLI, a maintained integration, or…

NVIDIA/NeMo-Relay

Build DeepStream GStreamer pipelines interactively. An agent skill from NVIDIA/skills.

NVIDIA/skills

A skill your agent uses to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors…

NVIDIA/skills