
NVIDIA
Showing 61β120 of 201 skills Β· Page 2 of 4
NVIDIA / rfd4-proteina-nim
3.4kRun RFD4-Proteina NIM for joint protein structure and sequence design, conditioned generation, and reward-guided search using the NVIDIA hosted API or a self-hosted NIM. Not for the older RFdiffusion contigs API.
NVIDIA / cdf-event-video-generation
3.4kRun the CDF Orchestration Event Video Generation DAG on Kubernetes or OSMO - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation.
NVIDIA / cdf-orchestration-preflight
3.4kSet up missing Linux prerequisites and audit whether a Cosmos Data Factory (CDF) Orchestration checkout and its Kubernetes or OSMO environment are ready to install the controller and run every packaged DAG.
NVIDIA / compute-sanitizer-diagnose-cuda-bugs
3.4kDetect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the repβ¦
NVIDIA / deepstream-profile-pipeline
3.4kProfile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement
NVIDIA / digital-health-clinical-asr-eval
3.4kStage 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).
NVIDIA / earth2studio-create-datasource
3.4kCreate and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.
NVIDIA / earth2studio-data-fetch
3.4kFetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.
NVIDIA / earth2studio-discover
3.4kFind Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.
NVIDIA / earth2studio-install
3.4kGuide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models, or PhysicsNeMo questions.
NVIDIA / ethos-explore
3.4kCaptures what an AI agent is supposed to do β its purpose, boundaries, and success criteria β as a durable snapshot for anyone building, evaluating, reviewing, or changing it. Explores the user's codebase and docs first, then asks one intent question at a time for what source cannot supply.
NVIDIA / ethos-orchestrate
3.4kEntry point for an AI agent's ETHOS.md: a durable snapshot of what the agent is for, what it must not do, and what success looks like. Routes a request to explore and capture intent (ethos-explore), or write or edit the file (ethos-write). Owns the standard every ethos sub-flow follows
NVIDIA / ethos-write
3.4kWrites an AI agent's ethos.md β a durable snapshot of its purpose, intended behavior, boundaries, and success criteria β from the answers gathered by ethos-explore.
NVIDIA / holoscan-setup
3.4kAssess a host and choose a Holoscan SDK 5.x installation method using release availability, CUDA 13 compatibility, and component needs.
NVIDIA / isaac-humanoid-cloud-control
3.4kRun streamed Unitree G1 cloud-navigation demos in Isaac Sim with guarded gantry release. Use for demo, destination, Mission Control, or cleanup requests.
NVIDIA / jetson-customize-clocks
3.4kUse 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 tuning or nvpmodel edits.
NVIDIA / boltz2-nim
3.4kUse Boltz2 NIM for biomolecular structure prediction and binding affinity. Invoke for Boltz2, protein structures, protein-ligand/DNA/RNA complexes, SMILES or CCD ligands, pIC50/IC50 affinity scoring, mmCIF output, hosted NVIDIA API calls, or local Docker deployment.
NVIDIA / drug-discovery-pipeline
3.4kScreen drug candidates end-to-end using three BioNeMo NIMs in sequence:
NVIDIA / cuopt-install
3.4kInstall cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.
NVIDIA / dynamo-router-starter
3.4kStart 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.
NVIDIA / i4h-workflow-dataset-annotate
3.4kGrade or filter workflow HDF5 episodes with an OpenAI-compatible vision model. Use for visual success labels; do not use for replay, policy evaluation, or recordings without frames.
NVIDIA / i4h-workflow-finetune
3.4kFine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or checkpoint rollout.
NVIDIA / i4h-workflow-setup
3.4kPreflight and set up the root-level workflow runtime. Use for installation, missing component environments, or third-party failures; do not use for rollout validation.
NVIDIA / skill-inspector
23.8kReview AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review
NVIDIA / SkillSpector
26.4kSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
NVIDIA / kermt-embed
3.4kExtract 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.
NVIDIA / kermt-infer
3.4kRun 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 keβ¦
NVIDIA / kermt-monitor
3.4kCheck 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 / kermt-setup
3.4kBootstrap the KERMT agent environment β 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 / openfold2-nim
3.4kUse this skill for OpenFold2, NVIDIA's BioNeMo NIM microservice for monomer protein structure prediction. Invoke whenever the user mentions OpenFold2, AlphaFold2-like monomer folding, protein sequence-to-structure prediction, A3M MSAs, mmCIF templates, hosted NVIDIA API calls, or local Docker deployβ¦
NVIDIA / cdf-auto-labeling
3.4kUse when a user needs to get started with CDF Auto-Labeling, plan a scenario, run or debug a shipped cookbook, author prompts or cookbooks, migrate a pipeline, configure a stage, or pull the prebuilt stage containers from NGC (nvcr.io).
NVIDIA / deepstream-sop
3.4kUse this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice β a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification.
NVIDIA / hsb-ip-create-top
3.4kCreate or explain fixed-format HSB FPGA_top.sv wrappers from validated HOLOLINK_def.svh files. Do not use for def generation or validation.
NVIDIA / rfdiffusion-nim
3.4kRun RFDiffusion protein backbone design via NVIDIA NIM. Use for de novo protein backbones, motif scaffolding, binder design, hotspot residues, contigs syntax, diffusion steps, hosted NVIDIA API calls, local Docker deployment, and PDB backbone outputs for ProteinMPNN sequence design.
NVIDIA / cuopt-server-api-python
3.4kcuOpt REST server β start server, endpoints, Python/curl client examples
NVIDIA / deepstream-dev
3.4kNVIDIA DeepStream SDK development with Python pyservicemaker API
NVIDIA / deepstream-run-mv3dt
3.4kRun and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT
NVIDIA / i4h-lerobot-viz
3.4kServe and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5 or incomplete conversion output.
NVIDIA / i4h-workflow
3.4kOrient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not execute a known stage.
NVIDIA / i4h-workflow-dataset-convert
3.4kConvert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use for replay, augmentation, or raw-data repair.
NVIDIA / i4h-workflow-dataset-mimic
3.4kExpand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments. Use for synthetic variants; do not use to collect data, alter state directly, or generate new images.
NVIDIA / i4h-workflow-dataset-replay
3.4kReplay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or LeRobot data.
NVIDIA / i4h-workflow-dataset-teleop
3.4kRecord demonstrations through a workflow's teleop Task into workflow HDF5. Use for keyboard, leader, VR, or bus input; do not use for policy evaluation or autonomous rule-based Tasks.
NVIDIA / i4h-workflow-e2e
3.4kRun the maintained workflow data-to-policy pipeline from recording through checkpoint validation. Use for full end-to-end requests; do not use for one individual stage.
NVIDIA / cdf-image-attribute-augmentation
3.4kRun the CDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented dataset generation.
NVIDIA / cuopt-routing-api-python
3.4kVehicle routing (VRP, TSP, PDP) with cuOpt β Python API only
NVIDIA / deepstream-generate-pipeline
3.4kBuild DeepStream GStreamer pipelines interactively
NVIDIA / digital-health-clinical-asr-build
3.4kStage 2 of the Clinical ASR Flywheel
NVIDIA / digital-health-clinical-asr-finetune
3.4kStage 4 of the Clinical ASR Flywheel
NVIDIA / doca-aes-gcm
3.4kUse this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC β configuring `doca_aes_gcm_task_encrypt` / `_task_decrypt`, querying `doca_aes_gcm_cap_*` for per-key-type (only `DOCA_AES_GCM_KEY_128` / `_256` β AES-192 not supported) and per-task support, sizingβ¦
NVIDIA / doca-argp
3.4kUse this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app β adding / removing / renaming flags; wiring `doca_argp_init` β register params β `doca_argp_start` β `doca_argp_destroy` in order; picking a parameter type from the full public enum (`DOCA_ARGP_TYPE_STRINβ¦
NVIDIA / doca-argus
3.4kUse this skill when the user is deploying or operating the DOCA Argus Service β the packaged BlueField-side runtime-security container that watches the BlueField and attached host for suspicious activity, integrity violations, and operational anomalies, and forwards findings to a SIEM (Splunk / ELKβ¦
NVIDIA / doca-bench
3.4kRun `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for RDMA, Compress, AES-GCM, SHA, DMA, EC, Ethernet, Comch, or GPUNetIO on a host or BlueField Arm.
NVIDIA / doca-bf4-deployment
3.4kBlueField-3 or any other generation is not this skill. Name `doca-bf3-deployment` and stop; do not read further or run commands.
NVIDIA / doca-comch
3.4kUse this skill when the user is doing hands-on DOCA Comch work on a host + BlueField pair β bringing up host β DPU PCIe control-plane messaging, picking server (DPU) vs client (host) roles, choosing slow-path send-task / recv-callback vs fast-path producer / consumer, querying max-msg-size or max-clβ¦
NVIDIA / doca-comm-channel-admin
3.4kUse this skill to enumerate hostβDPU DOCA comch (formerly Comm Channel) servers and connections via the shipped doca_comm_channel_admin binary β listing comch-capable devices and decoding the per-device server / connection table (server name, PID, in-use / max, PCIe address).
NVIDIA / doca-common
3.4kUse this skill whenever the user is doing hands-on DOCA programming on a BlueField DPU or ConnectX NIC and needs the foundation primitives every per-library context rests on β walking the doca_ctx lifecycle, discovering doca_dev / doca_devinfo and gating on doca_*_cap_* before trusting a feature, wiβ¦
NVIDIA / doca-compress
3.4kHardware compression offload with DOCA Compress on a BlueField DPU, ConnectX NIC, or host: DEFLATE compress and decompress, plus LZ4 decompress (stream and block; LZ4 encode is NOT supported), instead of CPU zlib / zstd.
NVIDIA / doca-dma
3.4kUse this skill when the user is doing hands-on DOCA DMA programming β bringing up a doca_dma context, configuring the single doca_dma_task_memcpy task type, sizing buffers via the doca_dma_cap_task_memcpy_* queries, setting LOCAL_READ_ONLY / LOCAL_READ_WRITE permissions on source / destination doca_β¦
NVIDIA / doca-dpa
3.4kUse this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField β creating the `doca_dpa` Core context, loading a DPACC-compiled DPA app image (`doca_dpa_app`), creating DPA threads, launching kernels via `doca_dpa_kernel_launch_update_*`, draining `doca_dpa_completion`, runninβ¦