SkillAgentSearch skills...
Home

NVIDIA

201 skills across 201 repos731.0k repo starsGitHub

Showing 61–120 of 201 skills Β· Page 2 of 4

NVIDIA / rfd4-proteina-nim

3.4k

Run 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.

πŸ“„ SKILL.mduniversal
skillapidesign+1
92
Updated 1mo ago

NVIDIA / cdf-event-video-generation

3.4k

Run the CDF Orchestration Event Video Generation DAG on Kubernetes or OSMO - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation.

πŸ“„ SKILL.mduniversal
skillapiimage+1
92
Updated 1mo ago

NVIDIA / cdf-orchestration-preflight

3.4k

Set 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.

πŸ“„ SKILL.mduniversal
skillkubernetes
92
Updated 1mo ago

NVIDIA / compute-sanitizer-diagnose-cuda-bugs

3.4k

Detect 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 rep…

πŸ“„ SKILL.mdzed
skill
92
Updated 1mo ago

NVIDIA / deepstream-profile-pipeline

3.4k

Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement

πŸ“„ SKILL.mduniversal
skillreviewpython
92
Updated 1mo ago

NVIDIA / digital-health-clinical-asr-eval

3.4k

Stage 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).

πŸ“„ SKILL.mduniversal
skillgitapi
92
Updated 1mo ago

NVIDIA / earth2studio-create-datasource

3.4k

Create 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.

πŸ“„ SKILL.mduniversal
skillpython
92
Updated 1mo ago

NVIDIA / earth2studio-data-fetch

3.4k

Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.

πŸ“„ SKILL.mduniversal
skillapipython
92
Updated 1mo ago

NVIDIA / earth2studio-discover

3.4k

Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.

πŸ“„ SKILL.mduniversal
skillpython
92
Updated 1mo ago

NVIDIA / earth2studio-install

3.4k

Guide 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.

πŸ“„ SKILL.mduniversal
skillpython
92
Updated 1mo ago

NVIDIA / ethos-explore

3.4k

Captures 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.

πŸ“„ SKILL.mduniversal
skilldesignreview
92
Updated 1mo ago

NVIDIA / ethos-orchestrate

3.4k

Entry 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

πŸ“„ SKILL.mduniversal
skill
92
Updated 1mo ago

NVIDIA / ethos-write

3.4k

Writes 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.

πŸ“„ SKILL.mduniversal
skilldesignreview
92
Updated 1mo ago

NVIDIA / holoscan-setup

3.4k

Assess a host and choose a Holoscan SDK 5.x installation method using release availability, CUDA 13 compatibility, and component needs.

πŸ“„ SKILL.mduniversal
skilldevelopmentgit+2
92
Updated 1mo ago

NVIDIA / isaac-humanoid-cloud-control

3.4k

Run streamed Unitree G1 cloud-navigation demos in Isaac Sim with guarded gantry release. Use for demo, destination, Mission Control, or cleanup requests.

πŸ“„ SKILL.mduniversal
skill
92
Updated 1mo ago

NVIDIA / jetson-customize-clocks

3.4k

Use 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.

πŸ“„ SKILL.mduniversal
skill
92
Updated 1mo ago

NVIDIA / boltz2-nim

3.4k

Use 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.

πŸ“„ SKILL.mduniversal
skillapidocker
91
Updated 1mo ago

NVIDIA / drug-discovery-pipeline

3.4k

Screen drug candidates end-to-end using three BioNeMo NIMs in sequence:

πŸ“„ SKILL.mduniversal
skillapi
91
Updated 1mo ago

NVIDIA / cuopt-install

3.4k

Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.

πŸ“„ SKILL.mduniversal
skilldockerpython+1
91
Updated 1mo ago

NVIDIA / dynamo-router-starter

3.4k

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.

πŸ“„ SKILL.mduniversal
skill
91
Updated 1mo ago

NVIDIA / i4h-workflow-dataset-annotate

3.4k

Grade 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.

πŸ“„ SKILL.mduniversal
skill
91
Updated 1mo ago

NVIDIA / i4h-workflow-finetune

3.4k

Fine-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.

πŸ“„ SKILL.mduniversal
skill
91
Updated 1mo ago

NVIDIA / i4h-workflow-setup

3.4k

Preflight and set up the root-level workflow runtime. Use for installation, missing component environments, or third-party failures; do not use for rollout validation.

πŸ“„ SKILL.mduniversal
skill
91
Updated 1mo ago

NVIDIA / skill-inspector

23.8k

Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review

πŸ“„ SKILL.mduniversal
skillreviewrust
91
Updated 16d ago

NVIDIA / SkillSpector

26.4k

Security 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.

πŸ€– CLAUDE.mdclaude codecodex
claudemcpsecurity
90
Updated 7h ago

NVIDIA / kermt-embed

3.4k

Extract 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.

πŸ“„ SKILL.mdclaude codezed+1
skilldockerdesign
90
Updated 1mo ago

NVIDIA / kermt-infer

3.4k

Run 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 ke…

πŸ“„ SKILL.mdclaude codecodex
skilldockerdesign
90
Updated 1mo ago

NVIDIA / kermt-monitor

3.4k

Check 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).

πŸ“„ SKILL.mdclaude codecodex
skilldockerdesign
90
Updated 1mo ago

NVIDIA / kermt-setup

3.4k

Bootstrap 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.

πŸ“„ SKILL.mdclaude codecodex
skilldockerdesign+1
90
Updated 1mo ago

NVIDIA / openfold2-nim

3.4k

Use 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 deploy…

πŸ“„ SKILL.mduniversal
skillapidocker
90
Updated 1mo ago

NVIDIA / cdf-auto-labeling

3.4k

Use 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).

πŸ“„ SKILL.mduniversal
skillreview
90
Updated 1mo ago

NVIDIA / deepstream-sop

3.4k

Use 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.

πŸ“„ SKILL.mduniversal
skillapi
90
Updated 1mo ago

NVIDIA / hsb-ip-create-top

3.4k

Create or explain fixed-format HSB FPGA_top.sv wrappers from validated HOLOLINK_def.svh files. Do not use for def generation or validation.

πŸ“„ SKILL.mduniversal
skilldesign
90
Updated 1mo ago

NVIDIA / rfdiffusion-nim

3.4k

Run 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.

πŸ“„ SKILL.mduniversal
skillapidocker+1
89
Updated 1mo ago

NVIDIA / cuopt-server-api-python

3.4k

cuOpt REST server β€” start server, endpoints, Python/curl client examples

πŸ“„ SKILL.mduniversal
skillapipython+1
89
Updated 1mo ago

NVIDIA / deepstream-dev

3.4k

NVIDIA DeepStream SDK development with Python pyservicemaker API

πŸ“„ SKILL.mduniversal
skilldevelopmentapi+2
89
Updated 1mo ago

NVIDIA / deepstream-run-mv3dt

3.4k

Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT

πŸ“„ SKILL.mdzed
skill
89
Updated 1mo ago

NVIDIA / i4h-lerobot-viz

3.4k

Serve 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.

πŸ“„ SKILL.mduniversal
skill
89
Updated 1mo ago

NVIDIA / i4h-workflow

3.4k

Orient 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.

πŸ“„ SKILL.mduniversal
skill
89
Updated 1mo ago

NVIDIA / i4h-workflow-dataset-convert

3.4k

Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use for replay, augmentation, or raw-data repair.

πŸ“„ SKILL.mduniversal
skill
89
Updated 1mo ago

NVIDIA / i4h-workflow-dataset-mimic

3.4k

Expand 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.

πŸ“„ SKILL.mduniversal
skillimage
89
Updated 1mo ago

NVIDIA / i4h-workflow-dataset-replay

3.4k

Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or LeRobot data.

πŸ“„ SKILL.mduniversal
skill
89
Updated 1mo ago

NVIDIA / i4h-workflow-dataset-teleop

3.4k

Record 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.

πŸ“„ SKILL.mduniversal
skill
89
Updated 1mo ago

NVIDIA / i4h-workflow-e2e

3.4k

Run 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.

πŸ“„ SKILL.mduniversal
skill
89
Updated 1mo ago

NVIDIA / cdf-image-attribute-augmentation

3.4k

Run the CDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented dataset generation.

πŸ“„ SKILL.mduniversal
skillimagekubernetes
88
Updated 1mo ago

NVIDIA / cuopt-routing-api-python

3.4k

Vehicle routing (VRP, TSP, PDP) with cuOpt β€” Python API only

πŸ“„ SKILL.mduniversal
skillapipython
88
Updated 1mo ago

NVIDIA / deepstream-generate-pipeline

3.4k

Build DeepStream GStreamer pipelines interactively

πŸ“„ SKILL.mduniversal
skillimage
88
Updated 1mo ago

NVIDIA / digital-health-clinical-asr-build

3.4k

Stage 2 of the Clinical ASR Flywheel

πŸ“„ SKILL.mduniversal
skillgitapi
88
Updated 1mo ago

NVIDIA / digital-health-clinical-asr-finetune

3.4k

Stage 4 of the Clinical ASR Flywheel

πŸ“„ SKILL.mduniversal
skillgit
88
Updated 1mo ago

NVIDIA / doca-aes-gcm

3.4k

Use 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, sizing…

πŸ“„ SKILL.mduniversal
skillsecurity
88
Updated 1mo ago

NVIDIA / doca-argp

3.4k

Use 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_STRIN…

πŸ“„ SKILL.mduniversal
skill
88
Updated 1mo ago

NVIDIA / doca-argus

3.4k

Use 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 / ELK…

πŸ“„ SKILL.mduniversal
skillsecurity
88
Updated 1mo ago

NVIDIA / doca-bench

3.4k

Run `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.

πŸ“„ SKILL.mduniversal
skill
88
Updated 1mo ago

NVIDIA / doca-bf4-deployment

3.4k

BlueField-3 or any other generation is not this skill. Name `doca-bf3-deployment` and stop; do not read further or run commands.

πŸ“„ SKILL.mduniversal
skill
88
Updated 1mo ago

NVIDIA / doca-comch

3.4k

Use this skill when the user is doing hands-on DOCA Comch work on a host + BlueField pair β€” bringing up host ↔ 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-cl…

πŸ“„ SKILL.mduniversal
skillapi
88
Updated 1mo ago

NVIDIA / doca-comm-channel-admin

3.4k

Use this skill to enumerate host↔DPU 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).

πŸ“„ SKILL.mduniversal
skillrest
88
Updated 1mo ago

NVIDIA / doca-common

3.4k

Use 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, wi…

πŸ“„ SKILL.mddevin
skillrustrest
88
Updated 1mo ago

NVIDIA / doca-compress

3.4k

Hardware 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.

πŸ“„ SKILL.mduniversal
skill
88
Updated 1mo ago

NVIDIA / doca-dma

3.4k

Use 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_…

πŸ“„ SKILL.mduniversal
skillmcp
88
Updated 1mo ago

NVIDIA / doca-dpa

3.4k

Use 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`, runnin…

πŸ“„ SKILL.mduniversal
skillimage
88
Updated 1mo ago
NVIDIA β€” Creator Profile β€” Page 2 | SkillAgent