Search
NVIDIA AI Platform · NVIDIA/skills
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 49 | Scaffold a standalone RTVI CV microservice that plugs into VSS Search and Alerts profiles via Kafka mdx-raw. | NVIDIA/ | 3.6k | — | ~4.5k | Automated safety check: Pass | Proprietary | 2 days ago |
| 50 | Use only to generate or update a governance skill card for a specified existing agent skill directory. | NVIDIA/ | 3.6k | — | ~1.6k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 51 | Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. | NVIDIA/ | 3.6k | — | ~5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 52 | Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly requested: evaluate the base model on Proxy and… | NVIDIA/ | 3.6k | — | ~5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 53 | Run iterative improvement for NVIDIA TAO CLIP / SigLIP image-text retrieval on attribute-labelled data. | NVIDIA/ | 3.6k | — | ~4.2k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 54 | Host setup for TAO GPU backends. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~3.4k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 55 | Optical Inspection for defect detection using Siamese networks. | NVIDIA/ | 3.6k | — | ~4.4k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 56 | A skill your agent uses for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. | NVIDIA/ | 3.6k | — | ~4.5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 57 | Use Boltz2 NIM for biomolecular structure prediction and binding affinity. | NVIDIA/ | 3.6k | 1 repo | ~1.4k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 58 | A skill your agent uses when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker capacity with authenticated samples and… | NVIDIA/ | 3.6k | 1 repo | ~1.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 59 | A skill your agent uses when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled from live APIs, authenticated NVIDIA samples, and NVIDIA… | NVIDIA/ | 3.6k | 1 repo | ~2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 60 | A skill your agent uses when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise… | NVIDIA/ | 3.6k | 1 repo | ~2.2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 61 | A skill your agent uses when turning a Jetson encoder use case into one surface-neutral recipe with native Video Codec SDK and PyNvVideoCodec projections. | NVIDIA/ | 3.6k | 1 repo | ~1.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 62 | A skill your agent uses when installing, repairing, reusing, inspecting, or verifying readiness of the native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson, including the one-frame… | NVIDIA/ | 3.6k | 1 repo | ~2.4k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 63 | DALI imperative dynamic mode (nvidia.dali.experimental.dynamic, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks. | NVIDIA/ | 3.6k | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 64 | A skill your agent uses when controlling NVIDIA Broadcast through MCP to apply effects, process local media, select devices, or change camera resolution, or when Broadcast is missing or too old to… | NVIDIA/ | 3.6k | — | ~10k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 65 | Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory. | NVIDIA/ | 3.6k | 1 repo | ~1.9k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 66 | 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/ | 3.6k | 1 repo | ~3k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 67 | Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck. | NVIDIA/ | 3.6k | 1 repo | ~1.2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 68 | Model and publish semantic definitions in Auto Ontology. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 69 | Query Auto Ontology and validate generated SQL, rows, and answers. | NVIDIA/ | 3.6k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 70 | Set up or troubleshoot the Auto Ontology runtime. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~2.7k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 71 | Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend. | NVIDIA/ | 3.6k | — | ~3.6k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 72 | A skill your agent uses for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance. | NVIDIA/ | 3.6k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 73 | Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). | NVIDIA/ | 3.6k | — | ~3.2k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 74 | NVIDIA DeepStream SDK development with Python pyservicemaker API. | NVIDIA/ | 3.6k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 75 | Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. | NVIDIA/ | 3.6k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 76 | A skill your agent uses when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether… | NVIDIA/ | 3.6k | — | ~4.7k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 77 | Stage 2 of the Clinical ASR Flywheel. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 78 | Stage 1 of Clinical ASR Flywheel. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~4.5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 79 | A skill your agent uses to deploy and operate a CollectX (clx) based DOCA telemetry collector on a host or BlueField — wiring providers / counters into the collector, running the collection daemon… | NVIDIA/ | 3.6k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 80 | A skill your agent uses when the user is hands-on deploying an in-bundle DOCA service container (Argus, DMS, Firefly, or UROM service) on a BlueField — kubelet standalone watching a static-pod… | NVIDIA/ | 3.6k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 81 | A skill your agent uses when the user needs to locate authoritative information about NVIDIA DOCA without access to the source tree — finding the right docs.nvidia.com page for a… | NVIDIA/ | 3.6k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 82 | Install or repair the FoundationPose perception pipeline and build its FoundationStereo TensorRT engines. | NVIDIA/ | 3.6k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 83 | A skill your agent uses for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking. | NVIDIA/ | 3.6k | — | ~1.8k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 84 | A skill your agent uses when a concrete ./holohub command fails, hangs, regresses, or returns wrong output and needs reproducible diagnosis and verification. | NVIDIA/ | 3.6k | — | ~1.7k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 85 | A skill your agent uses for reusable Holoscan Module work with ./holohub: scaffold, tests, editable install, DEB/WHEEL packaging, and clean-consumer proof. | NVIDIA/ | 3.6k | — | ~1.7k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 86 | Flash the FPGA on an HSB board connected to an NVIDIA devkit. | NVIDIA/ | 3.6k | — | ~4.4k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 87 | Choose or explain HSB Sensor RX packetizer fields for HOLOLINKdef.svh. | NVIDIA/ | 3.6k | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 88 | A skill your agent uses when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bspsources/. | NVIDIA/ | 3.6k | — | ~5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 89 | A skill your agent uses 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. | NVIDIA/ | 3.6k | — | ~4.8k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 90 | A skill your agent uses to flash a promoted BSP image to a Jetson DUT in RCM mode via flash.sh or l4tinitrdflash.sh. | NVIDIA/ | 3.6k | — | ~4.9k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 91 | A skill your agent uses to promote overlay files and built artifacts into the staged BSP image. | NVIDIA/ | 3.6k | — | ~5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 92 | Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. | NVIDIA/ | 3.6k | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 93 | Routes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted. | NVIDIA/ | 3.6k | — | ~3k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 94 | Used for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr. | NVIDIA/ | 3.6k | — | ~2k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 95 | A skill your agent uses for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. | NVIDIA/ | 3.6k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 96 | A skill your agent uses when operating PAIDF Curation and Retrieval or NVIDIA Cosmos Curator pipelines (split, filter, caption, embed, dedup, shard, image annotate) or PAIDF Data Mining… | NVIDIA/ | 3.6k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
