GitHub organization
Agent skills by NVIDIA, page 8
Skills by NVIDIA, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 337 | A skill your agent uses when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. | NVIDIA/ | 3.5k | — | ~3.7k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 338 | A skill your agent uses to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. | NVIDIA/ | 3.5k | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 339 | A skill your agent uses to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). | NVIDIA/ | 3.5k | — | ~5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 340 | A skill your agent uses to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. | NVIDIA/ | 3.5k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 341 | A skill your agent uses to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). | NVIDIA/ | 3.5k | — | ~2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 342 | A skill your agent uses to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). | NVIDIA/ | 3.5k | — | ~2.3k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 343 | A skill your agent uses to diagnose and fix incorrect gradients in differentiable Warp programs. | NVIDIA/ | 3.5k | — | ~4.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 344 | A skill your agent uses when baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin behavior, including telemetry, state, adaptivehints… | NVIDIA/ | 192 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 345 | A skill your agent uses when choosing or configuring NeMo Relay 0.6 or 0.7 observability through the built-in plugin, subscribers, or exporters, including raw ATOF events, ATIF trajectories… | NVIDIA/ | 192 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 346 | Perform a NeMo Relay project release-version change across project-owned manifests, dependencies, lockfiles, and generated attribution surfaces while keeping just set-version coverage complete. | NVIDIA/ | 192 | — | ~776 | Automated safety check: Pass | Apache-2.0 | today |
| 347 | cuOpt REST server — start server, endpoints, Python/curl client examples. | NVIDIA/ | 3.5k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 348 | Prepare and run PAIDF Cosmos Predict video generation for DEFT media samples. | NVIDIA/ | 3.5k | — | ~4.6k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 349 | A skill your agent uses when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. | NVIDIA/ | 3.5k | — | ~4.7k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 350 | Create and push a signed, annotated NeMo Relay beta tag from its release branch or validated main. | NVIDIA/ | 192 | — | ~728 | Automated safety check: Pass | Apache-2.0 | today |
| 351 | Create and push a signed, annotated NeMo Relay release-candidate tag from its validated release branch. | NVIDIA/ | 192 | — | ~635 | Automated safety check: Pass | Apache-2.0 | today |
| 352 | Create and push a signed, annotated NeMo Relay stable tag, then prepare an unpublished GitHub Release draft for review. | NVIDIA/ | 192 | — | ~827 | Automated safety check: Pass | Apache-2.0 | today |
| 353 | Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. | NVIDIA/ | 3.5k | — | ~3.9k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 354 | LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.5k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 355 | Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. | NVIDIA/ | 3.5k | — | ~821 | Automated safety check: Notes | Apache-2.0 | yesterday |
| 356 | Used for header-only preflight of one DICOM series folder before conversion or inference. | NVIDIA/ | 3.5k | — | ~864 | Automated safety check: Notes | Apache-2.0 | yesterday |
| 357 | Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. | NVIDIA/ | 3.5k | — | ~926 | Automated safety check: Notes | Apache-2.0 | yesterday |
| 358 | A skill your agent uses when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring docaaesgcmtaskencrypt / taskdecrypt, querying docaaesgcmcap for… | NVIDIA/ | 3.5k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 359 | A skill your agent uses for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart →… | NVIDIA/ | 3.5k | — | ~3.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 360 | A skill your agent uses when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side runtime-security container that watches the BlueField and attached host for… | NVIDIA/ | 3.5k | — | ~4.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 361 | Run docabench (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… | NVIDIA/ | 3.5k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 362 | A skill your agent uses when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in — a versioned shared library with DOCAEXPERIMENTAL-marked C entry points that… | NVIDIA/ | 3.5k | — | ~4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 363 | A skill your agent uses when the user wants to invoke the read-only docacaps CLI to ask what DOCA sees on this host — listing DOCA devices and PCIe addresses, listing representor devices, asking… | NVIDIA/ | 3.5k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 364 | A skill your agent uses when the user is doing hands-on DOCA Comch work on a host + BlueField pair — bringing up host ↔ DPU PCIe control-plane messaging, picking server (DPU) vs client (host) roles… | NVIDIA/ | 3.5k | — | ~3.1k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 365 | A skill your agent uses to enumerate host↔DPU DOCA comch (formerly Comm Channel) servers and connections via the shipped docacommchanneladmin binary — listing comch-capable devices and decoding the… | NVIDIA/ | 3.5k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 366 | A skill your agent uses 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 — walking the… | NVIDIA/ | 3.5k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 367 | A skill your agent uses for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling compress-deflate, decompress-deflate, decompress-lz4-stream, or… | NVIDIA/ | 3.5k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 368 | A skill your agent uses when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca symbol, a runtime call returning DOCAERROR, a silent service… | NVIDIA/ | 3.5k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 369 | A skill your agent uses when the user is doing hands-on DOCA DMA programming — bringing up a docadma context, configuring the single docadmataskmemcpy task type, sizing buffers via the… | NVIDIA/ | 3.5k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 370 | Operate NVIDIA DOCA Management Service (dmsd + dmspe) on a BlueField, Arm/x86 host, or Kubernetes pod: choose deployment and authentication, configure -allowedusers and dmsgroup, use gNMI… | NVIDIA/ | 3.5k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 371 | A skill your agent uses when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the docadpa Core context, loading a DPACC-compiled DPA app image (docadpaapp), creating DPA… | NVIDIA/ | 3.5k | — | ~5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 372 | A skill your agent uses when the user runs docadpahltracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR… | NVIDIA/ | 3.5k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 373 | A skill your agent uses when the user has an existing DPDK application and is adding DOCA capabilities in-place — most commonly DOCA Flow hardware steering — without rewriting the data-plane in… | NVIDIA/ | 3.5k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 374 | A skill your agent uses when the user is doing hands-on DOCA Erasure Coding programming on a BlueField DPU, ConnectX NIC, or host — bringing up a docaec context, picking among the create / recover /… | NVIDIA/ | 3.5k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 375 | A skill your agent uses for hands-on DOCA Ethernet packet-queue work on a BlueField DPU or ConnectX NIC — bringing up a docaethrxq or docaethtxq on a port / representor / SF, picking among the four… | NVIDIA/ | 3.5k | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 376 | A skill your agent uses when the user is operating the DOCA Firefly Service container on BlueField — picking the four PTP configuration axes (role / profile / domain / interface), wiring the… | NVIDIA/ | 3.5k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 377 | Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware… | NVIDIA/ | 3.5k | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 378 | A skill your agent uses when the user is invoking docaflowdpaperf on DPA-capable hardware (ConnectX-7 minimum supported, ConnectX-8 recommended, or BlueField-3) to measure rule update / disable… | NVIDIA/ | 3.5k | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 379 | A skill your agent uses when the user is doing hands-on DOCA Flow DPA Provider work — exporting a doca-flow pipe or external resource (index-selector/memory) into BlueField DPA address space so a… | NVIDIA/ | 3.5k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 380 | PLAINTEXT-ONLY: the shipped docaflowgrpc server uses grpc::InsecureServerCredentials() with NO TLS / mTLS / token-auth knob on the binary — transport security must come from external infrastructure… | NVIDIA/ | 3.5k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 381 | A skill your agent uses when the user is measuring the host or DPU-CPU control-plane rate of a DOCA Flow pipeline with docaflowperf — picking a JSON policy from configs/, choosing the DPDK or DOCA… | NVIDIA/ | 3.5k | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 382 | A skill your agent uses for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. | NVIDIA/ | 3.5k | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 383 | A skill your agent uses when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via docagpuethrxq / docagpuethtxq, standing up the… | NVIDIA/ | 3.5k | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 384 | A skill your agent uses when the user is building, running, or interpreting the doca/tools/gpunetioibwritebw client+server benchmark — a CUDA kernel on the client posts RDMA WRITE work requests… | NVIDIA/ | 3.5k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
