deepstream-sop
deepstream-sop is an agent skill published by nvidia, listed under review & testing. It lives in the NVIDIA/skills repository, which has 3,735 GitHub stars and is licensed under Apache-2.0; we last read it on 2026-09-16.
This skill is used for building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice, a GPU-accelerated FastAPI service that detects assembly-line step sequences via event boundary detection and VLM classification. It processes factory/work-cell video for procedure compliance and integrates with various components including cameras and Kafka.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads NVIDIA/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add NVIDIA/skills
Maintenance
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
deepstream-sop compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| deepstream-sop (this page) | nvidia | Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP I… | 3,735 | 2026-10-26 |
| doca-aes-gcm(same repository) | nvidia | Use this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configu… | 3,735 | 2026-10-26 |
| doca-argp(same repository) | nvidia | Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / rem… | 3,735 | 2026-10-26 |
| doca-bare-metal-deployment(same repository) | nvidia | Running a DOCA-linked binary directly on the hardware, with no container or kubelet: on host x86 with a BlueF… | 3,735 | 2026-10-26 |
| doca-bench-extension(same repository) | nvidia | Use this skill when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in —… | 3,735 | 2026-10-26 |
| doca-caps(same repository) | nvidia | Use this skill when the user wants to invoke the read-only doca_caps CLI to ask what DOCA sees on this host —… | 3,735 | 2026-10-26 |
| doca-comch(same repository) | nvidia | Use this skill when the user is doing hands-on DOCA Comch work on a host + BlueField pair — bringing up host… | 3,735 | 2026-10-26 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about deepstream-sop
- What does deepstream-sop do?
- This skill is used for building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice, a GPU-accelerated FastAPI service that detects assembly-line step sequences via event boundary detection and VLM classification. It processes factory/work-cell video for procedure compliance and integrates with various components including cameras and Kafka.
- How do I install deepstream-sop?
- Run npx skills add NVIDIA/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes deepstream-sop?
- nvidia.
- Is deepstream-sop maintained, and what licence does it use?
- Its repository has 3,735 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-26. The repository declares the Apache-2.0 licence.
More agent skills for review & testing
- browser-testing-with-devtoolsby addyosmani
- code-review-and-qualityby addyosmani
- code-simplificationby addyosmani
- doubt-driven-developmentby addyosmani
- vitestby antfu
- webapp-testingby anthropic