Dev & Engineering ✓ NVIDIA · Official deepstreamsop-compliancevideo-analyticstritonfastapivllmbasler-camera

DeepStream SOP Compliance Inference

Build and operate a GPU-accelerated service that checks industrial work-step order and SOP compliance in video.

FollowSkills review · FSRS-2.0
Not recommended
51/ 100 5-point scale 2.6 / 5
Trust14 / 25 · 2.8/5

The documentation discloses flows involving files, RTSP, Basler cameras, VLM inference, Kafka, SSE, and optional RTSP output, and mentions an unprivileged default plus disconnect cleanup and required configuration. It does not systematically require user confirmation, sensitive-video handling, credential protection, rollback, or external-effect controls; Compose also exposes NGC_API_KEY, host networking, GPU access, an audio device, and SYS_PTRACE. Points are deducted for these gaps.

Reliability8 / 20 · 2.0/5

SKILL.md gives many key-path rules, fail-fast requirements, and cleanup instructions, while BENCHMARK.md claims test results. However, this is a static review with no committed, verifiable CI/test implementation covering the critical paths; the stack depends on GPU, DeepStream, Triton, vLLM, Pylon, and external models, and abnormal-input diagnostics are incomplete. The score therefore stays below the static ceiling.

Adaptability10 / 15 · 3.3/5

The trigger scope, intended scenarios, and non-trigger cases for generic DeepStream, object detection, and video summarization are explicit, and input types are well described. Boundaries for Chinese-language interaction, non-GPU environments, model availability, and camera availability are not stated; core dependencies also rely on overseas model repositories, Basler downloads, and NVIDIA runtime components, with no mainland-China reachability assessment.

Convention9 / 15 · 3.0/5

The skill has strong sectioning, an index, file mapping, environment-variable references, deployment, verification, and latency material, plus an owner, version, review date, and license declaration. It lacks a formal changelog, explicit maintenance/update process, fuller FAQs, and complete dependency-version governance; BENCHMARK.md records missing recommended Instructions and Examples sections, and repository license metadata is NOASSERTION.

Effectiveness6 / 15 · 2.0/5

The goal is clear and the workflow covers generation, evaluation, API use, camera requests, and latency measurement, with directly shaped examples. The source was not executed, so generated code, deployment, and inference results were not independently confirmed; GPU, commercial Pylon, and model requirements also impose substantial cost. The score is therefore conservative under static calibration.

Verifiability4 / 10 · 2.0/5

The material provides an upstream repository reference, a DDM paper citation, detailed rules, evaluation tasks, and an internal benchmark report, giving some auditability. It lacks independently reproducible committed tests, CI evidence, and item-level third-party corroboration, so the benchmark conclusions cannot be fully verified from the supplied files alone.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 55f18499943e
Before you use it
  • Deployment may send video or event data to external model repositories, the Basler CDN, Kafka, or RTSP; review data flows, credentials, network exposure, and authorization before production use.
  • GPU, DeepStream/Triton, vLLM, model weights, and potentially commercial Pylon SDK components are required; mainland-China and no-GPU usability is unproven.
  • The pass rates in BENCHMARK.md are author-supplied source material and do not replace local execution, CI, or end-to-end acceptance testing.
See the full review method →

What does this skill do, and when should you use it?

This skill targets NVIDIA's DeepStream SOP Inference Microservice, a GPU-accelerated FastAPI service for analyzing industrial video with event boundary detection and a vision-language model. It guides agents through file, RTSP, and Basler camera inputs and identifies missing or out-of-order operating steps. The pipeline segments video with a GEBD model through Triton, classifies chunks with a vLLM-served VLM, and emits results through SSE, Kafka, and Prometheus. It fits implementation, deployment, evaluation, debugging, and chunk-latency work for this specific SOP service.

Guides configuration and operation of the FastAPI /v1/chat/completions, /v1/metrics, and /v1/metadata endpoints; builds a four-stage pipeline for DeepStream processing, Triton GEBD inference, clip segmentation, Cosmos Reason VLM classification, and SOP sequence checking; handles file, RTSP, and Basler/Pylon camera inputs; streams results over SSE and publishes JSON or NvProto messages to Kafka; and covers evaluation, verification, Docker deployment, camera emulation, and file or camera latency measurement.

  1. An industrial software engineer builds video-based step-order verification for an assembly line.
  2. A platform engineer deploys the GPU, Triton, vLLM, and Kafka service with Docker Compose.
  3. A computer-vision engineer debugs GEBD segmentation, VLM classification, or missing-step detection.
  4. A factory-integration engineer connects an RTSP or Basler camera and validates live compliance output.
  5. A performance engineer measures SSE time to first chunk, end-to-end latency, or camera chunk latency.

What are this skill's strengths and limitations?

Pros
  • Covers implementation, deployment, evaluation, and latency measurement in one workflow.
  • Clearly separates GEBD-based segmentation from fixed-length uniform chunking.
  • Supports files, RTSP, and Basler/Pylon cameras, with SSE, Kafka, and Prometheus outputs.
  • Documents numerous implementation constraints for cleanup, GPU-frame handling, and concurrency.
Limitations
  • Requires a comparatively complex NVIDIA GPU software stack including Docker, DeepStream, Triton, vLLM, and Kafka.
  • Basler camera support requires the Pylon SDK; camera emulation has additional configuration requirements.
  • The supplied material does not provide a complete host compatibility matrix, performance benchmark, or end-to-end prerequisite list.
  • The scope is SOP sequence compliance, not generic object detection, tracking, or video summarization.

How do you install this skill?

Install the specific skill with the Skills CLI command documented in the repository README:

npx skills add nvidia/skills --skill deepstream-sop --yes

The CLI prompts for the installation destination. The README does not specify a fixed local folder or complete host-version prerequisites.

How do you use this skill?

Load the skill directory in an Agent Skills-compatible client and trigger it with a concrete request, for example: "Build and verify a DeepStream SOP inference service that accepts RTSP input, detects missing or out-of-order assembly steps, and streams results over SSE." For live RTSP or camera inputs, the skill requires stream=true. Full implementation depends on the referenced section files and the local sop-inference-bp reference code.

How does this skill compare with similar options?

The skill defines two chunking alternatives: the default ddm-net path uses GEBD/DDM for event-boundary detection, while uniform creates fixed-length chunks and bypasses Stage 1 GEBD. It does not compare the service with other products.

FAQ

Does the skill include a complete runnable service by itself?
It provides build, deployment, and debugging guidance and references sop-inference-bp source code; the supplied material does not state that installing the skill alone provides a complete runtime environment.
Are a GPU and network connectivity required?
The pipeline requires GPU-accelerated DeepStream processing; RTSP, Kafka, model downloads, or service communication require the applicable network connectivity.
What inputs are supported?
Video files, RTSP streams, and Basler/Pylon cameras are supported; live inputs must use stream=true.
Which models are used by default?
Stage 1 defaults to the DDM GEBD model through the Triton Python backend, and Stage 3 defaults to Cosmos Reason 1 7B; Cosmos Reason 2 is also supported.

More skills from this repository

All from NVIDIA/skills

Automation & Ops ✓ NVIDIA · Official

RTVI-CV 2D Detection & Tracking Operations

Deploy and operate the RTVI-CV 2D video detection and tracking microservice.

Dev & Engineering ✓ NVIDIA · Official

DeepStream Pipeline Profiler

Measure DeepStream pipelines and derive performance-focused configurations.

Automation & Ops ✓ NVIDIA · Official

VSS Multi-Camera 3D Detection and Tracking

Deploy multi-camera 3D perception with DeepStream and BEV Fusion.

Dev & Engineering ✓ NVIDIA · Official

NVIDIA DeepStream Development

Reliable Python pyservicemaker guidance for building NVIDIA DeepStream video analytics pipelines.

Automation & Ops ✓ NVIDIA · Official

AutoMagicCalib Calibration Stack Launcher

Deploy the AutoMagicCalib microservice and web UI with Docker Compose for a ready-to-use camera calibration stack.

Automation & Ops ✓ NVIDIA · Official

VSS Video Analysis Reports

Generates structured reports from recorded video clips or incident time ranges.

Data & Analysis ✓ NVIDIA · Official

VSS Video Analytics Query

Read video-analytics incidents, metrics, alerts, and sensor data through VA-MCP.

Automation & Ops ✓ NVIDIA · Official

VSS Standalone Video Analytics API

Deploy and verify NVIDIA’s VSS video analytics REST API without the full warehouse stack.

Dev & Engineering ✓ NVIDIA · Official

DeepStream Pipeline Builder

Collects pipeline requirements interactively, then generates and validates runnable GStreamer inference pipelines for NVIDIA DeepStream.

Automation & Ops ✓ NVIDIA · Official

VSS Standalone Behavior Analytics

Deploy and operate VSS behavior analytics independently without bringing up the full warehouse stack.

Automation & Ops ✓ NVIDIA · Official

Jetson Package & Environment Advisor

Select Jetson-compatible containers and GPU package indexes by device architecture.

Automation & Ops ✓ NVIDIA · Official

Jetson LLM Serving

Deploy OpenAI-compatible LLM and VLM servers on Jetson with vLLM or SGLang.

Automation & Ops ✓ NVIDIA · Official

Jetson vLLM Speculative Decoding

Configure speculative decoding for lower single-stream generation latency on Jetson vLLM servers.

Automation & Ops ✓ NVIDIA · Official

Jetson LLM Benchmark

Measure and compare LLM runtime performance on Jetson with structured JSON results.

Dev & Engineering ✓ NVIDIA · Official

Jetson Inference Memory Tuning

Choose a Jetson serving runtime and generate memory flags from the device snapshot and workload.

Data & Analysis ✓ NVIDIA · Official

RAGAS RAG Quality Evaluator

Benchmark retrieval-augmented generation quality against filesystem datasets.

Automation & Ops ✓ NVIDIA · Official

NVIDIA RAG Blueprint Operations

Deploy, configure, troubleshoot, and manage NVIDIA RAG Blueprint environments.

Dev & Engineering ✓ NVIDIA · Official

cuTile-to-Triton Kernel Converter

Port cuTile GPU kernels to validated, tunable Triton implementations.

Dev & Engineering ✓ NVIDIA · Official

AutoMagicCalib Video Calibration

Turn local multi-camera MP4 recordings into AutoMagicCalib calibration results through a REST API.

Automation & Ops ✓ NVIDIA · Official

VSS Video Auto-Calibration

Run end-to-end AutoMagicCalib calibration for local videos, RTSP cameras, or the bundled sample dataset.

Related skills