# Deepstream sop

> Deepstream sop is an open-source agent skill. Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-a. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/NVIDIA/skills/tree/main/skills/deepstream-sop
- **Repository:** https://github.com/nvidia/skills
- **GitHub stars:** 4,037
- **License:** Apache-2.0
- **Skill name:** deepstream-sop
- **Collection:** https://github.com/NVIDIA/skills
- **Listing updated:** 2026-11-17

## About

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.

## When your agent uses it

> 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.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Runs shell and Python scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/deepstream-sop)
- [Network calls found in its scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/deepstream-sop)
- [License: Apache-2.0](https://github.com/NVIDIA/skills/tree/HEAD/skills/deepstream-sop)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/deepstream-sop` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/deepstream-sop &&
cp -R "$tmp/skills/deepstream-sop" ~/.claude/skills/deepstream-sop &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/deepstream-sop` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/deepstream-sop` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/deepstream-sop &&
cp -R "$tmp/skills/deepstream-sop" ~/.agents/skills/deepstream-sop &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/deepstream-sop` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/deepstream-sop` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/deepstream-sop &&
cp -R "$tmp/skills/deepstream-sop" ~/.cursor/skills/deepstream-sop &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/deepstream-sop` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/NVIDIA/skills.git --path skills/deepstream-sop
```

Or copy the folder to `~/.gemini/skills/deepstream-sop` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/deepstream-sop`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/deepstream-sop &&
cp -R "$tmp/skills/deepstream-sop" ~/.copilot/skills/deepstream-sop &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/deepstream-sop` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/NVIDIA/skills.git
```

Then copy `skills/skills/deepstream-sop` into your agent's skills folder as `deepstream-sop`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Deepstream sop in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/deepstream-sop to use it in all your projects, or to .claude/skills/deepstream-sop in one project.

### Does Deepstream sop run scripts?

Yes. It runs shell and Python scripts. Its scripts contain network calls. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Deepstream sop?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

---
Source: https://ai-powered.com/skills/deepstream-sop
