Deepstream Dev

Brings NVIDIA's DeepStream SDK to Claude with full Python pyservicemaker API coverage. Built for video analytics pipelines where you need TensorRT inference, GStreamer plumbing, and optional tracking or Kafka integration. The skill enforces minimal pipeline patterns and catches the easy mistakes: wrong request pad syntax, memory model mismatches, and async sink configurations that deadlock state transitions. Ships with GPU memory handling rules, platform detection logic for Jetson versus x86, and version-specific guidance for GStreamer 1.24.2 and TensorRT 10.14. Genuinely useful if you're wiring up object detection on live streams and don't want to memorize nvstreammux quirks or NVMM caps strings.

skills.sh installs: 2.4K
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add nvidia/skills --skill deepstream-dev --agent claude-code

Installs into .claude/skills of the current project.

Files

DeepStream Development Skill

This skill requires access to all of the reference documents listed in the references/ directory below. Ensure they are available before executing the workflow.

When this skill is active, ALWAYS read the relevant reference documents before generating code. Do NOT rely on memory - the reference documents contain critical details about exact property names, correct API usage, and common pitfalls.

SDK and Architecture Quick Reference

DeepStream SDK Version Requirements

GStreamer: 1.24.2
NVIDIA Driver: 590+
CUDA: 13.1
TensorRT: 10.14.1.48
Platforms: Ubuntu 24.04 (x86_64 and ARM64/Jetson)

Typical Pipeline Flow

Source → Stream Muxer → Inference → [Tracker] → OSD → Renderer

Components in [brackets] are optional -- only add them when the user explicitly requests them.

SKILL.md on GitHub

Details

Repository: github.com/nvidia/skills
Categories: Backend & APIs, Data Science & ML, Python, Marketing & SEO
First seen: Jul 14, 2026