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.
npx -y skills add nvidia/skills --skill deepstream-dev --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills