DeepStream Pipeline Builder

DeepStream Pipeline Builder is an Automation skill for Claude Code, published by NVIDIA in skills.

3K stars345 forkson NVIDIA/skillsAdded 2026/08/17+3% in starsRepository updated 2026/08/17

agent-skillsagentic-aiai-agentsclaude-codecodexcoding-agentscudadeveloper-toolsllmomniversephysical-airagroboticssimulation

Install in seconds

Install DeepStream Pipeline Builder

Copy DeepStream Pipeline Builder into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/NVIDIA/skills/tree/main/skills/deepstream-generate-pipeline ~/.claude/skills/deepstream-generate-pipeline

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/NVIDIA/skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/deepstream-generate-pipeline/SKILL.md in NVIDIA/skills
Installs to: ~/.claude/skills/deepstream-generate-pipeline
Collection: One of 25 skills cataloged from this repository
Category: Automation — 1523 skills

What DeepStream Pipeline Builder does

DeepStream Pipeline Builder generates ready-to-run gst-launch-1.0 pipelines for NVIDIA DeepStream SDK. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming.

DeepStream Pipeline Builder is cataloged under Automation on DirSkills. DeepStream Pipeline Builder comes from a repository tagged agent-skills, agentic-ai, ai-agents, claude-code and codex.

Documentation

README

Excerpt

DeepStream Pipeline Builder

Generate ready-to-run gst-launch-1.0 pipelines for NVIDIA DeepStream SDK by collecting pipeline requirements through an interactive questionnaire, then assembling the pipeline using a standalone BM25 retrieval backend with structural metadata boosting (similarity search over 270+ verified pipelines, zero external dependencies).

Prerequisites

Python: 3.8+ (stdlib only — no pip packages required)
DeepStream SDK: Installed at /opt/nvidia/deepstream/deepstream/ (for gst-inspect-1.0 validation and element verification)
GStreamer: gst-launch-1.0 and gst-inspect-1.0 on PATH (installed with DeepStream)
Platform: x86 dGPU (T4, A100, L40, RTX, etc.) or aarch64 — Jetson (Orin, Xavier, Nano) / SBSA (Grace, GH200)

This is the opening of the README. Read the full README on GitHub.

Frequently asked about DeepStream Pipeline Builder

What else does NVIDIA publish alongside DeepStream Pipeline Builder?
DeepStream Pipeline Builder is one of 25 skills that DirSkills catalogs from NVIDIA/skills, the repository it ships in. Its siblings there include AIQ Deploy, AIQ Research and AMC RTSP Calibration. Each one is a separate skill with its own page in this directory, installs the same way DeepStream Pipeline Builder does, and is maintained by NVIDIA in that same repository. The rest of the collection is listed on the NVIDIA/skills page.
How does DeepStream Pipeline Builder compare to other Automation skills?
DeepStream Pipeline Builder ranks #405 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of DeepStream Pipeline Builder against them. Open each page to compare what they document and how they install.