cudaq-guide
CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.
jetson-print-device-info
Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target. This is an example skill.
Full skill instructions
Prints a concise summary of the Jetson device this skill runs on.
This skill is intended as a reference example for the jetson-device-skills repo and the NVIDIA-wide skills CI. It runs on the Jetson target (not the host PC) and performs read-only inspection — useful as a baseline capture before running performance tests.
Capture a baseline snapshot of a Jetson target's software stack and power mode before running performance, regression, or compatibility tests.
tr, cat, uname, uptime, lsb_release (or /etc/os-release).nvpmodel available for power mode (optional — skill falls back gracefully).None. The skill reads only from the local Jetson filesystem and standard CLIs.
Run each step in order and print the captured values into the report shown under Output format.
# Device-tree strings are null-terminated, so strip NULs before printing.
model=$(tr -d '\0' < /proc/device-tree/model 2>/dev/null)
case "$model" in
*Jetson*) ;;
*) echo "Not running on a Jetson target (model: '${model:-unknown}')"; exit 1 ;;
esac
echo "$model"
head -1 /etc/nv_tegra_release 2>/dev/null || echo "L4T release info not found"
# Equivalent: grep -m1 '^# R' /etc/nv_tegra_release
nvpmodel -q and join its two output lines (NV Power Mode: <name> and the mode number) onto one line. paste -sd only uses the first char of its delimiter, so use awk to insert the literal / separator:
nvpmodel -q 2>/dev/null | awk 'NR==1{a=$0; next} {print a" / "$0}' \
|| echo "nvpmodel not available"
uname -r
uptime -p
lsb_release, fall back to /etc/os-release):
lsb_release -ds 2>/dev/null || (. /etc/os-release && echo "$PRETTY_NAME") || echo "OS version not found"
Print a short report with these sections, one line each where possible:
Model: <device-tree model string>
L4T release: <release header line>
Power mode: <nvpmodel name> / <mode number>
Kernel: <uname -r>
Uptime: <uptime -p>
OS version: <lsb_release / /etc/os-release output>
Example output on an Orin AGX dev kit (L4T R36 / Ubuntu 22.04):
Model: NVIDIA Jetson AGX Orin Developer Kit
L4T release: # R36 (release), REVISION: 3.0
Power mode: NV Power Mode: MAXN / 0
Kernel: 5.15.136-tegra
Uptime: up 2 hours, 14 minutes
OS version: Ubuntu 22.04.4 LTS
Example output on an AGX Thor (L4T R39 / Ubuntu 24.04):
Model: NVIDIA Jetson AGX Thor Developer Kit
L4T release: # R39 (release), REVISION: 0.0
Power mode: NV Power Mode: 120W / 1
Kernel: 6.8.0-tegra
Uptime: up 12 minutes
OS version: Ubuntu 24.04 LTS
Each command falls back to a clearly labeled "... not found" / "... not available" string if the underlying file or binary is missing — the skill never errors out mid-report. If /proc/device-tree/model is missing or does not contain a Jetson string, exit early with a clear "not running on a Jetson target" message.
nvpmodel output format varies between L4T versions; the skill prints it verbatim rather than parsing.Error: /proc/device-tree/model: No such file or directory
Cause: Running on a host PC, not a Jetson target.
Solution: Run the skill on the Jetson device directly (e.g. via SSH).
Error: nvpmodel: command not found
Cause: L4T BSP not installed, or running in a minimal container without nvpmodel.
Solution: Expected on non-Jetson or stripped environments — the skill prints "nvpmodel not available" and continues.
/proc/device-tree/model will not contain a Jetson model string — detect that and exit with a clear message rather than printing misleading info.CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg` `.png` `.tiff`), Office (`.docx` `.pptx`), text (`.html` `.txt`), audio (`.mp3` `.wav` `.m4a`), or video (`.mp4` `.mov`). Prefer this over native Read / Grep for multi-file or non-PDF corpora. Not for: editing files, web browsing, single-file plain-text lookups, fine-tuning.
Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that require conversion, material/physics assignment, SimReady conformance, validation, and optional package creation; deploy or verify Content Agents services first when property assignment is enabled; route single-stage work through nested references.
Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
Top-level workflow skill for USD performance diagnosis and optimization. Handles slow loading, high memory, low FPS, and broad scene-optimization requests; delegates auth/runtime setup to Phase 0 owners.
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.
Use as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience