OpenParable
Skip to content
← Back to skills

Edge Deployment Skill

DevOps & Security

Edge Deployment Skill is an Agent Skill for devops & security published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

ML model optimization and deployment on robot edge devices (Jetson, embedded)

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/robotics-simulation/skills/edge-deployment/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/edge-deployment-skill, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Edge Deployment Skill

Overview

Expert skill for optimizing and deploying machine learning models on robot edge devices including NVIDIA Jetson and embedded systems.

Capabilities

  • Configure TensorRT optimization for NVIDIA Jetson
  • Set up ONNX model conversion and optimization
  • Implement INT8 and FP16 quantization
  • Configure DeepStream for video analytics
  • Set up CUDA graph optimization
  • Implement model pruning and distillation
  • Configure DLA (Deep Learning Accelerator) deployment
  • Set up multi-stream inference
  • Implement ROS2 inference nodes
  • Profile and benchmark on target hardware

Target Processes

  • nn-model-optimization.js
  • object-detection-pipeline.js
  • rl-robot-control.js
  • field-testing-validation.js

Dependencies

  • TensorRT
  • ONNX Runtime
  • NVIDIA Jetson SDK
  • DeepStream

Usage Context

This skill is invoked when processes require deploying ML models on edge devices with optimized inference performance.

Output Artifacts

  • TensorRT engine files
  • ONNX optimized models
  • Quantization configurations
  • DeepStream pipeline configs
  • Inference benchmark reports
  • ROS2 inference node implementations