Edge deployment
Skill a5c-ai/babysitter/library/specializations/robotics-simulation/skills/edge-deployment
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
npx -y skills add a5c-ai/babysitter --skill edge-deploymentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
ML model optimization and deployment on robot edge devices (Jetson, embedded)
SKILL.md
1.6 KB, 239 tokens by cl100k_base, as published. Nobody here has run it
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
What ships with it: 1 file
581 B alongside SKILL.md
- README.md581 B