ReddRadar
Agent skill
Edge Deployment Skill
ML model optimization and deployment on robot edge devices (Jetson, embedded)
Install this agent skill to your Project
npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/specializations/robotics-simulation/skills/edge-deployment
SKILL.md
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
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
a5c-ai/babysitter
gsd-tools
Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).
a5c-ai/babysitter
model-profile-resolution
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.
a5c-ai/babysitter
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
a5c-ai/babysitter
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
a5c-ai/babysitter
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
a5c-ai/babysitter
frontmatter-parsing
YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.
Didn't find tool you were looking for?