Senior Computer Vision

If you're building object detection or segmentation systems, this gives you training configs for YOLO, Detectron2, and MMDetection, plus optimization workflows for ONNX, TensorRT, and OpenVINO. The three workflows cover detection pipeline setup (architecture selection, dataset prep, training), production optimization (benchmarking, quantization, runtime conversion with actual speedup expectations), and dataset preparation with format conversion. Useful when you need to go from raw images to a deployed model and want the boilerplate decisions made for you. The optimization workflow is the strong part, walking through FP32 to FP16 to INT8 with calibration steps and realistic performance targets.

skills.sh installs: 143
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add borghei/claude-skills --skill senior-computer-vision --agent claude-code

Installs into .claude/skills of the current project.

Files

Senior Computer Vision Engineer

Design end-to-end computer vision pipelines for object detection, instance/semantic segmentation, and production deployment. Generates training configurations for YOLO/Detectron2/MMDetection, optimizes models for ONNX/TensorRT/OpenVINO runtimes, and builds dataset preparation workflows with format conversion and augmentation.

Core Capabilities

Detection pipeline design — requirements analysis, architecture selection (YOLO/RT-DETR/Faster R-CNN/DINO), dataset prep, training config, and metric evaluation.
Model optimization & deployment — baseline benchmarking, ONNX export, INT8/FP16 quantization, and conversion to TensorRT/OpenVINO/CoreML/TFLite per target platform.
Dataset engineering — audit, cleaning, format conversion (COCO/YOLO/VOC/CVAT/LabelMe), augmentation config, and stratified train/val/test splits.
Architecture guidance — detection and segmentation architecture trade-offs plus CNN vs Vision Transformer selection.
Production targets — FPS, mAP, latency P99, memory, and model-size budgets for real-time, high-accuracy, and edge deployments.