Skip to main content
skill CX Codex

senior-computer-vision · borghei — Claude Code skill

senior-computer-vision is a Claude Code skill for designing computer vision pipelines with object detection and segmentation.

LicenseRef-MIT-Commons-Clause 145 installs ★ 1,183 updated 2026-11-08

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add borghei/Claude-Skills --skill senior-computer-vision -a claude-code
Open on GitHub

What senior-computer-vision does

The skill provides three CLI tools: vision_model_trainer.py analyzes COCO or YOLO datasets and generates training configs, inference_optimizer.py tunes models for target platforms (GPU, edge, mobile) and exports to TensorRT or OpenVINO, dataset_pipeline_builder.py converts formats (COCO, YOLO, Pascal VOC), validates data, and builds train/val/test splits.

Architecture selection depends on the task—detection, segmentation, or classification—and speed-accuracy trade-offs. Default recommendation is YOLO26 (COCO mAP50-95: yolo26n 40.9, yolo26s 48.6, yolo26m 53.1); YOLO11 is supported for existing pipelines. Requires PyTorch (for .pt models) or onnxruntime (for ONNX); without them, inference_optimizer with --benchmark returns exit code 2.

The skill covers end-to-end workflows: data prep, architecture selection, training, and export to production targets. Does not include generative tasks (super-resolution, style transfer), 3D reconstruction, or SLAM.

What it helps with

  • generate a training config for YOLO on a custom dataset
  • optimize a trained model for inference on an edge device
  • convert a dataset from COCO to YOLO format and create splits
  • pick a detector architecture balancing accuracy and speed
  • export a model to TensorRT for GPU inference

Example prompts for the agent

  • Analyze the dataset in assets/sample_coco_valid and suggest an architecture for detection
  • Generate an MMDetection training config with batch size 16 and 100 epochs for my dataset
  • Optimize model.onnx for mobile deployment with quantization recommendations

How to install senior-computer-vision

1Skills CLI (Vercel)

npx skills add borghei/Claude-Skills --skill senior-computer-vision -a claude-code

2Manually: put the files in place

~/.claude/skills/senior-computer-vision/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/senior-computer-vision/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about senior-computer-vision

How do I install senior-computer-vision in Claude Code?

Run npx skills add borghei/Claude-Skills --skill senior-computer-vision -a claude-code in the terminal, then read ~/.claude/skills/senior-computer-vision/SKILL.md.

What does senior-computer-vision do?

The skill builds object detection and segmentation pipelines: it analyzes datasets, generates training configs for YOLO/Detectron2/MMDetection, optimizes and exports models to different platforms (GPU, edge, mobile).

What are the requirements?

For training, Python and PyTorch (for .pt models). For inference optimization, onnxruntime and numpy. Without them, recommendations are still given but benchmarking will not run.

Similar skills

All skills for AI and ML →

senior-computer-vision by other authors comes first.

senior-computer-vision Alireza Rezvani senior-computer-vision is a Claude Code skill for computer vision work, from object detection and image segmentation to model deployment. It applies to training pipelines and inference tuning. CX Codex +1 1,152installs computer-vision-pipeline curiositech A skill for building computer vision pipelines: object detection, tracking, and drone video analysis. Use it when you need to spot objects in frames or follow them through a video stream. CX Codex +1 288installs deepstream-import-vision-model Tushar Khinvasara The deepstream-import-vision-model skill takes an object-detection model from HuggingFace or NGC through a full NVIDIA DeepStream pipeline: ONNX, TRT engine, bbox parser, benchmark, PDF report. CX Codex +1 2,300installs Computer Vision aj-geddes A skill for computer vision work: image classification, object detection, segmentation and pose estimation with PyTorch and TensorFlow. CX Codex +1 510installs computer-vision-engineer davila7 computer-vision-engineer is a Claude Code subagent for building image and video analysis systems, from object detection to OCR. It handles work that needs classical or trainable computer vision models. CX Codex 1,248installs rtvi-cv-customize-model NVIDIA CORPORATION rtvi-cv-customize-model guides swapping the default DeepStream CV detector for a custom ONNX model in VSS Alerts Blueprint 2d_cv verification mode. CX Codex +1 ★ 4,106repo stars game-analytics-platform-computer-vision reason-machines game-analytics-platform-computer-vision guides the setup of a local fitness platform using computer vision, a Spring Boot backend, and a React dashboard for webcam workout tracking. CX Codex +1 1,600installs

From the same set120

The whole set →
aws-solution-architect aws-solution-architect — a skill for Claude Code, Codex, and Cursor that designs AWS architectures and outputs IaC templates. Tailors cloud patterns to workload demands and flags infrastructure savings. CX Codex +1 150installs playwright-pro playwright-pro — a skill for Claude Code, Codex, and Cursor. Generates Playwright end-to-end tests, builds Page Object structures, diagnoses flaky runs, and migrates suites from Cypress or Selenium. CX Codex +1 148installs skill-security-auditor skill-security-auditor — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode that scans agent skills before install. It detects prompt injection, dangerous code, credential harvesting and supply chain risks. CX Codex +1 146installs create-prd create-prd builds a product requirements doc in eight parts, from problem statement to P0/P1/P2 scope and release plan. Useful when a new feature needs one shared spec. CX Codex +1 146installs app-store-optimization app-store-optimization is a Claude Code skill that researches store keywords, refines app metadata, and analyzes reviews for Apple App Store and Google Play listings. CX Codex +1 144installs tdd-guide The tdd-guide Claude Code skill guides red-green-refactor cycles and works with test suites. It can draft tests from requirements and inspect coverage reports for gaps. CX Codex +1 143installs landing-page-generator The landing-page-generator Claude Code skill plans and builds landing pages around one conversion goal. It also supports campaign and lead-capture pages. CX Codex +1 142installs content-strategy content-strategy guides content planning by structuring topic clusters, defining content pillars, and auditing published material. CX Codex +1 140installs

Project sponsors

Companies that keep this analytics open