# senior-computer-vision

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

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 145 installs · ★ 1183 repo stars
- Author: borghei
- License: LicenseRef-MIT-Commons-Clause · policy=link-only · description only; the file stays with the author
- Source: https://github.com/borghei/Claude-Skills/tree/HEAD/engineering/senior-computer-vision/SKILL.md
- Updated: 2026-11-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/borghei-senior-computer-vision

## What it 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.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-computer-vision -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/senior-computer-vision/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/senior-computer-vision/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-computer-vision -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/senior-computer-vision/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-computer-vision -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/senior-computer-vision/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install borghei/Claude-Skills engineering/senior-computer-vision/SKILL.md
```

2. **Manually: put the files in place**
- File: `.github/skills/senior-computer-vision/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-computer-vision -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/borghei/Claude-Skills --path engineering/senior-computer-vision
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/senior-computer-vision/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-computer-vision -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/borghei/Claude-Skills/tree/HEAD/engineering/senior-computer-vision/SKILL.md

## When to use it
- 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
- 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

## Similar
- [computer-vision-pipeline](https://affpapa.org/en/nevibecode/skills/computer-vision-pipeline.md) — skill · 288 installs
- [deepstream-import-vision-model](https://affpapa.org/en/nevibecode/skills/deepstream-import-vision-model.md) — skill · 2300 installs
- [Computer Vision](https://affpapa.org/en/nevibecode/skills/computer-vision.md) — skill · 510 installs
- [computer-vision-engineer](https://affpapa.org/en/nevibecode/agents/computer-vision-engineer.md) — subagent · 1248 installs
- [rtvi-cv-customize-model](https://affpapa.org/en/nevibecode/skills/rtvi-cv-customize-model.md) — skill · ★ 4106 repo stars
- [game-analytics-platform-computer-vision](https://affpapa.org/en/nevibecode/skills/game-analytics-platform-computer-vision.md) — skill · 1600 installs

## Other versions with the same name
- [senior-computer-vision · alirezarezvani](https://affpapa.org/en/nevibecode/skills/senior-computer-vision.md) — 1152 installs

From the same set: [borghei/claude-skills](https://affpapa.org/en/nevibecode/by/borghei/claude-skills.md) — 120 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
