# computer-vision-engineer

This subagent helps build image and video analysis pipelines, from object detection and OCR to face recognition and tracking. Use it when a task calls for a dedicated computer-vision system.

- subagent · `type=agent` · Claude Code · 1248 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/data-ai/computer-vision-engineer.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/computer-vision-engineer

## What it does

computer-vision-engineer handles work involving classical or trainable vision models: object detection and segmentation, face recognition, document OCR, image-quality assessment, and video analysis. It can also help choose models and plan deployment. For a one-off question about an image without a custom pipeline, its description points to `ai-engineer` instead.

For early validation, the agent suggests considering zero-shot models; once classes and latency requirements are defined, a fine-tuned lightweight detector may be a better fit. Examples include Grounding DINO, YOLO11, EasyOCR, Tesseract, and InsightFace. YOLO11 uses AGPL-3.0, and closed-source commercial use requires a paid Ultralytics Enterprise license. Check that licensing before choosing it.

Install it in Claude Code with `npx claude-code-templates@latest --agent data-ai/computer-vision-engineer`. The agent file is listed at `.claude/agents/computer-vision-engineer.md`.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent data-ai/computer-vision-engineer
```

2. **Manually: put the files in place**
- File: `.claude/agents/computer-vision-engineer.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/computer-vision-engineer.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/computer-vision-engineer.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/data-ai/computer-vision-engineer.md

## When to use it
- detect and track objects across video frames
- extract text and fields from scanned documents
- build a face-recognition pipeline
- segment objects in images

## Example prompts
- Build a pipeline to detect products on shelf images and track them between frames.
- Set up OCR for scanned invoices and extract line items, totals, and vendor details.
- Design face recognition for an access system and account for privacy and bias concerns.

## Similar
- [prompt-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-prompt-engineer.md) — subagent · 16078 installs
- [prompt-engineer](https://affpapa.org/en/nevibecode/agents/prompt-engineer.md) — subagent · 16078 installs
- [ai-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-ai-engineer.md) — subagent · 7687 installs
- [ai-engineer](https://affpapa.org/en/nevibecode/agents/ai-engineer.md) — subagent · 7687 installs
- [search-specialist](https://affpapa.org/en/nevibecode/agents/search-specialist.md) — subagent · 6886 installs
- [business-analyst](https://affpapa.org/en/nevibecode/agents/business-analyst.md) — subagent · 3855 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 495 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