Skip to main content
affpapa.org
RU EN
subagent

computer-vision-engineer — Claude Code subagent: features and setup

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.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --agent data-ai/computer-vision-engineer
Open on GitHub

What computer-vision-engineer 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.

What it helps with

  • 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 for the agent

  • 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.

How to install computer-vision-engineer

1claude-code-templates

npx claude-code-templates@latest --agent data-ai/computer-vision-engineer

2Manually: put the files in place

.claude/agents/computer-vision-engineer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about computer-vision-engineer

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

Run npx claude-code-templates@latest --agent data-ai/computer-vision-engineer. The agent file is listed at .claude/agents/computer-vision-engineer.md.

What does computer-vision-engineer do?

It helps create computer-vision pipelines for images and video, including detection, segmentation, face recognition, OCR, and tracking.

When should I use computer-vision-engineer instead of ai-engineer?

Use computer-vision-engineer for a dedicated vision pipeline or trainable model. Its description directs one-off visual questions without a custom pipeline to ai-engineer.

Similar subagents

All subagents for AI and ML →
prompt-engineer VoltAgent Community This subagent designs, tests, and improves prompts for LLM production systems. Use it when prompts need evaluation, metrics, or cost tracking. 16,078installs prompt-engineer Seth Hobson This subagent designs and tests prompts for LLM features, agent workflows, and system instructions. Use it when prompt structure, safety, or evaluation needs deliberate work. CX Codex 16,078installs ai-engineer VoltAgent Community This subagent helps design AI systems, choose models, build training pipelines, and prepare deployment. Use it when work spans research through production. 7,687installs ai-engineer Seth Hobson This subagent designs LLM applications, RAG systems, and AI agents. Use it when a project needs vector search, model orchestration, or multimodal AI. CX Codex 7,687installs search-specialist Seth Hobson A web research subagent that filters sources and cross-checks facts. Use it for deep research, competitive analysis, and trend work. CX Codex 6,886installs business-analyst Seth Hobson This subagent analyzes business data and helps shape KPIs, forecasts, and financial models. Use it to turn a business question into an analysis plan and recommendations. CX Codex 3,855installs

From the same set495

The whole set →
terraform-specialist A Terraform subagent that builds modules, wires up remote state and hunts drift. Useful once your infrastructure outgrows a single main.tf. 1,349installs supabase-realtime-optimizer This subagent reviews Supabase Realtime subscriptions, WebSocket connections, latency, and message flow. Use it when realtime behavior needs diagnosis or tuning. 1,346installs backup-before-edit A Claude hook that copies a file with a timestamp before every edit. Useful when the agent rewrites code and you want a way back. 1,328installs vercel-deployment-specialist Configures Vercel platform deployments, creates vercel.json setups, and implements edge logic. Helps automate releases and routing. 1,309installs executing-marketing-campaigns Structures campaign planning, outbound copy, and performance tracking inside Claude Code across email, social, and web channels. 1,236installs containerize-application A slash command that writes the Docker setup for your project: Dockerfile, .dockerignore, docker-compose and Kubernetes manifests. 1,200installs review-agent Audits Obsidian vault changes by checking reports, metadata, links, tags, and MOCs. Run it after enhancement work to spot inconsistencies across the vault. 1,198installs test-generator This subagent studies code changes and project test conventions before outlining useful test cases. Use it when new or changed logic needs coverage. 1,182installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor