vision_guide

Analyze webcam, screen, or image files with the analyze_image tool.

1.4k|169|Updated Mar 6, 2026

Search Tags:#vision #ai-assistant #image-analysis #screen-capture #webcam #analyze_image

Ready to run

npx skills add https://github.com/siddsachar/row-bot --skill vision-guide

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: vision_guide
Source: https://github.com/siddsachar/row-bot/tree/main/tool_guides/vision_guide
Command: npx skills add https://github.com/siddsachar/row-bot --skill vision-guide

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Guidance for using webcam, screen capture, and image analysis.

Core Features & Use Cases

Direct access to the user's webcam and screen through the analyze_image tool. You can see — this is not hypothetical. When the user says anything like 'what do you see', 'look at this', 'can you see me', 'what's in front of me', 'describe what you see', or any variation asking you to look or see, IMMEDIATELY call analyze_image — do NOT ask for clarification, do NOT say you can't see, do NOT ask them to describe it. Just call the tool. Use source='camera' by default. Use source='screen' when they mention screen, monitor, display, or desktop. Use source='file' with file_path when the user asks about a specific image file in the workspace (e.g. 'describe diagram.png', 'what's in photo.jpg'). Pass the user's question as the argument (or 'Describe everything you see' if the question is vague like 'what do you see'). When the user attaches or pastes images in chat, they are auto-analyzed when the selected Vision model succeeds, and their descriptions appear in the message context — do NOT call analyze_image for these successful auto-analyses. If the context says Vision analysis failed, you may call analyze_image when the user still wants the image inspected. Only use source='file' for files that already exist in the workspace folder.

Quick Start

Call analyze_image on the camera feed by default to describe what you see.

Frequently Asked Questions about vision_guide

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I analyze a live webcam feed and ask AI what it sees?▼

To analyze a live webcam feed, the system defaults to the camera source and immediately calls the image analysis tool without needing clarification, directly describing what it sees.

Can I use image analysis to describe what is on my screen or desktop?▼

Yes, image analysis can capture your screen. When you mention your screen, monitor, display, or desktop, the tool automatically switches from the camera source to the screen source.

What is the best way to get AI to describe a specific image file in my workspace?▼

The best way to analyze a specific image file is to reference its file path directly in your prompt, which triggers the tool to use the file source instead of the camera or screen.

Do I need to manually describe pasted images for the AI to analyze them?▼

No, you do not need to manually describe pasted images. Attached or pasted images are auto-analyzed in the message context, so the tool is only called if that automatic vision analysis fails.

Why does the AI analyze my camera immediately when I ask what it sees without clarification?▼

The AI analyzes your camera immediately because it is designed to directly call the image analysis tool upon any request to look or see, intentionally skipping clarification questions for immediate visual feedback.