visual-processor

Extract text, UI components, and relationships from images into Markdown summaries.

8|1|Updated Dec 28, 2025
One-click install
npx skills add https://github.com/officebeats/beats-pm-antigravity-brain --skill visual-processor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: visual-processor
Source: https://github.com/officebeats/beats-pm-antigravity-brain/tree/main/.agent/skills/visual-processor
Command: npx skills add https://github.com/officebeats/beats-pm-antigravity-brain --skill visual-processor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyzes images and screenshots to extract meaning, annotate content, and route findings to the right brain centers for faster visual decision-making.

Core Features & Use Cases

  • OCR & content extraction: Extract visible text and visual cues from images.
  • UI/Diagram Analysis: Detect UI components, charts, and diagrams to summarize layout and relationships.
  • Use Case: For a UI screenshot, generate a concise description and suggested next steps for designers or engineers.

Quick Start

Provide an image or screenshot to start the visual analysis and generate a descriptive summary.

Frequently Asked Questions about visual-processor

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

FAQPage Schema
How do I extract text and UI components from screenshots for routing?

To extract text and UI components from screenshots, perform OCR and visual content analysis to generate a descriptive summary and standardized routing cues for downstream AI workflows.

What is visual content analysis for UI bugs and diagrams?

Visual content analysis for UI bugs and diagrams is the process of detecting components and mapping relationships within images to produce a structured description and actionable next steps for engineers.

Can I analyze clipboard images and whiteboard diagrams without external dependencies?

Yes, you can analyze clipboard content and whiteboard diagrams without external dependencies by reading image files directly and processing them using built-in file and command operations.

What's the best way to generate descriptive summaries from chart screenshots?

The best way to generate descriptive summaries from chart screenshots is applying component detection and relationship mapping to extract semantic content and output a standardized Markdown analysis file.

Does image analysis for routing work with PNG files in staging directories?

Yes, image analysis for routing works with PNG files by processing the image content and outputting the primary artifact directly into a structured staging directory with date and type labels.

When should I not use automated OCR for visual content extraction?

You should not use automated OCR for visual content extraction when images lack distinguishable text patterns or when complex visual relationships require manual human interpretation for accurate routing.