gemini-image
Analyze images using Gemini's vision capabilities. Use for image analysis, text extraction from screenshots, and visual content understanding.
By johnlindquist · 1,234 installs
npx skills add johnlindquist/claude --skill gemini-image
Source repository · Upstream listing
Gemini Image Analysis
Analyze images using Gemini Pro's vision capabilities.
Prerequisites
CLI Reference
Basic Image Analysis
Analysis Operations
General Description
Extract Text (OCR)
Code from Screenshot
UI Analysis
Error Analysis
Diagram Understanding
Specific Use Cases
Debug Screenshot
Compare Before/After
Design Feedback
Data Extraction
Form Analysis
Workflow Patterns
Screenshot to Issue
UI to Code
Documentation
Image Types Supported
PNG, JPEG, GIF, WebP
Screenshots
Photos
Diagrams and charts
UI mockups
Code snippets
Documents
Best Practices
1. Use clear images Higher quality = better analysis
2. Crop to relevant area Remove unnecessary context
3. Ask specific questions Vague prompts get vague answers
4. Provide context Tell Gemini what you're looking for
5. Verify extracted text OCR isn't perfect
6. Multiple angles Use multiple images for complex subjects