Vision and multimodal capabilities for Claude including image analysis, PDF processing, and document understanding. Activate for image input, base64 encoding, multiple images, and visual analysis.

Vision & Multimodal Skill Leverage Claude's vision capabilities for image analysis, document processing, and multimodal understanding. When to Use This Skill Image analysis and description Document/PDF processing Screenshot analysis OCR like text extraction Visual comparison Chart and diagram interpretation Supported Formats Format Status Best For JPEG ✓ Photos, natural scenes PNG ✓ Screenshots, UI, text GIF ✓ Animated (first frame) WebP ✓ Modern, compressed PDF ✓ Documents (via Files API) Image Size Guidelines Minimum: 200 pixels (smaller = reduced accuracy) Optimal: 1000x1000 pixels Maximum: 8000x8000 pixels Token cost: ~(width × height) / 1000 Tip: Resize to 1568px max dimension for 30 50% token savings Core Patterns Pattern 1: Single Image Analysis Pattern 2: Image from URL Pattern 3: Multiple Images Pattern 4: Few Shot with Images Pattern 5: PDF Processing Prompt Engineering for Vision Strategy 1: Role Assignment Strategy 2: Step by Step Thinking Strategy 3: Structured Output Image Optimization Common Use Cases Text Extraction (OCR like) Table Extraction Chart Analysis Best Practices DO: Use high quality images (≥1000px) Resize large images to save tokens Provide context about what to look for Use few shot examples for consistent output DON'T: Send images smaller than 200px Expect perfect OCR for handwriting Send very large images ( 8000px) Ignore token costs for multiple images Limitations Cannot identify specific individuals May struggle with very small text Animated GIFs: only first frame analyzed Some specialized symbols may be misread See Also [[llm integration]] API basics [[extended thinking]] Complex reasoning [[citations retrieval]] Document citations

vision-multimodal