Setup & Installation
npx skills add https://github.com/fal-ai-community/skills --skill fal-vision
https://github.com/fal-ai-community/skills/tree/main/skills/claude.ai/fal-vision
View on GitHubWhat This Skill Does
Analyzes images through fal.ai vision models. Supports object segmentation, object detection, OCR text extraction, image captioning, and visual question answering, all from a single shell script with different operation flags.
Bundles five distinct image analysis tasks into one script with a consistent interface, so you don't need separate tools or API calls for segmentation, detection, OCR, captioning, and visual QA.
When to use it
- Extracting text from a screenshot of a receipt or invoice
- Segmenting a specific object in a photo for further editing
- Counting items in a product image by running object detection
- Getting a plain-text description of a chart or diagram
- Asking a question about the contents of a medical scan or floor plan