image-to-text

Installation
SKILL.md

Image to Text

Extract all readable text from an image using OCR (Tesseract). Returns the full text content along with word-level bounding boxes and confidence scores.

When to Use

  • Reading text content from a screenshot or design mockup
  • Extracting UI copy (labels, buttons, headings) so you don't have to retype it
  • Getting text positions and bounding boxes from a design image

How It Works

  1. The image is passed to Tesseract.js for optical character recognition
  2. Tesseract segments the image into lines and words
  3. Returns the full text plus word-level details (position, confidence)

Usage

Installs
627
GitHub Stars
80
First Seen
Mar 6, 2026
image-to-text — pascalorg/skills