image-ocr

Extract text from image files using Tesseract OCR.

Updated Mar 11, 2026
One-click install
npx skills add https://github.com/ekkus93/vscode_skills --skill image-ocr-ekkus93
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-ocr
Source: https://github.com/ekkus93/vscode_skills/tree/main/skills/image-ocr
Command: npx skills add https://github.com/ekkus93/vscode_skills --skill image-ocr-ekkus93

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OCR converts image-based content into searchable, editable text, saving time from manual transcription.

Core Features & Use Cases

  • Extracts text from common image formats (png, jpg, jpeg, tif, tiff) using Tesseract.
  • Supports language selection (default eng) and outputs plain text to a .txt file.
  • Useful for processing receipts, photos, screenshots, and scanned documents.

Quick Start

Provide an input image path to start OCR and return the extracted text to a .txt file.

Frequently Asked Questions about image-ocr

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

FAQPage Schema
How do I extract text from a scanned image?

To extract text from a scanned image, you need OCR software like Tesseract. This process converts image-based content into searchable, editable text, saving time from manual transcription of photos and scanned documents.

What image formats are supported for image-to-text conversion?

Image-to-text conversion supports common formats including png, jpg, jpeg, tif, and tiff. You provide an input image path, and the extracted text is output to a plain text .txt file.

Do I need Tesseract installed to perform OCR on receipts?

Yes, you must have Tesseract installed to perform OCR on receipts. This tool applies Tesseract to extract text across Linux and macOS environments where the dependency is available.

Can I extract text from screenshots in languages other than English?

Yes, you can extract text from screenshots in other languages by specifying the language parameter. It defaults to English (eng) when a language is not explicitly provided during the OCR process.

What is the best way to process scanned documents into editable text?

The best way to process scanned documents into editable text is using Tesseract OCR. It directly parses image files such as receipts and screenshots, outputting the recognized characters into a plain .txt file.