image-ocr

Extract readable text from JPG, PNG, and WEBP images into JSON.

4|Updated Feb 22, 2026
One-click install
npx skills add https://github.com/GeneralReasoning/env-skillsbench --skill image-ocr-generalreasoning
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-ocr
Source: https://github.com/GeneralReasoning/env-skillsbench/tree/main/jpg-ocr-stat/environment/skills/image-ocr
Command: npx skills add https://github.com/GeneralReasoning/env-skillsbench --skill image-ocr-generalreasoning

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert image content containing text into machine-readable text by applying Tesseract OCR via pytesseract, enabling digitization of documents, receipts, and screenshots without manual transcription.

Core Features & Use Cases

  • OCR for photographs, scans, and screenshots to produce searchable text.
  • Batch processing support for large image sets in data pipelines.
  • Useful for document digitization, form data capture, receipts archiving, and accessibility improvements.

Quick Start

Provide the image file path and the skill will return the extracted text in JSON.

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 images using Python for a data pipeline?

To extract text from images, this skill applies Tesseract OCR via the pytesseract Python library to process photographs and scans, returning structured JSON data suitable for batch processing in data pipelines.

What image formats are supported by Tesseract OCR for text extraction?

Tesseract OCR text extraction supports common image formats including JPG, PNG, and WEBP, allowing you to digitize documents, receipts, and screenshots by converting them into searchable text.

Do I need to install pytesseract and Pillow to perform OCR on image files?

Yes, you need the Python libraries pytesseract and Pillow installed to perform OCR on image files, as the skill relies on these dependencies to process images and output extracted text as JSON.

Can I batch process receipts and forms to extract text from multiple images?

You can batch process receipts and forms to extract text from multiple images because the skill supports large image sets in digitization workflows, outputting structured text data for each processed file.

What is the best way to digitize screenshots and scans into machine-readable text?

The best way to digitize screenshots and scans into machine-readable text is using Tesseract OCR, which automatically transcribes image content into structured JSON data without requiring manual data entry.