extract

Name: extract
Availability: InStock
Author: Hasna

Extract text and structured data from images and PDFs into plain text, Markdown, or JSON.

24|26|Updated Feb 14, 2026

Search Tags:#ocr #data extraction #pdf #image #text extraction #extract #openai vision

Ready to run

npx skills add https://github.com/hasna/skills --skill extract-hasna

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: extract
Source: https://github.com/hasna/skills/tree/main/skills/skill-extract
Command: npx skills add https://github.com/hasna/skills --skill extract-hasna

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdf-parse, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the extraction of text and structured data from images and PDF documents, saving you the time and effort of manual data entry and transcription.

Core Features & Use Cases

Image OCR: Accurately extract text from images using advanced AI vision models.
PDF Text Extraction: Parse text content directly from PDF files.
Structured Output: Get your extracted data in plain text, Markdown, or JSON formats.
Use Case: Automatically extract invoice details from a scanned receipt image or convert a multi-page PDF report into a structured Markdown document for easier review.

Quick Start

Use the extract skill to get the text from the image file named 'receipt.png'.

Frequently Asked Questions about extract

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

FAQPage Schema

How do I extract text from scanned images and PDF files?▼

To extract text from images and PDFs, this skill uses AI-powered OCR and native parsing to pull content from PNG, JPG, and PDF files. It processes the input and returns the extracted text directly.

Can I get structured JSON output from OCR data extraction?▼

Yes, OCR data extraction supports structured JSON output alongside plain text and Markdown formats. Optional AI structuring organizes the extracted natural language data into your desired output schema.

Does pdf-parse work for extracting text from multi-page PDF reports?▼

Yes, pdf-parse is used for extracting text directly from multi-page PDF reports. It natively parses the document to retrieve text content, which can then be formatted into Markdown for easier review.

What is the best way to automate invoice data extraction from receipts?▼

The best way to automate invoice data extraction from receipts is using AI vision models to analyze the image. This approach accurately captures text and structured data, eliminating manual transcription effort.

Does image text extraction work with OpenAI Vision for JPG and PNG formats?▼

Yes, image text extraction leverages OpenAI Vision to analyze and pull text from JPG and PNG formats. The AI vision models accurately recognize and transcribe the text content within your image files.

What are the limitations of AI-powered OCR for data extraction?▼

AI-powered OCR for data extraction is limited by the quality of input images and the native parsing capabilities for PDFs. Complex layouts or low-resolution scans may result in less accurate text recognition and structuring.