skills.rest
Liangwei-zhang
Liangwei-zhangCOMMUNITY
Explore all skills by this author →
GitHub

doc-reader

Extract text from PDFs and apply OCR to image-based pages.

Updated Apr 14, 2026
Search Tags:#ocr#pdf#document-processing#text-extraction#papers#annual-reports#read-document
One-click install
npx skills add https://github.com/Liangwei-zhang/six-stock --skill doc-reader-liangwei-zhang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doc-reader
Source: https://github.com/Liangwei-zhang/six-stock/tree/main/Vibe-Trading/agent/src/skills/doc-reader
Command: npx skills add https://github.com/Liangwei-zhang/six-stock --skill doc-reader-liangwei-zhang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Read PDFs and scanned documents to automatically extract text pages and apply OCR, turning static files into searchable content for research, archiving, and review.

Core Features & Use Cases

  • Text extraction from text-based PDF pages
  • OCR for image or scanned pages
  • Support for full documents or specific page ranges

Quick Start

Call read_document on a PDF to extract text and apply OCR to image-based pages.

Frequently Asked Questions about doc-reader

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

FAQPage Schema
How do I extract text from scanned PDF documents and image-based pages?▼

To extract text from scanned PDF documents, the Skill applies OCR to image-based pages and standard text extraction to text-based pages, returning structured searchable text output for research and archiving.

What is the best way to digitize annual reports and contracts for searchable text?▼

The best way to digitize annual reports and contracts is using automated text extraction and OCR, which turns static PDF files into structured searchable content while handling both text-based and scanned image pages.

Does this PDF text extraction tool work on both text-based and scanned image pages?▼

Yes, the PDF text extraction tool works on both text-based and scanned image pages by automatically applying direct text extraction or OCR respectively, ensuring full-document digitization for academic papers and contracts.

Can I process only a specific page range instead of a full PDF document?▼

Yes, you can process specific page ranges instead of a full PDF document by defining the page selection during the read_document call, receiving targeted extracted text and a JSON summary of pages read.

Related Skills

Explore More Education & Research Skills→
DaddyElonMusk69DaddyElonMusk69

doc-reader

Extract text from PDFs with OCR for scanned pages.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
NickCrewNickCrew
29

pdf

Extract text, tables, and structured data from PDF documents.

Community
Advanced
robertbr123robertbr123

nano-pdf

Modify text, titles, and dates in PDF documents via natural language commands.

Community
Basic