doc-reader

Extract text from PDFs, images, spreadsheets, and code files.

15|2|Updated May 1, 2026
One-click install
npx skills add https://github.com/OpenSucker/OpenSucker --skill doc-reader-opensucker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc-reader
Source: https://github.com/OpenSucker/OpenSucker/tree/main/skills/vibe_skills/doc-reader
Command: npx skills add https://github.com/OpenSucker/OpenSucker --skill doc-reader-opensucker

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rapidocr-onnxruntime, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables users to extract and comprehend text from diverse document formats, reducing manual copying and data entry efforts.

Core Features & Use Cases

  • Universal Document Access: Read text from PDFs, Word, Excel, PowerPoint, images, CSV, JSON, YAML, HTML, source code, and other common file types.
  • Versatile Data Handling: Supports extracting text from images via OCR, reading tables from Excel, and parsing code files, making it ideal for research, review, and data analysis.
  • Use Case: Imagine reviewing an entire research report stored as a PDF, an Excel database, and embedded images; this Skill consolidates all into structured text for analysis and summarization.

Quick Start

Use the doc-reader to extract text content from the uploaded PDF file 'report.pdf' for review.

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 a PDF and an Excel spreadsheet simultaneously?

To extract text from a PDF and Excel simultaneously, use a universal document reader that parses both file formats into structured text. This Skill handles PDFs, spreadsheets, and images, consolidating diverse files for unified analysis.

Can I use OCR to extract text from images embedded in a Word document?

Yes, you can use OCR to extract text from images embedded in a Word document. The Skill utilizes the rapidocr-onnxruntime dependency to perform text recognition on images, enabling comprehensive data extraction from mixed-format files.

What is the best way to read and parse source code files for research?

The best way to read and parse source code files for research is using a universal document parsing tool. This Skill supports extracting and comprehending text from source code, CSV, JSON, and YAML, facilitating efficient review workflows.

Does doc-reader work with PowerPoint and HTML files?

Yes, doc-reader works with PowerPoint and HTML files. It extracts and reads text from multiple document formats including PPT, HTML, PDFs, Word, and Excel, reducing manual copying and data entry efforts across various file types.

How to extract data tables from Excel for automated review workflows?

To extract data tables from Excel for automated review workflows, apply a versatile data handling tool that reads spreadsheet structures. This Skill parses Excel files and converts them into structured text for analysis and summarization.

Do I need rapidocr-onnxruntime to process PDF text extraction?

You need rapidocr-onnxruntime specifically when processing scanned PDFs or extracting text from images. For standard text-based PDFs and spreadsheets, the Skill parses text directly without requiring the OCR engine dependency.