doc-reader

Extract text and OCR content from PDF documents with page selection.

30.4k|4.9k|Updated Apr 1, 2026

Search Tags:#ocr #pdf #text-extraction #research-analysis #document-reading #annual-report #read_document

Ready to run

npx skills add https://github.com/HKUDS/Vibe-Trading --skill doc-reader-hkuds

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: doc-reader
Source: https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/doc-reader
Command: npx skills add https://github.com/HKUDS/Vibe-Trading --skill doc-reader-hkuds

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Facing lengthy PDF reports that mix digital text and scanned imagery delays insight, so this Skill automates both direct extraction and OCR recognition to deliver the full document content quickly.

Core Features & Use Cases

Text and OCR extraction: Pull text directly from native pages and apply OCR to scanned or image-heavy pages with bilingual support.
Selective reading: Target precise sections by specifying page ranges when working through annual reports, research papers, or contracts to stay within character limits.
Workflow example: Read a research paper to capture the abstract, methodology, and conclusion before summarizing the key findings or metrics.

Quick Start

Ask the agent to call read_document with the desired PDF file path and optional pages range so you can immediately review the extracted text.

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 scanned PDF for research analysis?▼

It applies OCR recognition to scanned or image-heavy PDF pages alongside direct text extraction, delivering full document content quickly and avoiding manual transcription for research analysis.

Can I extract text from specific pages in an annual report?▼

Yes, you can target precise sections in an annual report by specifying a page range, allowing selective reading to stay within character limits while extracting the exact text needed.

Does PDF text extraction work with bilingual content?▼

Yes, the OCR extraction process supports bilingual content, pulling text directly from native digital pages and applying OCR to scanned or image-heavy pages to capture the full bilingual document content.

What is the maximum character limit for PDF document reading?▼

The maximum capacity for PDF document reading is 15000 characters, and the system explicitly flags truncation beyond this threshold to ensure you are aware of any cut-off content during extraction.

What is the best way to read a research paper PDF without manual transcription?▼

Automated text and OCR extraction is the best way to read a research paper PDF without manual transcription, allowing you to capture specific sections like the abstract and methodology by targeting page ranges.