skills.rest
Gozei
GozeiCOMMUNITY
Explore all skills by this author →
GitHub

pdf-ocr

Convert scanned PDFs to editable DOCX using Baidu OCR with Chinese support.

Updated Aug 23, 2026
Search Tags:#ocr#pdf#word#docx#image-preservation#baidu-ocr
One-click install
npx skills add https://github.com/Gozei/ClawX --skill pdf-ocr-gozei
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-ocr
Source: https://github.com/Gozei/ClawX/tree/main/resources/custom-skills/pdf-ocr
Command: npx skills add https://github.com/Gozei/ClawX --skill pdf-ocr-gozei

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, python-docx, pillow, and includes scripts (resource) components.

What problem does it solve?

PDF scanned documents often exist only as images; this skill converts them into editable Word text using OCR, cropping headers/footers, preserving images and handling cover pages as images.

Core Features & Use Cases

  • OCR-based conversion of scanned PDFs to Word documents with Chinese OCR support
  • Automatic header/footer cropping and image preservation, including color cover pages
  • Use case: digitizing paper archives, research papers, and contracts to enable editing and search

Quick Start

Run the pdf_to_docx.py script on your scanned PDF to generate an OCR’d Word document

Frequently Asked Questions about pdf-ocr

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

FAQPage Schema
How do I convert scanned PDF to Word with OCR?▼

To convert a scanned PDF to Word, run the provided script which applies Baidu OCR to extract text and outputs an editable DOCX file with images preserved and headers cropped.

Does this PDF OCR conversion support Chinese text extraction?▼

Yes, Chinese OCR is fully supported. The skill leverages the Baidu OCR API to accurately extract Chinese text from scanned PDF documents into editable Word format.

Can I digitize contracts and academic PDFs while preserving images?▼

Yes, you can digitize contracts and academic PDFs because the OCR process preserves images and handles color cover pages, cropping headers and footers to output a clean DOCX.

Do I need to pay for the Baidu OCR API to digitize paper archives?▼

No payment is required initially because the skill uses the Baidu OCR API with a free quota, allowing you to digitize paper archives into editable Word text without immediate cost.

What is the best way to crop headers and footers when converting PDF to DOCX?▼

The best way to crop headers and footers during PDF to DOCX conversion is using this skill, which automatically removes them during the OCR process to ensure clean text extraction.

Are color cover pages processed as images or text during scanned PDF OCR?▼

Color cover pages are processed and preserved as images during the scanned PDF OCR conversion, ensuring visual integrity while extracting the editable text from the document body.

Related Skills

Explore More Content & Communication Skills→
peteromalletpeteromallet
97

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

Community
Advanced
jiunbaejiunbae
12

document-processor

Extract and convert text, tables, images, and metadata across PDF, DOCX, XLSX, PPTX formats.

Community
Advanced
jdrodriguezjdrodriguez
6

ocr

Extract text from scanned PDFs and images using OCR.

Community
Advanced
lenadlmlenadlm

ocr-and-documents

Extract text from PDFs and scanned documents using OCR engines.

Community
Advanced