skills.rest
zerwiz
zerwizCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text and structured content from PDFs, scans, and DOCX files.

1|Updated Apr 10, 2026
Search Tags:#ocr#pdf#markdown#tables#document extraction#scanned documents
One-click install
npx skills add https://github.com/zerwiz/wayofpi --skill ocr-and-documents-zerwiz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/zerwiz/wayofpi/tree/main/.hermes/hermes-agent/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/zerwiz/wayofpi --skill ocr-and-documents-zerwiz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires marker-pdf, pymupdf, pymupdf4llm, and includes scripts (resource) components.

What problem does it solve?

This Skill turns PDFs, scans, and office documents into readable text, saving you from manual copy-paste and OCR cleanup.

Core Features & Use Cases

  • Remote document extraction: Pull markdown from URLs first when a document is available online.
  • Local PDF parsing: Use lightweight text extraction for normal PDFs and richer OCR for scanned or layout-heavy files.
  • Office document support: Handle DOCX directly and defer PPTX to the dedicated presentation workflow.
  • Use case: Convert a batch of research papers, invoices, or scanned reports into text, tables, and metadata for review or downstream automation.

Quick Start

Ask the skill to extract clean text and tables from the attached document 'scanned-report.pdf' and return the result in markdown.

Frequently Asked Questions about ocr-and-documents

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

FAQPage Schema
How do I extract text and tables from a scanned PDF document?▼

To extract text and tables from a scanned PDF, you need OCR and layout recovery. This Skill uses marker-pdf to perform OCR on scanned documents, recovering structured content, tables, and images, and returns the result in markdown format.

Can I extract markdown from a PDF available at a remote URL?▼

Yes, you can extract markdown from a remote URL. The Skill applies a web extraction method to pull document content directly from online sources, converting it into usable text without requiring a local download.

What is the best way to convert research papers and invoices into markdown?▼

The best way to convert research papers and invoices into markdown is using a tool that handles complex layouts. This Skill processes local text-based PDFs with pymupdf and applies marker-pdf for OCR-heavy files to extract structured text and metadata.

Does this document extraction method support DOCX files?▼

Yes, this document extraction method supports DOCX files directly. It handles office documents alongside local PDFs and scanned documents, deferring PPTX files to a dedicated presentation workflow.

Why does my PDF text extraction return misaligned or missing tables?▼

PDF text extraction returns misaligned tables when using lightweight parsing on layout-heavy files. This Skill solves that by applying marker-pdf for OCR and layout recovery, accurately extracting structured tables and images from complex documents.

Do I need OCR for normal text-based PDFs?▼

You do not need OCR for normal text-based PDFs. This Skill uses lightweight local parsing via pymupdf for standard text extraction, reserving heavier OCR processing via marker-pdf for scanned or layout-heavy documents.

Related Skills

Explore More Education & Research Skills→
attentiondotnetattentiondotnet

ocr-and-documents

Extract text from PDFs, DOCX, PPTX, and scanned documents via OCR.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

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

Official
Intermediate
zhangzhang-111-izhangzhang-111-i
2

rag-architect

Designs RAG pipelines with chunking, embedding, retrieval, and evaluation strategies.

Community
Advanced
afel6afel6

ocr-and-documents

Extract text and structured content from PDFs and scanned documents.

Community
Intermediate