skills.rest
tapway
tapwayOFFICIAL
Explore all skills by this author →
WebsiteGitHub

document-processing

Extract text from PDFs and scans via OCR and edit PDF text using natural language prompts.

1|Updated Jun 21, 2026
Search Tags:#ocr#document processing#pdf#text extraction#pymupdf#marker-pdf#pdf editing
One-click install
npx skills add https://github.com/tapway/shogun-os --skill document-processing-tapway
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: document-processing
Source: https://github.com/tapway/shogun-os/tree/main/skills/general/document-processing
Command: npx skills add https://github.com/tapway/shogun-os --skill document-processing-tapway

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Working with PDFs often means choosing between multiple extraction and editing tools without clear guidance. This Skill provides a decision framework for extracting text from PDFs and scanned documents, and for editing existing PDF text, typos, and titles. ## Core Features & Use Cases - Text Extraction: Extract text from PDFs and scans using liteparse (default), pymupdf (lightweight fallback), or marker-pdf (high-quality OCR for complex layouts). - PDF Text Editing: Edit existing PDF text, fix typos, and update titles via natural language prompts using the nano-pdf CLI. - Use Case: You receive a scanned contract PDF and need its text for review, then must fix a client name typo on page 2. Use marker-pdf for OCR extraction, then run nano-pdf to change the name and produce an edited PDF. ## Quick Start Extract the text from the attached scanned report.pdf and then fix the typo 'Recieved' to 'Received' on page 1.

Frequently Asked Questions about document-processing

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

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

Use liteparse with OCR enabled (lit parse document.pdf) or marker-pdf for scanned documents, since both include built-in OCR. pymupdf only works on text-based PDFs and cannot read scanned images.

How do I edit text in an existing PDF?▼

Use the nano-pdf CLI with a natural language instruction, for example: nano-pdf edit file.pdf 1 "Change the title to 'Q3 Results'". It outputs an edited PDF; always verify the result afterward.

liteparse vs pymupdf vs marker-pdf for PDF extraction?▼

liteparse is the default: fast, ~10MB, with built-in OCR and markdown output. pymupdf is a lightweight fallback for simple text PDFs. marker-pdf (~3-5GB with PyTorch) handles complex layouts, equations, and heavy batch OCR.

Can I extract text from a PDF hosted at a URL?▼

Yes, try web_extract on the URL first, which converts PDFs to markdown via Firecrawl with no local dependencies. Use local extractors only for local files, failures, or batch processing.

Why did nano-pdf edit the wrong page?▼

Page numbers may be 0-based or 1-based depending on the nano-pdf version. If the edit hits the wrong page, retry with the page number adjusted by plus or minus one.

Related Skills

Explore More Personal & Entrepreneur Skills→
Aum08DesaiAum08Desai

ocr-and-documents

Extract text and structured data from PDFs, scans, and images.

Community
Intermediate
peteanderson80peteanderson80

pdf

Extract and summarize content and structure from PDF documents.

Community
Intermediate
mjunaidcamjunaidca
27

working-with-documents

Automate creation, editing, and conversion of DOCX, PDF, and PPTX documents.

Community
Advanced
photonics-dhlphotonics-dhl

ocr-and-documents

Extract text and structured data from PDFs and documents using OCR and parsing tools.

Community
Intermediate