doc-parser

Parse PDFs, Word documents, and images into structured data with docling.

368|75|Updated Jan 29, 2026

Search Tags:#ocr #pdf extraction #document parsing #data structuring #docling #layout analysis

Ready to run

npx skills add https://github.com/claude-office-skills/skills --skill doc-parser

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: doc-parser
Source: https://github.com/claude-office-skills/skills/tree/main/doc-parser
Command: npx skills add https://github.com/claude-office-skills/skills --skill doc-parser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires docling, and includes references (resource) components.

What problem does it solve?

This Skill tackles the challenge of extracting and structuring information from various document formats, including complex PDFs, Word documents, and images, preserving their original layout and content.

Core Features & Use Cases

Advanced Document Parsing: Utilizes the docling library for state-of-the-art document understanding.
Structure Preservation: Maintains the original layout, tables, figures, and multi-column text flow.
Multi-format Support: Handles PDFs (native and scanned), Word documents, images, and HTML.
Use Case: Convert a research paper into structured Markdown, extract all tables from a financial report, or parse an academic paper to identify its title, abstract, sections, and references.

Quick Start

Use the doc-parser skill to convert the attached document 'research_paper.pdf' into structured markdown.

Frequently Asked Questions about doc-parser

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

FAQPage Schema

How do I extract tables from a PDF and preserve the original layout?▼

Document parsing with docling extracts tables from PDFs while preserving the original layout, including multi-column text flow, figures, and structural hierarchy for accurate data output.

Can I parse scanned PDFs and images to get structured text output?▼

Yes, document parsing supports scanned PDFs and images by utilizing OCR and layout analysis, converting visual document content into structured text formats like Markdown.

What is the best way to convert a research paper into structured Markdown?▼

Converting a research paper into structured Markdown requires an advanced parser like docling, which identifies titles, abstracts, sections, and references while maintaining the original document structure.

Does docling support multi-column text flow when extracting content from Word documents?▼

Yes, docling supports multi-column text flow when extracting content from Word documents, ensuring the structural layout is preserved during the document parsing process.

What document formats are supported for advanced layout analysis and data structuring?▼

Supported formats for layout analysis and data structuring include native and scanned PDFs, Word documents, images, and HTML, enabling comprehensive extraction of tables and figures.