doc-parser

Parse PDFs, Word files, slides, images, and HTML into structured markdown and tables.

1|Updated May 18, 2026

Search Tags:#ocr #pdf extraction #tables #document parsing #layout analysis #markdown export

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you convert complex documents into structured, machine-readable output without losing layout, tables, captions, or reading order, which is especially useful when manual copying would be slow and error-prone.

Core Features & Use Cases

Document Parsing: Extract text, headings, tables, figures, and metadata from PDFs, Word files, PowerPoint slides, images, and HTML.
Layout-Aware Analysis: Preserve multi-column reading order and document structure for reports, papers, contracts, and technical docs.
Structured Exports: Produce markdown, plain text, dictionaries, and dataframe-ready table data for downstream processing.
Use Case: Use it to turn a scanned business report into organized sections, extracted tables, and figure captions for analysis or indexing.

Quick Start

Ask the skill to parse your document and return structured markdown, tables, and figure details while preserving the original document layout.

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 and text from complex PDFs while preserving layout?▼

To extract tables and text from complex PDFs while preserving layout, use layout-aware document parsing. This approach maintains multi-column reading order, headings, and figure captions, returning structured markdown and dataframe-ready outputs.

Can I parse scanned images and PowerPoint slides into structured markdown?▼

Yes, you can parse scanned images and PowerPoint slides into structured markdown. OCR-ready processing recognizes text in images and slides, extracting headings, tables, and metadata while preserving the original document structure.

What is the best way to convert technical documents into dataframe-ready table data?▼

The best way to convert technical documents into dataframe-ready table data is through structured document parsing. It isolates tabular data from PDFs and Word files, exporting dictionaries and structured tables without misaligning rows.

Does layout-aware extraction maintain reading order in multi-column reports?▼

Layout-aware extraction does maintain reading order in multi-column reports. By analyzing visual structure, it correctly sequences text blocks across columns, ensuring exported markdown matches the logical flow.

What file formats are supported for structured document parsing and metadata extraction?▼

Supported file formats for structured document parsing include PDFs, Word files, PowerPoint slides, images, and HTML. The process extracts headings, tables, figures, and metadata from these formats.