skills.rest
claude-office-skills
claude-office-skillsOFFICIAL
Explore all skills by this author →
GitHub

data-extractor

Extract structured text, tables, and metadata from PDF, DOCX, HTML, and email documents.

368|75|Updated Jan 29, 2026
Search Tags:#data extraction#pdf#rag#text extraction#document parsing#unstructured
One-click install
npx skills add https://github.com/claude-office-skills/skills --skill data-extractor-claude-office-skills
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-extractor
Source: https://github.com/claude-office-skills/skills/tree/main/data-extractor
Command: npx skills add https://github.com/claude-office-skills/skills --skill data-extractor-claude-office-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the extraction of structured data from various document formats, including PDFs, Word documents, emails, and HTML, simplifying data retrieval and processing.

Core Features & Use Cases

  • Universal Document Parsing: Processes a wide range of file types using the unstructured library.
  • Structured Data Output: Extracts text, tables, and metadata into organized formats like JSON or DataFrames.
  • Use Case: Automatically parse a collection of mixed-format documents (PDFs, DOCX, emails) to extract key information and compile it into a searchable corpus for RAG applications.

Quick Start

Use the data-extractor skill to extract all text and tables from the document 'report.pdf'.

Frequently Asked Questions about data-extractor

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

FAQPage Schema
How do I extract structured data from PDF and DOCX files for RAG ingestion?▼

To extract structured data for RAG ingestion, you can parse PDFs, DOCX, HTML, and emails into organized JSON formats. This process categorizes document elements like text and tables, making the output directly usable for retrieval systems.

What is the best way to parse unstructured PDF documents into JSON?▼

The best way to parse unstructured PDF documents into JSON is using a universal document parsing library like unstructured. It automatically categorizes text, tables, and metadata from diverse formats into structured outputs.

Does the unstructured library support extracting tables from HTML and email formats?▼

Yes, the unstructured library supports extracting tables and text from HTML and email formats. It processes a wide range of file types to categorize elements for document analysis and content summarization.

Can I compile mixed-format documents into a searchable corpus for AI applications?▼

Yes, you can compile mixed-format documents into a searchable corpus for AI applications. The tool parses collections of PDFs, DOCX, and emails to extract key information for RAG systems.

What are the limitations of automated text extraction from diverse document formats?▼

Limitations of automated text extraction depend on the unstructured library's parsing capabilities for complex layouts. While it handles diverse document formats like PDF and DOCX, highly irregular structures may affect categorization accuracy.

Related Skills

Explore More Software Engineering Skills→
tomique34tomique34
8

tmq-markdown2anything

Convert markdown files to styled PDF, DOCX, or HTML documents.

Community
Intermediate
mupengi-botmupengi-bot
11

rag-engineer

Design RAG systems with embedding models, vector databases, and retrieval optimization.

Community
Advanced
voidrotvoidrot

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications.

Community
Advanced
xberg-ioxberg-io
26

extracting-with-ocr

Extract machine-readable text from scanned PDFs and images using OCR engines.

Official
Advanced