pdf-extraction

Extract text, tables, citations, and metadata from PDF documents.

33|10|Updated Apr 30, 2026

Search Tags:#ocr #pdf #citations #metadata #extraction #tables #grounded-context

Ready to run

npx skills add https://github.com/andreaswasita/copilot-cowork-dojo --skill pdf-extraction-andreaswasita

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf-extraction
Source: https://github.com/andreaswasita/copilot-cowork-dojo/tree/main/skills/pdf-extraction
Command: npx skills add https://github.com/andreaswasita/copilot-cowork-dojo --skill pdf-extraction-andreaswasita

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

PDF documents often explode into chaotic, unusable text. This skill extracts text, tables, citations, forms, and metadata from PDFs to provide grounded context for downstream Copilot work such as research synthesis, memos, or summaries.

Core Features & Use Cases

Classify native vs scanned PDFs and identify sections for extraction.
Pull metadata (title, date, author, jurisdiction) and structure data for reuse.
Extract sections, tables, and quotes in a structure-preserving format, supporting encrypted or hybrid documents and large packs.
Produce outputs suitable for subsequent skills like research-synthesis, decision-memo, or document-summarization.

Quick Start

Extract all text, tables, and metadata from the provided PDF to create grounded context for downstream tasks.

Frequently Asked Questions about pdf-extraction

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

FAQPage Schema

How do I extract structured text and tables from a PDF for research synthesis?▼

To extract structured text and tables from a PDF, this skill parses native and image-based documents while preserving their original structure. It identifies sections, pulls metadata like title and date, and formats the output specifically for downstream research synthesis and memo generation.

Can I pull metadata and citations from scanned PDFs?▼

Yes, you can pull metadata and citations from scanned PDFs. The skill classifies documents as native or scanned, applies OCR for image-based files, and extracts titles, dates, authors, and jurisdictions to provide grounded context for due-diligence workflows.

What is the best way to extract data from encrypted or restricted regulatory filings?▼

The best way to extract data from encrypted or restricted regulatory filings is using a skill that explicitly flags access limitations. This tool processes hybrid documents and large packs, preserving tables and quotes while identifying restricted content that cannot be parsed.

How do I extract data from PDF contracts without losing the document structure?▼

You can extract data from PDF contracts without losing structure by using a skill designed to preserve formatting. It pulls sections, tables, and quotes into a structure-preserving format, ensuring the grounded context remains intact for subsequent document summarization.

Does this PDF extraction approach work for large packs of hybrid documents?▼

Yes, this PDF extraction approach works for large packs of hybrid documents. It processes mixed native and scanned files, preserves structural elements like tables and forms, and flags any encrypted content to ensure reliable extraction across entire document sets.