pdf-extraction

Extract text, tables, and metadata from PDFs into Markdown.

1|Updated Apr 20, 2026
One-click install
npx skills add https://github.com/IndianBoy42/dot-opencode --skill pdf-extraction-indianboy42
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf-extraction
Source: https://github.com/IndianBoy42/dot-opencode/tree/main/skills/pdf-extraction
Command: npx skills add https://github.com/IndianBoy42/dot-opencode --skill pdf-extraction-indianboy42

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mistralai, pdfplumber, pymupdf4llm, pytesseract, pdf2image, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

PDF documents often contain valuable text, tables, and metadata that are hard to extract, summarize, or repurpose, especially when dealing with scanned files requiring OCR.

Core Features & Use Cases

  • Extract text, tables, and metadata from PDFs, and convert content to Markdown for easy ingestion by LLMs and RAG pipelines.
  • Support for both text-based PDFs and scanned documents with OCR options, enabling accurate data extraction across formats.
  • Domain-specific extraction capabilities can be combined with dedicated modules like datasheet-extraction and paper-extraction for specialized workflows.

Quick Start

Run the default extraction to convert a PDF into Markdown text that can be fed into downstream AI workflows.

Frequently Asked Questions about pdf-extraction

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

FAQPage Schema
How do I extract tables and text from PDFs for RAG pipelines?

You can extract tables and text from PDFs for RAG pipelines by converting the document content into structured markdown. This approach uses Python tools like pymupdf4llm and pdfplumber to generate deterministic outputs suitable for downstream LLM ingestion.

Can I extract text from scanned PDFs using OCR?

Yes, you can extract text from scanned PDFs using OCR capabilities powered by pytesseract and pdf2image. This allows the extraction process to accurately handle image-based documents and convert them into searchable markdown text.

What is the best way to convert PDF to markdown for LLM ingestion?

The best way to convert PDF to markdown for LLM ingestion is using a deterministic extraction tool that parses text, tables, and metadata. Relying on libraries like pymupdf4llm ensures the output is structured as chunks suitable for AI workflows.

Does pdfplumber support extracting metadata alongside tables?

Yes, pdfplumber supports extracting metadata alongside tables and text from PDF documents. The extracted information is then converted into markdown, ensuring both data and document properties are available for downstream processing.

Why does PDF extraction fail on scanned documents without OCR?

PDF extraction fails on scanned documents without OCR because the content consists of images rather than embedded text layers. Applying OCR through pytesseract and pdf2image is required to recognize and extract the text from these image-based files.

Can I use this PDF extraction approach for domain-specific documents?

Yes, you can use this PDF extraction approach for domain-specific documents by combining it with dedicated modules like datasheet-extraction and paper-extraction. These specialized workflows handle unique formatting requirements for technical datasheets and research papers.