pdf-reader_skill

Overview

This skill reads PDF files and converts their text content into structured Markdown. It preserves page boundaries, extracts tables as Markdown tables, and supports multi-page batch processing. The tool requires the pdfplumber Python package and is designed for use in environments like WSL. It does not perform OCR on scanned images.

How this skill works

The script opens a PDF with pdfplumber, iterates pages, extracts text and table objects, and formats each page into Markdown sections with page headers and a total-pages summary. Tables detected by pdfplumber are converted into Markdown table syntax and inserted under a Tables subsection for that page. File paths can be adapted for WSL by converting Windows-style paths (C:...) into /mnt/c/... before calling the script.

When to use it

• You need a readable Markdown version of a digitally-born PDF (not a scanned image).
• You want page-separated output or page-number references retained.
• You need simple table extraction into Markdown for inclusion in docs or repos.
• You are processing multiple PDFs in bulk and want structured outputs.
• You work in WSL and can run Python scripts with pdfplumber installed.

Best practices

• Ensure pdfplumber is installed (pip install pdfplumber) and Python is configured in your environment.
• Convert Windows paths to WSL paths when running under WSL (C:\ -> /mnt/c/ and backslashes to slashes).
• Split very large PDFs into smaller batches if you encounter memory issues.
• Verify extracted tables and complex layouts manually — complex layouts may be simplified.
• For scanned PDFs, run an OCR step first (OCRmyPDF or pytesseract + pdf2image) before using this tool.

Example use cases

• Convert a policy or guideline PDF into Markdown to publish in a documentation repository.
• Extract contract text and tables for quick review and annotation in Markdown.
• Batch-process a folder of reports to produce per-file Markdown summaries with tables.
• Quickly preview the textual contents of a multi-page PDF while preserving page breaks.
• Prepare Markdown-friendly excerpts from research papers that include simple tables.