Extract PDF book content into chapterized Markdown with metadata.
npx skills add https://github.com/NoiseMeldOrg/skills --skill extract-book
Please help me install this Agent Skill. Skill: extract-book Source: https://github.com/NoiseMeldOrg/skills/tree/main/skills/extract-book Command: npx skills add https://github.com/NoiseMeldOrg/skills --skill extract-book
This skill converts PDFs of books into well-structured Markdown with chapters, metadata blocks, and cleaned text.
Convert a PDF book into structured Markdown with chapters, metadata, and clean text.
High-intent search queries and answers about installing and using this skill.
PDF book-to-Markdown conversion uses pdfplumber for text extraction and heuristic chapter detection to produce navigable, multi-chapter Markdown outputs. It automatically builds metadata blocks and cleaned text sections.
Chapter detection during PDF text extraction identifies structural boundaries using multiple strategies including text markers, single-number markers, named sections, and table of contents analysis. This multi-strategy approach ensures reliable multi-chapter Markdown outputs for long-form books.
Image-only PDF pages that cannot be OCRed are handled through an optional vision pass using pypdfium2 for image rendering. This creates image-rendered placeholders within the Markdown, ensuring an end-to-end extraction workflow.
Automatic metadata extraction for long-form PDF books captures title, author, publisher, ISBN, and copyright information. This metadata is embedded directly into the structured Markdown output as clean metadata blocks alongside chapterized text content.
The best way to structure long-form manuals into searchable Markdown is applying heuristic chapter detection with pdfplumber text extraction. This produces clean, navigable documents with per-chapter sections and metadata blocks suitable for long-term reference.
Missed chapters in PDF-to-Markdown extraction often occur when chapter markers rely on non-standard formatting. This skill mitigates that by combining multiple heuristic detection strategies—text markers, single-number markers, named sections, and TOC-based detection—for reliable boundary identification.
Unson-LLCExtract PDF text by page using Python's pdfplumber library.
mcclowesParse Markdown into an AST and render it to HTML per CommonMark.
eatbreadsExtract logged-in Xiaohongshu posts into markdown files with OCR.
anilcan-karaExtract text from PDFs and scanned documents using pymupdf or marker-pdf.
