What dependencies are required to run this skill?

The skill uses pypdf, which is automatically managed via 'uv' inline script dependencies for a seamless setup.

Can I use the split files for RAG or LLM context?

Absolutely. Splitting by chapters creates natural semantic boundaries that significantly improve retrieval accuracy in RAG systems and make document management easier in tools like NotebookLM.

Does it handle very large PDF files?

Yes, it includes logic to handle large chapter detection (100+ pages) and prompts for verification to ensure appendices or sub-sections aren't accidentally merged.

How does this skill detect chapter boundaries?

It uses a multi-layered approach: first checking for embedded PDF bookmarks, then scanning the text for common patterns like 'Chapter 1' or 'Section I', and finally allowing the user to verify the proposed boundaries.

Does it work if my PDF doesn't have a Table of Contents?

Yes. If no bookmarks are found, the skill extracts text from the document to identify headers and manually defined TOC listings to suggest split points.

PDF Chapter Splitter

Name: PDF Chapter Splitter
Author: jongwony

byjongwony

0•

콘텐츠 관리

Splits long PDF documents into individual chapter files based on table of contents, bookmarks, or custom text patterns.

The PDF Chapter Splitter skill empowers Claude to intelligently decompose large documents into manageable sections using the pypdf library. It streamlines the document processing workflow by analyzing internal metadata for bookmarks, identifying text-based chapter patterns with regex, and verifying boundary accuracy before execution. This skill is particularly valuable for users needing to prepare granular data for RAG systems, NotebookLM, or structured archival, ensuring that large PDFs are segmented according to their natural semantic structure.

주요 기능

01Regex-based chapter detection (Numbered, Roman Numerals, Part/Section)

02Automated sanitized file naming with index-based prefixing

03Specialized handling for large chapters and missing metadata

04Automatic Table of Contents (TOC) and bookmark extraction

05Interactive boundary verification to ensure precise splitting

060 GitHub stars

사용 사례

01Breaking down massive business reports into individual sections for team distribution

02Segmenting technical documentation for improved retrieval accuracy in RAG systems

03Preparing book chapters as separate sources for AI tools like NotebookLM

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jongwony/cc-plugin pdf-split

For use in Claude.ai and ChatGPT

Download Skill