pdf-toc-splitter
CommunitySplit large PDFs into structured, bookmark-preserving chunks.
Authorberad217
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Large PDFs are difficult to process, read, or ingest into AI systems due to their size, and manual splitting often loses document structure and bookmarks, making the resulting chunks hard to navigate.
Core Features & Use Cases
- Structure-aware splitting: Split PDFs using their existing table of contents/bookmarks, inferred headings, fixed page counts, or manual break points.
- Editable slice plans: Refine split boundaries by editing a simple JSON plan, enabling recursive subdivision of large sections without re-analyzing the full document.
- Bookmark preservation: Each output chunk retains its relevant bookmarks, rebased to start at page 1 for easy navigation.
- Use case example: Split a 2000-page industry standard into chapter-level PDFs for team reference, or break a large research paper into sections for RAG pipeline ingestion.
Quick Start
Use the pdf-toc-splitter skill to split the attached large PDF 'technical-manual.pdf' into chapter-sized chunks with preserved bookmarks.
Dependency Matrix
Required Modules
pymupdf
Components
assets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: pdf-toc-splitter Download link: https://github.com/berad217/human-training/archive/main.zip#pdf-toc-splitter Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 536,000+ vetted skills library on demand.