skills.rest
stsrjkt-bit
stsrjkt-bitCOMMUNITY
Explore all skills by this author →
GitHub

pdf-splitter

Split multi-subject science PDFs into per-subject documents with Gemini page classification and human review.

Updated Aug 27, 2026
Search Tags:#education#pdf#split#science#classification#human-in-the-loop#boundary
One-click install
npx skills add https://github.com/stsrjkt-bit/claude-plugins --skill pdf-splitter-stsrjkt-bit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-splitter
Source: https://github.com/stsrjkt-bit/claude-plugins/tree/main/kakomon-university-rebuild/skills/pdf-splitter
Command: npx skills add https://github.com/stsrjkt-bit/claude-plugins --skill pdf-splitter-stsrjkt-bit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill splits multi-subject science PDFs (physics, chemistry, biology, earth science) into per-subject documents and ensures accurate page boundary handling without relying on misleading cover or footer page numbers.

Core Features & Use Cases

  • Human-in-the-loop boundary verification: Gemini classifies all pages and a reviewer confirms and fixes boundaries before final split.
  • Per-subject split output: Generates separate PDFs for each subject with optional answer sheets where applicable.
  • Review pack and decision guide: Provides a review workflow and guidance to correct misclassifications and edge cases.
  • Use case: Ideal for university entrance exam bundles that combine science subjects and social studies, where consistent page structuring is inconsistent.

Quick Start

Run the pdf-splitter on your multi-subject science PDF and verify the page boundaries before finalizing the splits.

Frequently Asked Questions about pdf-splitter

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

FAQPage Schema
How do I split a multi-subject science PDF into separate documents by subject?▼

Splitting multi-subject science PDFs involves classifying each page by subject (physics, chemistry, biology, earth science) and identifying correct boundaries to generate separate per-subject PDFs. This process handles mixed bundles and ignores misleading cover page numbers.

What is the best way to handle inconsistent page structuring when splitting university entrance exam bundles?▼

Handling inconsistent exam bundles requires per-page classification to correctly identify subject boundaries, bypassing misleading cover or footer page numbers. It accommodates variable placement of answer sheets and mixed subject bundles for accurate partitioning.

Can I manually verify PDF page boundaries before finalizing a subject-specific split?▼

Yes, a human-in-the-loop review workflow allows you to verify and correct page boundaries before finalizing the split. A review pack and decision guide are provided to help correct misclassifications and edge cases.

How does automated per-page classification work for mixed science PDFs?▼

Automated per-page classification uses Gemini-based AI to analyze and categorize each page of a mixed science PDF by subject. This classification handles blank pages and cover pages before outputting per-subject PDFs and a review bundle.

Does the PDF splitting process handle blank pages and variable answer sheet placement?▼

Yes, the PDF splitting process handles blank pages, cover pages, and the variable placement of answer sheets within the document. It ensures these elements do not disrupt the accurate identification of subject boundaries.

Related Skills

Explore More Education & Research Skills→
jinyhjinyh
19

nsfc_i2_revision

Parse NSFC review comments and generate six-section revision reports with literature-backed edits.

Community
Advanced
Ikram-AlamIkram-Alam

evaluation

Evaluate agent outputs against rubrics and ground truth with multi-dimensional scoring.

Community
Basic
jaredcroxtonjaredcroxton

nano-pdf

Edit PDF text on a specified page using natural-language instructions.

Community
Basic
andy4917andy4917

pdf

Create, render, and extract content from PDF files using reportlab, pdfplumber, and pypdf.

Community
Intermediate