When should I use the Doc-Splitter skill?

Use it when your documentation source exceeds 5,000 pages or has distinct technical categories that require specialized context for AI agents to remain accurate.

How does it handle errors during the splitting process?

It includes a recovery protocol to pause and diagnose issues like URL pattern overlaps or orphan pages, allowing for manual configuration adjustments before retrying.

What is a 'Router' skill in this context?

A Router skill acts as a central hub that analyzes user queries and directs them to the specific sub-skill containing the most relevant documentation category.

Does this require the skill-seekers CLI?

The workflow is optimized for use with the skill-seekers CLI to automate the estimation, scraping, and routing table generation steps.

Can I split documentation by file count instead of category?

Yes, the skill supports a 'size-based' strategy, which partitions documentation every N pages to ensure uniform distribution regardless of content type.

Documentation Splitter

Name: Documentation Splitter
Author: jmagly

byjmagly

•

콘텐츠 관리

Partitions massive documentation sites into focused, navigable sub-skills with intelligent routing for AI agents.

The Doc-Splitter skill is a specialized utility designed to solve context scaling issues when working with massive documentation sets. It enables users to process documentation sites exceeding 10,000 pages—such as Godot, AWS, or MSDN—by estimating page counts, analyzing category structures, and executing intelligent split strategies. By creating a hub-and-spoke 'Router' architecture, it ensures that Claude can navigate vast technical libraries without overwhelming the context window, providing specialized sub-skills for specific domains like scripting, physics, or networking.

주요 기능

01Multiple split strategies including category, size, router, and hybrid modes

0267 GitHub stars

03Intelligent router generation to automatically direct queries to the correct sub-skill

04Built-in recovery protocols for handling overlaps, orphan pages, and uneven splits

05Automated page count estimation and category boundary analysis

06Parallel scraping support for rapid generation of partitioned knowledge bases

사용 사례

01Organizing enterprise-scale internal wikis into a structured router-based skill hierarchy

02Converting massive game engine documentation into manageable sub-skills for AI agents

03Partitioning cloud infrastructure docs (AWS/Azure) to optimize DevOps automation context

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jmagly/ai-writing-guide doc-splitter

For use in Claude.ai and ChatGPT

Download Skill