Structure Extraction Skill

Extract document structure patterns and save reusable templates to rules/structure/.

2|Updated Oct 23, 2025
One-click install
npx skills add https://github.com/boringdata/kurt-demo --skill structure-extraction-skill
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Structure Extraction Skill
Source: https://github.com/boringdata/kurt-demo/tree/main/_archived/structure-extraction-skill
Command: npx skills add https://github.com/boringdata/kurt-demo --skill structure-extraction-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill analyzes content to identify consistent document structures (section flow, headline patterns, content organization) and saves them as structure templates in rules/structure/ for use in content creation projects.

Core Features & Use Cases

  • Pattern Discovery: Identify common section orders, heading patterns, and content layouts.
  • Template Creation: Save reusable structure templates under rules/structure/.
  • Incremental Updates: Refine templates over time as new content is analyzed.

Quick Start

  • Auto-discover structure for tutorials and API references: invoke structure-extraction-skill --type tutorial --auto-discover invoke structure-extraction-skill --type api-reference --auto-discover
  • Provide specific documents to extract structure: invoke structure-extraction-skill with documents: <file-paths>

Frequently Asked Questions about Structure Extraction Skill

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

FAQPage Schema
How do I extract document structure patterns to create reusable templates?

Structure extraction analyzes your documents to identify consistent section flows, heading patterns, and content organization, then saves these patterns as templates in rules/structure/ for reuse across new content. Requires 3-5 substantial documents in /sources/ or accessible paths.

What content types can I analyze for structural patterns?

You can extract structure from tutorials, API references, landing pages, blogs, guides, and case studies. The Skill identifies common organizational patterns across these document types and creates templates applicable to similar content.

How do I get started with auto-discovering document structure?

Use auto-discover mode by invoking the Skill with a content type: invoke structure-extraction-skill --type tutorial --auto-discover or --type api-reference --auto-discover. The Skill scans your documents and generates structure templates automatically.

Can I update templates incrementally as I add new content?

Yes, the Skill supports incremental template refinement. Analyze new documents over time to refine existing templates in rules/structure/, with options for manual selection, auto-discovery, and overwrite control for template updates.

What should I do if pattern matching fails during content creation?

Structure extraction helps when rule matching fails by re-analyzing your content corpus to identify missed patterns or edge cases. Run the Skill on updated documents to discover overlooked structural patterns and refine your templates.