identify-page-structure

Identifies section boundaries and content sequences within scraped webpages for AEM import.

Updated Feb 15, 2026
One-click install
npx skills add https://github.com/Permit-Junction/permitjunction-website --skill identify-page-structure-permit-junction
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: identify-page-structure
Source: https://github.com/Permit-Junction/permitjunction-website/tree/main/.claude/skills/identify-page-structure
Command: npx skills add https://github.com/Permit-Junction/permitjunction-website --skill identify-page-structure-permit-junction

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill analyzes scraped webpage content to identify distinct sections and the sequence of content within each section, preparing it for structured import into AEM Edge Delivery Services.

Core Features & Use Cases

  • Section Boundary Detection: Visually identifies and categorizes top-level sections based on layout and thematic changes.
  • Content Sequence Analysis: Breaks down each section into logical content sequences, distinguishing between default content and potential blocks.
  • Block Inventory Survey: Catalogs available AEM blocks to inform authoring decisions.
  • Use Case: After scraping a competitor's landing page, use this Skill to understand its structure (e.g., hero section, feature grid, testimonial carousel) before recreating it in AEM.

Quick Start

Analyze the provided HTML and screenshot to identify page sections and their content sequences.

Frequently Asked Questions about identify-page-structure

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

FAQPage Schema
How do I identify page sections and content sequence from scraped HTML for AEM import?

To identify page sections for AEM import, this Skill analyzes scraped HTML and screenshots to detect section boundaries using visual cues, then maps the content flow within each section. It outputs a structured representation of the page hierarchy and available blocks.

What is the best way to map webpage structure for AEM Edge Delivery Services?

The best way to map webpage structure for AEM Edge Delivery Services is using a two-level analysis: first detecting section breaks from layout changes, then cataloging content sequences and available AEM blocks within each section to guide authoring decisions.

Does webpage section detection require both HTML and screenshots to find section boundaries?

Yes, webpage section detection uses both HTML and screenshots to identify section boundaries. The Skill relies on visual cues from screenshots to categorize top-level sections, then parses the HTML to analyze the content flow within each distinct boundary.

Can I catalog available AEM blocks from a competitor's scraped landing page?

You can catalog available AEM blocks from a scraped landing page by invoking the block inventory function during content sequence analysis. It distinguishes between default content and potential blocks, informing your authoring decisions when recreating the page structure.

How does content sequence analysis distinguish between default content and AEM blocks?

Content sequence analysis distinguishes default content from AEM blocks by invoking decomposition and block inventory skills within each detected section. It breaks down the logical content flow to separate standard elements from cataloged block components.

Why does scraped webpage structure analysis separate section detection from content flow mapping?

Scraped webpage structure analysis separates section detection from content flow mapping to ensure accuracy. It first establishes top-level section boundaries from visual layout cues, then independently analyzes the internal content sequence within each isolated section.