identify-page-structure

Detect top-level sections and content sequences in scraped webpage outputs.

Updated Jan 16, 2026

Search Tags:#authoring #analyze #web-scrape #sections #page-structure #content-sequences

Ready to run

npx skills add https://github.com/treeves/ak-test --skill identify-page-structure-treeves

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: identify-page-structure
Source: https://github.com/treeves/ak-test/tree/main/.skills/identify-page-structure
Command: npx skills add https://github.com/treeves/ak-test --skill identify-page-structure-treeves

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Identify the hierarchical structure of a scraped webpage by detecting top-level sections and the content sequences within each section, enabling consistent authoring decisions in AEM Edge Delivery workflows.

Core Features & Use Cases

Two-level analysis: detect sections (level 1) and content sequences within each section (level 2).
Interoperability with other skills: can invoke page-decomposition for per-section sequencing and consult block-inventory for available blocks.
Prerequisites: relies on scraped webpage outputs (screenshot, cleaned.html, metadata.json) and is typically invoked by the page-import orchestrator.
Use Case: Prepares a scraped page for authoring by outlining sections and sequences to guide templating and layout decisions.

Quick Start

Run the identify-page-structure skill against a scraped output (screenshot.png, cleaned.html, metadata.json) to produce a structured map of 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 sections and content sequences in a scraped webpage?▼

Identify page structure by running the skill against scraped outputs (screenshot, cleaned HTML, metadata) to detect top-level sections and content sequences within each section, producing a hierarchical map for authoring decisions.

What inputs does page structure analysis require?▼

Page structure identification requires scraped webpage outputs: screenshot.png, cleaned.html, and metadata.json. These outputs typically come from web-scrape results and are often processed through the page-import orchestrator.

Can I use page structure analysis with AEM Edge Delivery workflows?▼

Yes. Page structure analysis prepares scraped pages for AEM Edge Delivery authoring by outlining sections and content sequences to guide templating and layout decisions in your workflow.

How does two-level analysis work for web content mapping?▼

Two-level analysis detects sections at level 1, then invokes page-decomposition to analyze content sequences within each section at level 2, creating a structured map for downstream authoring.

What other skills can work together with page structure identification?▼

Page structure identification interoperates with page-decomposition for per-section sequencing and block-inventory to survey available blocks, enabling coordinated analysis across your authoring pipeline.