identify-page-structure

Identify section boundaries and content sequences in scraped webpages for AEM Edge Delivery Services import.

1|Updated Jun 22, 2026
One-click install
npx skills add https://github.com/aemgdc/aemdev --skill identify-page-structure-aemgdc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: identify-page-structure
Source: https://github.com/aemgdc/aemdev/tree/main/.agents/skills/identify-page-structure
Command: npx skills add https://github.com/aemgdc/aemdev --skill identify-page-structure-aemgdc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When importing an existing webpage into AEM Edge Delivery Services, you need a structured understanding of the page before making authoring decisions. This Skill analyzes scraped webpage output (screenshot, HTML, metadata) and breaks it into a two-level hierarchy of sections and content sequences, so downstream skills can map content to blocks accurately. ## Core Features & Use Cases - Section Boundary Detection: Examines the full-page screenshot to find visual and thematic breaks such as background color changes, spacing shifts, and dividers, while excluding headers, footers, and cookie banners. - Content Sequence Analysis: For each section, identifies vertical flows of related content (default content or blocks) with neutral descriptions, deferring block naming to later authoring steps. - Block Inventory Survey: Catalogs local project blocks and available Block Collection blocks with purposes and example URLs before any authoring decisions are made. - Use Case: During a site migration, you scrape a legacy marketing page and use this Skill to produce a structured outline (e.g., light hero section, grey card grid section, dark tabs section) that the authoring-analysis skill then converts into concrete AEM block choices. ## Quick Start Analyze the scraped webpage output in this workspace and identify its section boundaries, content sequences, and available blocks for AEM import.

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 section boundaries in a scraped webpage?▼

Examine the full-page screenshot for visual cues like background color changes, spacing shifts, horizontal dividers, and thematic content shifts. Exclude headers, footers, and cookie banners since those are auto-populated during AEM import.

What is a content sequence in AEM page import?▼

A content sequence is a vertical flow of related content within a section that becomes either default content (headings, paragraphs, lists) or a block. Sequences break whenever content changes from default to block or between different block types.

What input does this page structure analysis require?▼

It requires output from a prior webpage scrape: a full-page screenshot.png, a cleaned.html file with page content, and a metadata.json file with paths. Without these artifacts the two-level analysis cannot run.

Should I assign block names during structure identification?▼

No. Describe content neutrally, such as "grid of items with images" rather than "Cards block". Block selection happens later in the authoring-analysis step after surveying the available block inventory.

Why survey available blocks before making authoring decisions?▼

Surveying local blocks and Block Collection blocks first mirrors how real authors work with a block library. It ensures downstream authoring choices map to blocks that actually exist in the project or can be added.