identify-page-structure

Identify page structure by detecting section boundaries and content sequences in scraped webpage output. The skill analyzes HTML, screenshots, and metadata to produce a two-level hierarchy mapping sections, describing their content sequences, and listing available blocks for informed authoring decisions.

Section boundaries are top-level divisions based on visual or thematic breaks like background changes and spacing. Content sequences are detailed groupings within each section, such as grids or lists, described neutrally without premature block naming.

Yes. The skill surveys available blocks before authoring decisions are made, providing block inventory context alongside section and content descriptions to guide authentic mapping of content to AEM components.

Use the scrape-webpage workflow to generate cleaned HTML and screenshot output. Feed both artifacts into the identify-page-structure skill along with available metadata to begin two-level structural decomposition.

Headers and footers are excluded from section boundary detection. The skill focuses on primary page content and thematic groupings, using visual cues like spacing and background changes to guide section identification.