Analysis Workflow

What this skill does

The Analysis Workflow skill helps you validate that a target webpage contains the data fields your extraction template requires. It walks you through fetching the page content, identifying structured data like Schema.org JSON-LD scripts, meta tags, or HTML selectors, and confirming that these elements reliably map to the variables your project needs. This ensures your template extracts accurate, actionable data rather than failing silently or producing incomplete results.

Who it's for

This skill is ideal for SEO specialists and content marketers who build or maintain data extraction templates for web scraping or content aggregation. Growth leads overseeing automation of content feeds and PPC operators who rely on structured metadata to optimize ads will also benefit. Agencies delivering large-scale data projects need this workflow to validate client pages before scaling extraction across multiple URLs.

Key workflows

First, you fetch a representative page using WebFetch or a DOM snapshot to capture current HTML content. Next, you inspect the page for Schema.org JSON-LD scripts, which provide the most reliable structured data for field mapping. If no schema is found, you check for meta tags in the head section that might hold relevant metadata. Finally, if neither schema nor meta tags are present, you identify and verify CSS selectors against the HTML structure to extract needed information, ensuring the selectors are precise and stable.

Common questions

How do I know if my template variables are valid? Validate them against the JSON-LD schema, meta tags, or verified CSS selectors found on the fetched page. What if required fields are missing in the schema? You may need to supplement with manual entry or prompt variables for those fields. Can I automate template selection based on schema? Yes, you can use the schema type in the triggers array to automatically apply templates when matching structured data is detected.

How to use in Metaflow

Attach this skill to a Metaflow agent task by specifying the target page URL for fetching and analysis. The agent will retrieve the page content and run through the workflow to identify valid data extraction variables, flagging any missing fields compared to your Base requirements. Expect clear feedback on which schema, meta tags, or selectors are usable for your template, helping you refine extraction before deployment. This skill integrates smoothly with other content scraping and validation tasks within Metaflow.

For broader context, see our roundup of claude skills for marketing, and read Claude skills for SEO for related setup guidance.