ecommerce-seo is a store audit workflow for AI agents, covering WooCommerce, Shopify, Magento and custom platforms. It collects the store URL and platform, picks representative category and product pages, and inspects them because store templates repeat.
It works through five areas: faceted navigation and crawl budget, category pages, product pages, structured data and a final report with an e-commerce SEO score, a count of junk-indexed URLs and a 30-day plan.
What You Get
- An e-commerce SEO score for the store
- An estimate of the crawl-budget leak as a count of junk-indexed URLs
- Handling advice for filter, sort and pagination URLs
- Findings on thin product pages, variants and out-of-stock handling
- Top fixes ranked by impact and effort, plus a 30-day plan
Common Use Cases
- Finding out why filter URLs are showing up in Google
- Reviewing product and category templates on a WooCommerce or Shopify store
- Deciding what to do with out-of-stock and discontinued products
- Checking Product and Offer markup before chasing rich results
What Makes It Unique
It treats faceted navigation as the main leak in store SEO and quantifies it with a count of junk-indexed URLs, with concrete options: canonical filtered variants to the clean category, noindex follow on low-value combinations, or robots rules for pure sort parameters. Its product-page rules cover keeping ranking out-of-stock products live with availability marked, and redirecting dead SKUs to a category or replacement.
Under The Hood
The skill is a short wrapper whose SKILL.md tells the agent to read a longer WORKFLOW.md in the seo folder of the same repository and follow it. The workflow is prose only and ships no scripts. It has the agent fetch store pages from the public web, read a shared preamble file, and optionally pull queries, pages and index coverage from Search Console through a connected capability. It never publishes changes to a live site without an explicit yes, hands schema creation to the schema markup skill, and treats fetched pages as untrusted data.