Nobody has reviewed the published collections as a set, so vague copy and overlapping pages go unnoticed. In this case, the immediate task is to audit collection pages for search-intent alignment. The output should be an inventory with each page scored against its stated intent, noting where copy, overlap or missing products weaken it.
First replace every [bracketed] placeholder with real store scope and constraints, then add any actual records or data you have, and paste it into your preferred AI assistant or Spark agent. Spark will follow this page's workflow to produce structured output and verification steps.
Act as a Shopify operations specialist.
Help me audit collection pages for search-intent alignment.
My store context is [describe the business, products and target audience].
My scope is [specify the affected products, pages, customers or reporting period]. Use these inputs: [the store's own collection index as the source list, with each collection's URL, title element, meta description, opening copy, product count, included products, index status and inbound internal links]. Score each page against the single buyer intent it claims to serve, downgrading pages whose product set does not serve that intent, whose copy repeats another page or inherited template boilerplate, or whose included products are missing or unavailable, recording the specific reason for each downgrade.
Return a collection-level SEO brief and revised copy with the audit findings checked against the merchant's records for the specified task.
Show the relevant evidence or before-and-after examples and explain how I can verify the result.
If essential data is missing, ask for it and mark unsupported conclusions as unknown.
Do not invent metrics, product claims or customer facts.
For any publication, message, account or store change, use only connected tools within my explicitly authorized scope and report success only after verification; otherwise provide the draft or proposed steps.Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
Inventory every published collection using the store's own collection index as the source of the list, recording its URL, title element, meta description, opening copy, product count, included products, index status and the internal links pointing at it.
Score each page against the single buyer intent it claims to serve, downgrading pages whose product set does not serve that intent, whose copy repeats another page or inherited template boilerplate, or whose included products are missing or unavailable, recording the specific reason for each downgrade.
Deliver a collection-level SEO brief carrying revised copy and one recommended action per URL, reconcile the inventoried URL count against the store's published collection list so nothing is skipped, and separate pages needing copy edits from those needing a scope change.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
By checking three things together: the products included really serve the claimed intent, the copy states it in the shopper's words, and nothing else in the store targets the same term. Missing any one is recorded as a downgrade with the reason named, never as a bare score.
As a downgrade tied to the other URL carrying the same wording, rather than as a rewrite task alone. Two pages sharing a paragraph usually means two pages competing for one intent, so the scope question must be settled before new copy is drafted for either.
Only when the page cannot serve the intent it claims. A narrow collection with clear copy and complete product data passes, while a larger collection whose included products are all unavailable fails because there is nothing left for the shopper to buy.
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Ciwi Spark builds Shopify-native AI tools and agents around the workflows merchants actually run: research, ads, translation, and customer support. Stop rewriting the same prompts by hand.