01
Step 1
Collect the page inventory, rendered headings, metadata fields, the unsorted backlog entries with their claimed evidence, and the merchant's effort scale for fixes.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Find actionable SEO content and metadata issues
A merchant already has a long, unsorted backlog of suspected SEO problems and cannot tell which entries deserve a developer's time this week. In this case, the immediate task is to find actionable SEO content and metadata issues. The workflow should produce a ranked shortlist in which each finding carries its evidence strength, affected URL and fix effort.
Topic
SEO Metadata and Content Audits
Target keyword
shopify seo issue checker
Copyable AI prompt
A prompt you can drop directly into Spark
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.
ai-prompt.txt
Act as a Shopify operations specialist.
Help me find actionable SEO content and metadata issues.
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 page inventory, rendered headings, metadata fields, the unsorted backlog entries with claimed evidence, and the merchant's effort scale for fixes]. Classify each backlog entry as confirmed or unconfirmed against the records the merchant holds, rank confirmed issues by evidence strength and fix effort on the stated scale, and move unchecked assumptions into a separate unconfirmed list naming the check still required.
Return a shortlist of actionable issues with affected URLs, evidence strength and fixes 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.How to solve
A recommended resolution workflow
Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
02
Step 2
Classify each backlog entry as confirmed or unconfirmed against the records the merchant holds, rank confirmed issues by evidence strength and fix effort on the stated scale, and move unchecked assumptions into a separate unconfirmed list naming the check still required.
03
Step 3
Deliver a ranked shortlist with affected URLs, evidence basis and fix effort per finding, then verify every confirmed finding appears in the records and each unconfirmed entry names its missing check.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How does the backlog enter the ranking?
Each backlog entry is first classified as confirmed or unconfirmed against the records the merchant holds, and only confirmed issues are ranked, by evidence strength and fix effort on the stated scale. Unconfirmed entries move to a separate list with the check they still need. This keeps the week's shortlist defensible.
What separates a confirmed issue from an assumption?
A confirmed issue can be pointed to in the records: the field that is empty, the pages that share a title, the heading that is missing. An assumption is a claim with no record behind it yet. The shortlist names the record for every confirmed item, so a developer can verify any line before spending time on it.
What does the shortlist record per finding?
The affected URLs, the evidence and where it sits, the proposed fix, the effort grade on the merchant's stated scale, and the rank position. Unconfirmed items carry the missing check instead of a fix. With those fields a reviewer can challenge any ranking without reopening the whole backlog.
Related scenarios
Continue with adjacent or same-topic scenarios
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Next step
Want these AI scenarios embedded directly into daily operations?
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.