01
Step 1
Export current SKUs with product and variant identifiers, inventory quantities, the supplier codes already attached and the naming convention the merchant wants applied.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Prepare a reversible bulk SKU correction file
A merchant has settled on one naming convention, but the catalogue still holds years of ad-hoc SKUs and a careless import would break variant matching. In this case, the immediate task is to prepare a reversible bulk SKU correction file. The workflow should produce an old-to-new mapping with a rollback column and rows needing confirmation marked.
Topic
SKU Generation and Cleanup
Target keyword
shopify bulk edit skus
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 prepare a reversible bulk SKU correction file.
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: [current SKUs with product and variant identifiers, inventory quantities, attached supplier codes, and the naming convention the merchant wants applied].
Build one old-to-new mapping row per variant while holding the variant identifier fixed so every row stays traceable, and mark for merchant confirmation any row where the convention is ambiguous, where two variants would produce the same new value, or where the new value already exists elsewhere in the catalogue.
Return a reversible correction file with a rollback column 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
Build one old-to-new mapping row per variant while holding the variant identifier fixed so every row stays traceable, and mark for merchant confirmation any row where the convention is ambiguous, where two variants would produce the same new value, or where the new value already exists elsewhere in the catalogue.
03
Step 3
Deliver a correction file carrying the old value, the new value and a rollback column holding the original, verify that the row count equals the exported variant count and that no new value appears twice, and list the excluded variants with the reason each was left out.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why include a rollback column?
A rollback column lets the merchant restore the earlier identifiers if a downstream system rejects the update or stock lands against the wrong variant. The boundary is that rollback only works while the old values are also written to the file, so never import a stripped version.
Can SKUs change while orders are still open?
Prefer a window with no open movement, because open orders and pending supplier documents keep referencing the old identifier. Where that is impossible, freeze the affected variants, run the import, and reconcile open orders against the mapping before fulfilling anything.
Which rows should be left for manual confirmation?
Any row where the convention is ambiguous, where two variants collide on the new value, or where the new value already exists elsewhere. Those need a merchant decision, and the file carries them as unconfirmed rows rather than dropping them silently.
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.