A merchant is adding a new range and wants identifiers assigned by rule rather than typed by hand each time. In this case, the immediate task is to generate unique SKUs using a documented naming rule. The workflow should produce an identifier per sellable variant with the rule written down and the output checked for collisions.
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 generate unique SKUs using a documented naming rule.
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: [distinguishing attributes per sellable variant such as product type, option values, size and colour, the naming pattern already in use, the character set and length limit, and existing plus reserved SKUs for collision testing]. Apply one deterministic rule in a fixed attribute order with a stated separator and casing, normalising spaces and accents so the same attributes always produce the same identifier, and flag any variant whose attribute set is incomplete or whose generated value breaches the stated length limit instead of emitting it.
Return generated SKUs with the rule documented and collisions checked 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.
Collect, for one catalogue scope the merchant names, the distinguishing attributes per sellable variant such as product type, option values, size and colour, together with the naming pattern already in use, the character set and length limit an identifier must satisfy, and the full list of existing and reserved SKUs to test collisions against.
Apply one deterministic rule in a fixed attribute order with a stated separator and casing, normalising spaces and accents so the same attributes always produce the same identifier, and flag any variant whose attribute set is incomplete or whose generated value breaches the stated length limit instead of emitting it.
Deliver the generated identifiers next to their variant identifiers with the rule written out and the collision test result, verify that the emitted row count equals the count of sellable variants and that no generated value appears twice, and list every held-back variant with the reason it was not assigned.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Hold the pair for a merchant decision rather than appending a sequence number silently. Auto-numbering hides a data problem in the catalogue, and the second variant needs either a corrected attribute or a merchant-approved suffix recorded alongside the rule.
No. Values that change over time make the identifier unstable and break matching with earlier supplier and inventory records. Encode only attributes describing the physical variant and keep commercial fields in their own columns, so a price change never forces a SKU change.
Compare each generated value against existing SKUs and any reserved identifiers, then review every flagged pair before applying changes. The test must run against the same catalogue state the import will touch, since a value free today can be claimed by an import already queued.
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.