Several products need whole option grids built at once, and the merchant cannot confirm every pairing exists in the range. In this case, the immediate task is to create missing variants from valid option combinations. The workflow should produce a variant matrix and precise change list counting what each product gains and dropping unsupported pairings.
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 create missing variants from valid option combinations.
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 target products with their handles and identifiers, the option names and values each declares, the supplier-confirmed list of combinations that exist, the variants already present with their SKUs, and the price and inventory fields the merchant supplied].
Build the allowed combination matrix from the confirmed list only, diff it against the variants already present to produce the missing set per product, and hold back any row that duplicates an existing variant, carries no SKU where the merchant tracks inventory per combination, or has no price supplied.
Return a variant matrix and precise change list, with a per-product count of variants to be created 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 the target products with their handles and identifiers, the option names and values each declares, the supplier-confirmed list of combinations that exist, the variants already present with their SKUs, and the price and inventory fields the merchant supplied.
Build the allowed combination matrix from the confirmed list only, diff it against the variants already present to produce the missing set per product, and hold back any row that duplicates an existing variant, carries no SKU where the merchant tracks inventory per combination, or has no price supplied.
Deliver a variant matrix and precise change list with a per-product count of variants to be created, then confirm that the rows created for each product equal the missing count from its matrix and that every held-back pairing appears with the reason it was excluded.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
It is matched on the full option value set and on the SKU where one is recorded, then marked as present and left out of the creation list. Creating it again would produce two variants for one purchasable item, so the matrix names the existing variant against that combination instead of adding a row.
The product is held out of the run and reported, because a combination inferred from the option grid may not exist in the supplier's range and cannot be fulfilled once sold. It returns to the list once the merchant supplies the confirmed combinations, and the report records what is missing rather than guessing it.
The change list is grouped per product with its own count so a partial result can be traced, and products with held-back rows can be applied separately from the clean ones. Applying everything as one block hides which product produced a mismatch, and the per-product counts are what make the result checkable afterwards.
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.