The same specification is written several ways across the catalog, so buyers cannot compare two listings. In this case, the immediate task is to complete and standardize product specifications. The workflow should produce an enriched product data draft where every value follows one agreed format and unit, and conflicting specifications are listed apart.
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 complete and standardize product specifications.
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 specification values recorded per product, the target specification schema and per-category required attributes, the agreed naming and unit conventions, and supplier sheets carrying the same attributes]. Rewrite every value into the agreed attribute name, unit and number format, closing gaps only where a merchant-supplied source states the value, and flagging products whose records disagree on one attribute, whose value cannot be expressed in the required unit without an assumption, or whose category marks the attribute required while no source supplies it.
Return an enriched product data draft with unresolved fields 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 specification values recorded per product, the target specification schema with the attributes required for each category, the naming and unit conventions the merchant has adopted, and any supplier sheets carrying the same attributes.
Rewrite every value into the agreed attribute name, unit and number format, closing gaps only where a merchant-supplied source states the value, and flagging products whose records disagree on one attribute, whose value cannot be expressed in the required unit without an assumption, or whose category marks the attribute required while no source supplies it.
Deliver an enriched draft in which each attribute carries one name, unit and format across the whole catalog, accompanied by a conflicts list showing every competing value with its source and an unresolved list of open fields, then sample-check the rewritten values against the merchant's own records and confirm no value exposed to filters was lost.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Both values are kept visible in a conflicts list with the record each came from, and neither is written over the other. Picking the more plausible one produces a catalog nobody can audit, whereas supplier material usually settles it quickly once the contradiction is shown with both sources attached.
Not for scarcity alone. Requirements are stated per category, so an attribute few products carry may still be mandatory for them, and dropping it removes the only comparative detail in that niche. Conversely, an optional attribute nobody can source is better left empty than filled with approximations.
It can, which is why a sample is reviewed before wide application. The record keeps full precision and consistent units while the storefront may shorten or restate them, so trimming happens at the presentation layer only and never removes detail stored in the catalog itself.
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.