How to Write a Shopify Product Description from SKU Facts

Product copy mints a 5-star quote and a bestseller rank. Facts had a 12 oz stoneware mug. Print counts. Leave reviews NOT IN INPUTS.

The matching generator is the Shopify Product Description from SKU Facts (Character Caps, No Invented Reviews) (Shopify Product Description From Sku Facts Character Caps No Invented Reviews) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).

Lock title meta and body caps from Inputs

Write a Shopify product title, meta, and description from SKU facts. Print character counts. No invented reviews or ranks. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.

Paste these fields before you hit run:

SKU facts (title nouns, materials, size, care, handle if any): [Facts]
Title cap: [TitleCap]
Meta cap: [MetaCap]
Body cap (characters): [BodyCap]
Words I must not use: [Banned]
What I must never invent (reviews, ranks, materials, discounts): [Never]
Output format: [Format]
Language: [Lang]
Handle I lock (or UNKNOWN): [Handle]
Price I may print (or UNKNOWN): [Price]

That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.

Quote only SKU facts in the body

Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.

Walk the Generate list in order:

1. Honesty ledger: Facts nouns, TitleCap, MetaCap, BodyCap, Handle, Price, Lang. Forbidden: invented reviews, invented ranks, invented materials.
2. Title under TitleCap with count. Only Facts nouns.
3. Meta under MetaCap with count. No star ratings.
4. Body under BodyCap with count. Short paragraphs from Facts only.
5. Handle: quote Handle or HANDLE UNKNOWN. Do not invent a slug.
6. Price: quote Price or PRICE UNKNOWN. Do not invent a compare-at.
7. Refuse list: review quotes, #1 bestseller, Amazon A+ modules, collection-page clone, invented discounts.
8. Compliance pass: quote Banned and Never hits. Cut them. Print all three counts. Format as Format.

If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.

Refuse invented reviews ranks and discounts

Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.

Honor the constraints as hard stops, not vibes:

• Shopify product copy from Facts only. Not a collection page and not Amazon A+.
• Never invent reviews, ranks, or materials.
• Honor TitleCap, MetaCap, and BodyCap and print counts.
• No emojis.

When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.

Print character counts against every cap

Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.

Tags on the card (shopify product description sku, character caps product copy, no invented reviews) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.

Fill the card, then run

Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.