Generate Google Product Schema Code From Your Product Data
Wrong or missing schema code quietly blocks your product from showing star ratings and price in Google, and that visibility loss goes unnoticed for months. This prompt turns the product info you already have into ready-to-paste, verifiable code, no guesswork, no made-up fields.
You are an experienced technical SEO specialist. Your job is to generate valid Product schema (JSON-LD) code from the product information I give you. Never invent data. Use only what I provide; if a field is missing, leave it out of the code entirely and call out separately which field is missing. Generate the schema code using the following information: [Product Name]: [Description]: [Image URL]: [Price]: (number, no currency symbol) [Currency]: (USD) [Stock Status]: (In stock / Out of stock) [Brand]: (if available) [SKU]: (if available) [Average Rating and Review Count]: (if available) Output: 1. Valid JSON-LD code, ready to drop straight into your HTML. 2. A short note under the code listing which fields are missing and how filling them in would strengthen the schema. 3. The name of Google's Rich Results Test tool, for you to validate the code.
How to use it
- Use it to auto-generate schema code the moment you publish a new product page.
- Use it to refresh an existing product page's schema with current data (price, stock).
- Use it to rebuild the schema from scratch once you notice a schema error cost you a rich result.
Example / tip
A candle maker enters the product name, price, and stock status, and leaves the brand field blank. The output produces valid JSON-LD and adds a note underneath: 'brand field is missing, add it and you'll also start showing up in Google's brand filters.'
Usage example
Copy the prompt as is, fill in the bracketed fields for your own business, and paste it into ChatGPT or Claude. The more concrete your input, the more useful the output. Take the first draft, ask for a one-sentence fix on whatever you don't like, then give it a final pass in your own voice.
When not to use it
Don't force it if you have no real input to work with. A prompt doesn't fill an empty field with data, it organizes and speeds up what you already know. Never publish the output unchecked; AI sometimes produces a claim that sounds right but is wrong or made up. Always verify anything that needs proof yourself: numbers, prices, guarantees.
Output quality checklist
- Is the output specific to your input, or generic filler that fits any business? If it's generic, run it again with more concrete input.
- Does every number, ratio, or claim have something backing it? Delete the unbacked ones or soften them honestly.
- Does it sound like you? Simplify the cliches and inflated lines in your own voice.
- Does it give one clear next step? If the reader knows what to do, the output did its job.
