Create advanced Works with: Claude, Gemini, ChatGPT

Product Data Cleanup for Variants and Attributes (JSON)

Json output Needs file upload / long context Has example

Turn messy product data into consistent structured records.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Clean and structure product data for upload. Platform requirements: [PLATFORM_REQUIREMENTS]. Messy source data (one product per line, or a table): [PASTE_PRODUCT_DATA].

Return valid JSON only: an array where each item has "sku", "title" (Title Case, brand first if supplied), "parent_sku" (or null), "variant_attributes" (object with normalized keys such as color, size, material), "price" (number, currency stated in a separate "currency" key), "weight_g", "dimensions_cm" (object with l, w, h), "category_path" (array), "short_description" (max 160 characters), "tags" (array of up to 8), and "issues" (array of strings describing anything missing, ambiguous, or inconsistent).

Rules: normalize units (convert inches to centimeters, ounces to grams, show original in "issues" when converted); standardize color names; mark guesses with "issues" entries rather than inventing data; use null for missing values; do not merge items unless the SKU pattern clearly shows variants.

After the JSON, write a plain-text list of the five most common data problems you found and a rule I can apply to prevent them.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Claude, Gemini, ChatGPT or another assistant.

[{"sku": "TS-001-BLK-M", "title": "Cotton T-Shirt, Black, M", "parent_sku": "TS-001", "variant_attributes": {"color": "Black", "size": "M"}, "price": 19.9, "currency": "EUR", "weight_g": 180, "dimensions_cm": {"l": 70, "w": 50, "h": 1}, "category_path": ["Clothing", "T-Shirts"], "short_description": "Soft cotton T-shirt with a relaxed fit.", "tags": ["cotton", "t-shirt"], "issues": ["Weight converted from 6.3 oz to 180 g", "Color 'blk' normalized to 'Black'"]}]
Common data problems: mixed units (3 rows), inconsistent color names (12 rows), missing weight (5 rows). Rule: a data entry template with required fields and dropdown lists.

• catalog