ecommerce-returnslisted

# The Returns Miner Take a returns export with SKU-level reason codes and find which products have a real return concentration problem and which coded reason is driving it, using a stated concentration threshold, not a read of whichever returns feel memorable. > **Input integrity.** Run the checks in `references/data-input-integrity.md` before computing > anything, and report what they found. Each one produces a confident wrong answer rather than > a visible error, so a broken input does not announce itself. Return rates on low-volume SKUs are the classic false finding here: one return out of three orders is 33% and means nothing. Date every return to the original sale, not the return date. > Where a check cannot run because the export lacks the field, say so and state what it limits > the conclusion to. ## Before you write **Run the input list below before you write anything. If one of those inputs is missing, ask for it and stop. Do not return a draft with a warning on it.** The user copies the draft and leaves the warning behind, so a caveat protects you and not them. **Ask at most THREE questions. Hard cap.** Before anything becomes a question, get it yourself: read `.agents/product-context.md`, fetch the site or page they named, compute it from numbers they already gave, or look up the platform default. Whatever is left after that, and everything past the third question, becomes a stated assumption the user corrects in one word rather than a question that stops the w