benchmark-analysislisted

# The Benchmark Check Take one metric the user cares about and tell them, honestly, whether it is good, average, or concerning relative to a real reference point, stated clearly, never a confident-sounding number this skill invented on the spot. > **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. Confirm the user's metric is defined the same way as the benchmark's before comparing: tax and shipping inclusion, and what counts as an order, differ between sources and account for most apparent gaps. > 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