Skill market 7 skills

Tear the competitor listing you pasted in (title + bullets + per-image notes + price + rating / review count + image count) into a title formula, bullet structure, image narrative, price band and review velocity, then tier your own keyword list and compute competitor coverage

Run your listing text and the compliance ledger you filled in yourself against the 19 GPSR / PPWR / EPR / WEEE / battery law / claims clauses one by one, and grade each one "must fix / should fix / needs a human"

Run four checks before you list — high-risk words in your copy, risk baked into the category, the documents your supplier is missing, and whether you can use the images — and get an action list sorted P1/P2/P3. If a complaint, a law firm letter, or a court filing actually arrives, it only triages the type

Split an exported keyword list into five buying-intent tiers — core / scene / attribute / longtail / negative — then turn it into ad groups and a negative keyword list you can set up as written.

Two periods of operating data plus this period's action list go in; five things come out: metric-change attribution with hypotheses still to be validated, threshold alerts with a troubleshooting order, a one-page three-part review, three experiments with pass / fail / negative decision lines, and reusable lessons.

Sourcing data tells you how well it sells; only reviews tell you why people buy and why they send it back.

Actually crawls PDP / robots.txt / sitemap; six findings anyone can re-check