Listings & SEO · Podcast episode · source Oct 19, 2026
Listing Rewrite and Wasted-Spend Audit with Claude and the Helium 10 MCP
Rebuild a declining listing around proven keywords and find ad spend your rules miss
“found 41 keywords that had brought at least five sales each”
Per source From a vendor-affiliated source (see Worth knowing), not independently verified.
Copy-paste prompt
Check my advertising campaigns. If in the last 12 months, look back period. There are any search terms or ASINs in auto or broad campaigns that have more than 20 clicks, but no sales. Give it to me in a table that shows which campaigns are in how many clicks, how much spend.
This prompt is quoted or closely adapted from the original source. Replace anything in [brackets].
What they did
Helium 10's head of education connected Claude to the Helium 10 MCP on accounts he runs. For a children's workbook whose Search Query Performance impressions fell from 160,000 to 9,600 in a year, a custom Claude skill combined 12 months of SQP, current and historical Cerebro rankings for four competitors and 26 weeks of Brand Analytics, scored each keyword with his own formula, and wrote a listing that answers the Alexa questions shown on his and a competitor's page. He then ran audit prompts on the ad account with a 12-month lookback, to catch targets that never trip a 30- or 60-day rule because they collect a few clicks at a time.
How it went
The SQP step found 41 keywords that had brought at least five sales each in 12 months, and the scoring showed he was nowhere in search for about 80 percent of the keywords bringing sales to his competitors. On ads, the 60-day prompt found $146 across four search terms with no sales in about two minutes; the 12-month version took him close to the $10,000 of wasted spend he set out to find, and another prompt found nine targets above 100% ACOS with $815 of spend.
We only report what the source says. Results are self-reported unless noted.
Worth knowing
A Helium 10 employee demonstrating Helium 10's MCP. The rewritten listing hadn't gone live and the ad savings are projected, not measured. Both ideas work with exports too: score keywords by proven sales across sources, and audit ads over a long lookback.