An agent that studies the top-converting listings in your category and rewrites your titles, bullets, and keywords for each marketplace's rules — draft-ready for a human pass.
The agent pulls the top listings in your category: their titles, bullets, keywords, image order, and review counts.
2
Extract the patterns
What the winners repeat (and what they never say) becomes the brief: keyword set, structure, proof points.
3
Rewrite yours, per marketplace
Amazon, Walmart, and TikTok Shop each get a version written to their rules and character limits — not one text pasted three times.
4
Check against your facts
Every claim is matched to your product docs. Anything it can't source is flagged, never invented.
5
Human pass, then publish
You approve the drafts. The agent queues them; it never publishes unapproved copy.
What it needs
Inputs & tools
Your listingCurrent copy + product docs
Competitor dataFreshCrawl (live data)
RulesPer-marketplace limits
Output3 draft versions
ApprovalHuman publishes
Your time≈ 15 min/listing
A kitchen brand's Walmart title copied its Amazon title — including a keyword Walmart shoppers never search. The rewrite took the category's top Walmart listings as the brief; same product, native copy per channel.
Run this agent yourself
⚡
1 · Get a FreshCrawl subscription
The agent runs on live marketplace data. FreshCrawl plans start free (1,000 credits), paid plans from $29/mo — every plan includes MCP access and an API key. freshcrawl.io →
🔗
2 · Link the MCP to your LLM
In Claude or ChatGPT, add a custom FreshCrawl MCP connector — server crawl.onewally.com/mcp — and paste your FreshCrawl API key. Your LLM can now pull live offers, Buy Box history, and sales estimates itself.
📋
3 · Paste the prompt
Copy the prompt below into your LLM and name your store. The agent runs against the live data it can now reach — no code, no exports.
Copy the prompt
Starter prompt
Step 3 · Paste this into your LLM
# Listing Rewrite
Use the FreshCrawl MCP connected to this chat for all live marketplace data.
MY STORE (fill in once):
- Store name: [your store name]
- Seller ID or storefront URL: [paste it — the agent uses it to find your catalog]
- Marketplace: [Walmart US / Amazon US]
First, use the FreshCrawl MCP to look up my store, pull my catalog,
and work only on my listings. If you can't identify my store from
what I gave you, ask me for my storefront URL before anything else.
RUN SCHEDULE (set this where you run the prompt):
- Run this prompt: on demand per listing; re-check top listings monthly.
- If your LLM app supports scheduled/recurring tasks, set it there; otherwise re-paste the prompt on that cadence.
Here is my current listing and product fact sheet. Pull the top 10
converting listings in this category on each marketplace. Extract
their shared title structure and keyword patterns. Rewrite my
title, 5 bullets, and keyword set separately for Amazon, Walmart,
and TikTok Shop, following each platform's rules. Use only claims
from my fact sheet; flag anything you cannot source.
EXECUTION — READ CAREFULLY:
Drafts only. I review and publish all copy myself — never submit changes to a marketplace.
The prompt gets you the shape. The reliable version runs on live data through the MCP — that's steps 1 and 2 above.
Prices every lost Buy Box in dollars and ranks the fixes worst-first.
Questions sellers ask
Will it stuff keywords?
No — it mirrors the structure of listings that already convert in your category, which is mostly clarity and the right search terms in the right order.
Can it rewrite in bulk?
Yes, one listing at a time with the same brief — bulk runs queue drafts for review; nothing publishes without approval.
What about brand voice?
Give it two or three approved listings as voice samples; drafts are checked against them.
Run this on your store.
Every agent here runs on live FreshCrawl data through the MCP. Start free, connect your LLM, paste the prompt — or get the free Buy Box Loss Report and see the data first.