AgentConversion

Product page conversion analysis

High traffic, low conversion — and whether it's a page problem or a pricing problem. With a fix prescribed for each.

Works with
ClaudeChatGPTAny MCP-compatible AI tool
Requires
StoreHero MCPShopify
Get the prompt
Example chat in Claude. You ask: "Run the Product page conversion analysis agent for the last 30 days". Claude reads your StoreHero data and answers: Email and search pull your conversion rate up. Paid social traffic converts below its intent tier. It adds an interactive example chart, Conversion rate by traffic source, with example data you can switch below.
Conversion rate by traffic sourceExample

Example, Last 30 days: Store conversion rate 2.6%

  • Email4.8%
  • Google search3.2%
  • Meta1.4%
  • TikTok0.7%

Email: High intent and converting well. Grow the list.

The prompt

How to run it

Paste it into a new chat in Claude or ChatGPT and you get the answer straight away.

Use the StoreHero MCP to do the following analysis. Always anchor the answer in real StoreHero data, not platform-reported metrics.

Run a product page conversion analysis for the last 30 days. Pull the website analytics page from StoreHero with product-level performance — sessions, add-to-cart rate, conversion rate, revenue, and gross profit per order — for each product page.

Find product pages with high traffic but underperforming conversion. Specifically look for two failure patterns and treat them differently:

1. High sessions, low add-to-cart rate — typically signals a product page problem. The visitor was interested enough to land on the page but didn't put it in the cart. Likely causes: weak imagery, poor product description, missing reviews, lack of trust signals, sizing/fit concerns, unclear value proposition. Recommend a creative or content-led fix.

2. High sessions, healthy add-to-cart rate, but low overall conversion rate — typically signals a pricing or delivery/checkout issue. The visitor wanted the product but bailed before completing. Likely causes: shipping cost surprise, delivery time too slow, payment options limited, perceived total cost too high, returns policy unclear. Recommend a commercial or checkout fix.

Filter out low-volume noise — apply a minimum session threshold (suggest 200 sessions or 1% of total product page traffic, whichever is lower) before flagging a product as a problem.

Cross-reference each flagged product against StoreHero product profitability data. A product with poor conversion that's also low-margin is a deprioritise candidate; a product with poor conversion but strong margin and good repeat purchase rate is a high-priority fix because every percentage point of CR recovered drops to the bottom line.

For each product flagged, give a specific recommendation labelled either "Page-level fix" or "Commercial fix".

At the bottom of your answer, render an inline visual summary: a scatter plot of product pages with sessions on the x-axis, conversion rate on the y-axis, and dot size = gross profit per order. Highlight outliers (high traffic, low CR, high margin) with traffic-light colour. Add KPI cards for biggest revenue-recovery opportunity, biggest margin-recovery opportunity, and the median product page CR. Place text commentary alongside the visuals. Use the Spend Advisor tool to suggest what to explore next.

Get the full prompt

Enter your email to see every prompt in full and copy it in one click. It unlocks the whole library.

See our privacy policy.

How to use a skill

New to skills? It takes three steps and a few minutes: connect StoreHero once, copy a skill into Claude or ChatGPT, and ask.

  1. Connect StoreHero to Claude or ChatGPTAdd the StoreHero MCP connector once. It works with Claude, ChatGPT and any other tool that supports MCP. Setup guide
  2. Pick a prompt and copy it into ClaudeOpen one, press Copy prompt (or download the file) and paste it into a new chat.
  3. AskIt pulls your live StoreHero data and gives you the analysis in minutes. Ask follow-up questions in the same chat.

Run every prompt on your own numbers.

Connect your store to StoreHero and the whole library works on your live profit data.