- Home
- Skills
- E-commerce
- customer retention, rfm & win-back finder
More screenshots
Works with the AI Agents you already use
customer retention, rfm & win-back finder
Drop in a Shopify, Etsy, Square or any orders CSV: get monthly cohort retention, repeat rate, RFM segments and a prioritised win-back list of lapsed customers with revenue at stake.
$6.99
About this skill
Winning back a customer costs a fraction of finding a new one. Find out who to email this week.
Export your orders (it auto-detects common Shopify, Etsy and Square headers, and --col maps Stripe, WooCommerce or anything else). The tool groups orders by customer and builds a monthly cohort retention table. It computes repeat-purchase rate, time to second order, average order value and revenue per customer, scores everyone on Recency, Frequency and Monetary value, and sorts them into segments: Champions, Loyal, Potential loyal, New, Needs attention, At risk, Can't lose, Hibernating and Lost. It then produces a win-back list ranked by the revenue at stake, each with a suggested message angle, which you can export as a CSV for your email tool.
Built for small-business growth: it turns an export you already have into a list of actions for this week.
What it does
- Monthly cohort retention table and repeat-purchase rate
- RFM scoring (1-5) and 9 named segments with counts and revenue
- Median days to second order (use it to time your follow-up email)
- Win-back list ranked by lifetime value at risk, with a message angle per segment
- CSV export for Klaviyo, Mailchimp or Shopify Email, plus JSON
Who it's for
Small e-commerce and DTC owners, Etsy sellers and agencies running retention for clients.
Limits
Customers are identified by email or customer ID, so guest checkouts with different emails count as separate people. Decision support from your own data, not legal, tax or financial advice. Follow CAN-SPAM, GDPR and similar email rules when you contact customers.
What's included
- SKILL.md: workflow, commands, how to explain results
- scripts/: the tool (standard-library Python)
- references/: sources
- examples/: sample inputs used in the demo (all made up)
- tests/: unit tests (Python 3.8 / 3.9 / 3.13)
Standard-library Python only. No API keys, no network calls, no installs.
Customers are identified by email or customer ID, so guest checkouts with different emails count as separate people. Decision support from your own data, not legal, tax or financial advice. Follow CAN-SPAM, GDPR and similar email rules when contacting customers.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today