- Home
- Skills
- Marketing & SEO
- Win Back Old Customers (RFM Segments Explained Simply)
More screenshots
Works with the AI Agents you already use
Win Back Old Customers (RFM Segments Explained Simply)
Past customers, sorted by how long they've been gone and how much they've spent — each group gets the cheapest offer that can bring them back.
$12
Win Back Old Customers (RFM Segments Explained Simply)
Example session with this skill installed
Process this customer list: name,email,last_purchase,total_spent. John Doe,j.doe@example.com,2023-05-15,650. Jane Smith,jane@test.com,2024-02-10,120. Calculate segments and draft a warm sequence.
- Read your context and instructions
- Compiled the win back old
I have processed the customer list, deduplicated records, and calculated the RFM-lite scores. The VIP cutoff was set at $500. John Doe has been identified as a Dormant VIP (Last purchase > 180 days, Spend > $500), and Jane Smith is categorized as a Recent Buyer.
RFM Analysis and Campaign Draft
| Customer | Segment | Score | Offer | Estimated Value |
|---|---|---|---|---|
| John Doe | Dormant VIP | 68 | 20% Personal Code | $130.00 |
| Jane Smith | Recent Buyer | 85 | Free Shipping | $18.00 |
Segment: Dormant VIP (John Doe)
Tone: Warm
Email 1 (Day 0):
- Subject 1: A personal note from [Business Name]
- Subject 2: We miss your support, John
- Subject 3: A special thank you for your past orders
- Preview: We noticed it has been a while since your last visit on 2023-05-15.
Body: Hi John, we were looking through our records and noticed your total support of $650.00 over the years. We truly value your business. We wanted to send you a personal 20% discount code to use on your next visit.
SMS 1 (Day 3):
Body: Hi John, it's [Business Name]. Just checking if you saw our email? Use your 20% VIP code before it expires this week!
Segment: Recent Buyer (Jane Smith)
Tone: Warm
Email 1 (Day 0):
- Subject 1: A little something for your next order
- Subject 2: Keep the momentum going, Jane
- Subject 3: Free shipping on us
- Preview: Thanks for your recent order. Here is a perk for your next one.
Body: Hi Jane, thanks for shopping with us recently. We want to make your next visit even easier by covering the shipping costs.
Next steps
- Export the segment-specific lists for John Doe (Dormant VIP) and Jane Smith (Recent Buyer).
- Load the day 0 emails into your ESP with the provided merge fields.
- Schedule the day 3 SMS follow-up for the Dormant VIP segment.
Connects securely to your tools. The creator never sees your data.
About this skill
RFM sounds technical and isn't. It means three plain facts about each customer: how Recently they bought, how Frequently, and how much Money they've spent in total. Mailing your whole old list the same discount wastes money twice — your best customers would have come back at full price anyway, and your long-gone ones need more than the offer your regulars get. This skill sorts the list into groups and gives each one the cheapest offer that can move it.
Inside the package: the skill file with the segmentation rules, the scoring, the offer ladder, and the follow-up sequence; a filled example win-back plan; and the segment-and-offer reference. The groups: Champions (recent and high-spending), Recent buyers, At risk (about 3 to 6 months quiet), Lapsed (6 to 12 months), Dormant VIPs (gone over 6 months but big lifetime spend — the group a careless sort buries), Lost (over a year), and Needs info (no usable purchase date — they get a perk, never a guessed discount). The offer ladder runs opposite to instinct: Champions get a free gift and a referral ask, not a discount. Recent buyers get a small perk like free shipping. At risk get 10% off. Lapsed get 15%, this week only. Dormant VIPs get 20% with a personal code, sent like a personal note. Lost get 25% as a last chance, or a short goodbye survey asking what went wrong.
A run goes like this: hand the agent one spreadsheet export — name, email, last purchase date, total spent. It cleans the list first (duplicates out; anyone who unsubscribed, bounced, or complained goes onto a suppression list that is never mailed), scores every customer 0 to 100 from recency, spend, and frequency, and drafts a day 0, 3, 7, 14 email-and-text sequence per group, with copy in one tone and merge fields for name, offer, and last purchase date. Anyone who buys drops out of the sequence immediately. Results are judged on orders and revenue — never open rates — and the same math reruns on the real numbers afterwards. If the actual profit is negative, the fix is a shallower offer or a cleaner list, not a bigger blast.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Marketing & SEO.
Requires CSV headers for name, email, and last purchase date. Percentile calculations require a minimum list size to be statistically meaningful. No direct API integration for sending.
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 buying a skill.
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 6 days ago
- Accounts
ShopifyWooCommerce