# Win back quiet customers

A found skill by Anthropic.

Finds customers who have gone past their own normal buying rhythm, ranks them by what they were worth to you, and drafts a personal win-back message for each one.

Task: Sales and quotes
Works with: Claude, ChatGPT, Gemini
Tools: Claude
Difficulty: Intermediate
Country: United States

Use this when you want to reach out to customers who stopped buying.
Skip this if you want this sent or published without you.

Credit: Anthropic
Source: https://github.com/anthropics/knowledge-work-plugins/tree/main/small-business/skills/reactivate
Licence: Apache 2.0 (repo LICENSE)

## Skill text

Please turn the text below into a reusable skill. If you are Claude, save it as a skill. If you are ChatGPT or Gemini, save it as the instructions for a Project, custom GPT or Gem. If you cannot save skills, just follow these instructions now.

Name: Win back quiet customers (short version)

Description: Use this when I want to reach out to customers who stopped buying.

Ask me for:
1. My customer list with order dates and amounts.
2. What I can offer, if anything, such as a discount or just a check-in.

Steps:
1. For each customer, work out how often they usually buy.
2. List the ones who are well past their own usual gap, ranked by past value.
3. Flag anyone who left a bad review or asked for a refund before going quiet.
4. Let me remove anyone I do not want to contact.
5. Draft a short message for each, based on what they actually bought.

Output: A ranked list of quiet customers and a draft message for each.

Rules: Never invent an offer I have not agreed to. Do not send anything until I approve each message.

The full original skill by Anthropic, with more detail, is free on GitHub under the Apache 2.0 licence: https://github.com/anthropics/knowledge-work-plugins/tree/main/small-business/skills/reactivate

## More

- [This skill as a web page](https://agentstories.org/skills/win-back-quiet-customers.html)
- [All skills, as a Markdown list](https://agentstories.org/skills.md)
- [Skills directory](https://agentstories.org/skills/)
