agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/churn-win-back/SKILL.md

churn-win-back

Skill13 starsChanged 22 days agoMITView on GitHub

Use this skill when you want former customers back: \"win back churned customers\", \"re-engage cancelled accounts\", \"churn win-back campaign\", \"which lost customers should we call\". Sorts churned accounts by why and when they left, picks the ones worth winning back, finds what changed since (product, pricing, their situation), and writes a short, honest win-back sequence with the right offer for each churn reason. Produces a prioritised win-back list, messages and the rules for when to leave an account alone.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this for customers who cancelled in the last 3 to 24 months.

    line 16
  2. Distinctive:

    Every message names the reason they left and the specific change.

    line 52
  3. Distinctive:

    MUST check the churn reason before writing.

    line 59
  4. Distinctive:

    MUST respect opt-outs and data-retention promises made at cancellation.

    line 60
  5. Distinctive:

    NEVER claim a fix that has not shipped.

    line 61
  6. Distinctive:

    NEVER discount by default.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Use this for customers who cancelled in the last 3 to 24 months. Former customers already know the product and the problem; the question is whether the reason they left still holds.

Inputs

  • Churned accounts: churn date, plan and value, the stated reason, who the champion was, usage in the last 90 days before churn.
  • What changed since: features shipped, pricing or packaging changes, support improvements.
  • Current signals at those accounts: new leaders, growth, hiring, funding.

The play

1. Group by real churn reason

ReasonTypical evidenceWin-back angle
Missing featureTicket or request for it"The thing you needed now exists"
Price or budgetDowngrade attempts, finance involvedNew plan, smaller package, annual terms
Low adoptionFew active users, onboarding never finishedGuided restart, done-with-you setup
Champion leftMain user departed before churnNew owner, fresh onboarding
Switched to a competitorSaid so in the exit callCheck in near their contract renewal
Business changeDownsizing, pivot, acquisitionOnly if the situation reversed

2. Prioritise

Score each account: past value, how far they got (active users, outcomes), whether the churn reason is now fixed, and whether a new trigger exists. Start with accounts where the reason is fixed and a trigger fired.

3. Time it

  • Feature or price reasons: as soon as the fix ships.
  • Competitor switch: 9 to 11 months after churn, ahead of their renewal.
  • Low adoption: 3 to 6 months later, with a new owner if possible.

4. Write short and honest

Name the reason they left, say what changed, offer one easy step back. Never pretend the relationship ended well if it did not. Read references/win-back-messages.md for messages by churn reason.

5. Make returning easy

A clear path: data restored if retained, a short guided restart, a fair price. Ask what would need to be true for it to work this time.

What good looks like

  • Every message names the reason they left and the specific change.
  • Accounts that churned for reasons nothing has fixed are left alone.
  • Returners get an onboarding plan, so they do not churn twice for the same reason.
  • The common mistake is a blanket "We miss you! Here's 20% off" email to every former customer, which ignores why they left and trains people to churn for discounts.

Rules

  • MUST check the churn reason before writing.
  • MUST respect opt-outs and data-retention promises made at cancellation.
  • NEVER claim a fix that has not shipped.
  • NEVER discount by default; match the offer to the reason.

Example prompts

  • "Here are 85 accounts that churned last year with reasons. Who should we win back and how?"
  • "We just shipped the integration 12 churned customers asked for. Write the win-back emails."
  • "Plan a quarterly win-back play for customers who left for a competitor."

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free