Churn Prevention
This skill helps reduce voluntary and involuntary churn by designing cancel flows, exit surveys, save offers, and dunning sequences. It produces structured flow designs, email templates, and actionable recommendations to recover lost revenue.
✨ What it does
- Designs a 5-stage cancel flow with copy for each stage.
- Maps exit survey reasons to specific save offers.
- Provides a save offer playbook with when-to-use guidance.
- Sets up smart retry logic and a 5-email dunning sequence.
- Includes metrics benchmarks and red flags for churn tracking.
- Generates win-back email sequences for post-cancel.
🎯 When to use it
- When you need to design a new cancel flow from scratch or optimize an existing one.
- When you want to build save offers that match exit reasons to improve save rates.
- When you need to set up dunning emails and retry logic to recover failed payments.
- When you want to design an exit survey to capture why customers leave.
- When you need to write win-back emails for post-cancel reactivation.
🚀 How to use
Trigger the skill by asking to design or optimize a cancel flow, set up dunning, or create save offers. Provide context such as current churn rate, payment processor, and business model. Example prompts:
Design a cancel flow for my SaaS product.
Set up dunning for failed payments on Stripe.
Audit my current cancel flow and suggest improvements.
📄 Output: Deliverables include flow diagrams, email templates, retry schedules, exit survey designs, and prioritized recommendations.
📦 Add this skill to Claude Code
# 1. Get the skills repo
git clone --depth 1 https://github.com/alirezarezvani/claude-skills /tmp/claude-skills
# 2. Copy this skill into your project (or ~/.claude/skills for all projects)
mkdir -p .claude/skills
cp -r /tmp/claude-skills/marketing-skill/skills/churn-prevention .claude/skills/churn-preventionSkill source: marketing-skill/skills/churn-prevention/SKILL.md
⚠️ Good to know
This skill is not for customer health scoring or expansion revenue; use customer-success-manager for those. It assumes you have access to payment processor details and churn data.
❓ FAQ
What is the recommended save rate benchmark?
A save rate of 10-15% is good, and 20% or more is excellent.
How many retries are recommended in dunning?
The skill recommends up to 4 retries: at day 3, then 5 days later, then 7 days later, and a final attempt 3 days after that.
What should the exit survey ask?
It should ask one required multiple-choice question about the main reason for cancelling, with 6-8 reasons max.
🤖 Overview, features, install steps and FAQ were generated from the project's SKILL.md on Sep 4, 2026. Always check the original source before running commands.