Customer Service & Retention AI

Churn Prevention

Churn Prevention is an ecommerce AI skill for Alireza Rezvani, built for teams working with Codex, Claude Code, OpenClaw. Use it to you are handling recurring…

Provider
Alireza Rezvani
Platforms
Codex · Claude Code · OpenClaw
View original link · GitHub

What this skill helps you do

Addresses both voluntary churn (customers who decide to leave) and involuntary churn (failed payment cancellations) with three operational modes: building a cancel flow from scratch, optimizing an existing flow, and setting up dunning sequences. Implements a 5-stage cancel flow (trigger → exit survey → dynamic save offer → confirmation → post-cancel) with reason-matched offers including discounts, pauses, downgrades, extended trials, feature unlocks, and human support. Includes a dunning setup with smart retry logic (retries at days 3, 8, 15, 18), card updater service integration, a 5-email dunning sequence, and a churn impact calculator for modeling recovery potential.

Install and get started

Copy the full instructions into your AI tool. Test one low-risk example before connecting real store data.

Original Skill instructions

You are a SaaS churn prevention expert. Three modes: (1) Build Cancel Flow—5-stage: Cancel Trigger (visible, no dark patterns), Exit Survey (one required MC question, 6-8 reasons), Dynamic Save Offer (match reason: discount→price objection, pause→seasonal, downgrade→light usage, feature unlock→missing feature, human support→complexity), Confirmation (clear consequences), Post-Cancel (day-0 confirmation, day-7 re-engagement, day-30 win-back). (2) Optimize Existing—audit against benchmarks (save rate 10-15% good, 20%+ excellent; survey completion >80%). (3) Dunning—smart retries (days 3/8/15/18), card updater services, 5-email sequence neutral→urgent. Track save rate, churn rates, recovery rate weekly. Run churn_impact_calculator.py to model MRR recovery.

Useful tasks

  • Designing a cancel flow from scratch for SaaS products with no retention funnel
  • Auditing existing cancel flows for save rate optimization and exit survey improvements
  • Setting up dunning email sequences and smart retry logic for payment recovery
  • Mapping exit survey reasons to dynamic save offers for higher retention rates
  • Modeling churn impact and estimating monthly MRR savings from improved retention

How to use it

  • Match save offers to exit reasons—a generic discount signals pricing was fake
  • Make the exit survey one question, required, with 6-8 options—aim for >80% completion
  • Failed payment retries should wait 3 days; most recoveries happen in that window
  • Track win-back rate in the 7-day post-cancel window—it's the highest-recovery moment
  • If churn exceeds 5% monthly, flag for product/ICP review alongside retention work

More skills for this workflow

Content checked: