Systems Lab

Agent skill

retention-churn-prevention

Customer retention analysis, churn prediction, cohort analysis, win-back campaigns, and loyalty program design.

slowingSelf-containedActs undeclared569 words

Filed under Onboarding, retention and expansion.

From thatrebeccarae/claude-marketing · 42 skills · 119 · pushed 2026-05-14

What it does when it runs

Customer retention analysis, churn prediction, cohort analysis, win-back campaigns, and loyalty program design. Use when the user asks about churn, retention, customer lifetime value, cohort analysis, or win-back strategies.

Read from the skill and the 3 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files
shell

Ask about retention-churn-prevention

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/thatrebeccarae/claude-marketing.git /tmp/claude-marketing
git -C /tmp/claude-marketing sparse-checkout set "skills/retention-churn-prevention"
mkdir -p ~/.claude/skills/retention-churn-prevention
cp -R "/tmp/claude-marketing/skills/retention-churn-prevention/." ~/.claude/skills/retention-churn-prevention/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from thatrebeccarae/claude-marketing/blob/a8a63ec1341f05ec9c1e9cb52b4edeb14e3bdcba/skills/retention-churn-prevention/SKILL.md, which is licensed MIT (skill frontmatter). 569 words, 14 headings.

Retention & Churn Prevention

Analyze churn, predict at-risk customers, and design retention strategies.

Install

git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/retention-churn-prevention ~/.claude/skills/

Churn Analysis Framework

Churn Types

TypeDefinitionSignal
VoluntaryCustomer actively cancelsCancellation request, downgrade
InvoluntaryPayment failure, card expiryFailed charge, dunning
SilentStops using but does not cancelUsage decline, no logins

Churn Rate Calculation

Monthly churn rate = Customers lost / Customers at start of month
Annual churn rate = 1 - (1 - monthly rate)^12
Net revenue retention = (Start MRR + Expansion - Contraction - Churn) / Start MRR

Benchmarks

MetricExcellentGoodConcerning
Monthly churn (SaaS)<1%1-2%>3%
Annual churn (SaaS)<5%5-10%>15%
Net revenue retention>120%100-120%<100%

Customer Health Scoring

SignalWeightHealthyAt Risk
Product usage25%Daily/weeklyMonthly or less
Feature adoption20%5+ features1-2 features
Support sentiment15%Positive/noneNegative
Billing health15%On time, expandingLate, downgrading
Engagement15%Opens, clicksIgnores
NPS/CSAT10%Promoter (9-10)Detractor (0-6)

Early Warning Signals

TimeframeSignalAction
7 daysLogin frequency drops 50%+In-app nudge, value reminder
14 daysKey feature usage stopsCS outreach, usage tips
30 daysNo logins for 2+ weeksPersonal CS email, re-engagement
60 daysNPS detractor, unresolved ticketExecutive escalation, save offer
90 daysCancellation signalsRetention call, custom offer

Win-Back Campaigns

Timing

Post-Churn PeriodResponse RateApproach
0-7 days15-25%Immediate save, address exit reason
7-30 days8-15%New feature announcement, incentive
30-90 days3-8%Major update, significant discount
90+ days<3%Annual check-in

Win-Back Sequence

Email 1 (Day 1): Address exit reason, offer to help
Email 2 (Day 7): New features since they left
Email 3 (Day 14): Comeback incentive (discount or extended trial)
Email 4 (Day 30): Final offer with urgency

Retention Levers

  1. Onboarding — Time to first value predicts retention more than any other factor
  2. Engagement loops — Regular touchpoints (weekly reports, digests)
  3. Feature adoption — Users who adopt 3+ features churn 50% less
  4. Community — Community members have 2-3x higher retention
  5. Switching costs — Integrations and data create healthy lock-in
  6. Proactive support — Reach out before problems become cancellations

CLV Calculation

Simple CLV = ARPU / Monthly Churn Rate
Full CLV = ARPU * Gross Margin % * (1 / Churn Rate)
CLV:CAC ratio target: >3:1

Integration with Other Skills

  • klaviyo-analyst — Design retention email flows and win-back sequences
  • customer-journey-mapping — Map retention and advocacy stages
  • google-analytics — Cohort analysis and engagement metrics
  • cro-auditor — Optimize cancellation flow to save more customers

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what retention-churn-prevention does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.