--- name: "Retention churn prevention" repo: https://github.com/thatrebeccarae/claude-marketing source: https://github.com/thatrebeccarae/claude-marketing/blob/HEAD/skills/retention-churn-prevention/SKILL.md license: "MIT" install: "npx skills add thatrebeccarae/claude-marketing --skill retention-churn-prevention" page: https://100xlab.com/resources/agent-skills/thatrebeccarae-claude-marketing--retention-churn-prevention--ofgqbx --- # Retention & Churn Prevention Analyze churn, predict at-risk customers, and design retention strategies. ## Install ```bash git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/retention-churn-prevention ~/.claude/skills/ ``` ## Churn Analysis Framework ### Churn Types | Type | Definition | Signal | |------|-----------|--------| | **Voluntary** | Customer actively cancels | Cancellation request, downgrade | | **Involuntary** | Payment failure, card expiry | Failed charge, dunning | | **Silent** | Stops using but does not cancel | Usage 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 | Metric | Excellent | Good | Concerning | |--------|----------|------|-----------| | Monthly churn (SaaS) | <1% | 1-2% | >3% | | Annual churn (SaaS) | <5% | 5-10% | >15% | | Net revenue retention | >120% | 100-120% | <100% | ## Customer Health Scoring | Signal | Weight | Healthy | At Risk | |--------|--------|---------|---------| | Product usage | 25% | Daily/weekly | Monthly or less | | Feature adoption | 20% | 5+ features | 1-2 features | | Support sentiment | 15% | Positive/none | Negative | | Billing health | 15% | On time, expanding | Late, downgrading | | Engagement | 15% | Opens, clicks | Ignores | | NPS/CSAT | 10% | Promoter (9-10) | Detractor (0-6) | ## Early Warning Signals | Timeframe | Signal | Action | |-----------|--------|--------| | 7 days | Login frequency drops 50%+ | In-app nudge, value reminder | | 14 days | Key feature usage stops | CS outreach, usage tips | | 30 days | No logins for 2+ weeks | Personal CS email, re-engagement | | 60 days | NPS detractor, unresolved ticket | Executive escalation, save offer | | 90 days | Cancellation signals | Retention call, custom offer | ## Win-Back Campaigns ### Timing | Post-Churn Period | Response Rate | Approach | |------------------|---------------|----------| | 0-7 days | 15-25% | Immediate save, address exit reason | | 7-30 days | 8-15% | New feature announcement, incentive | | 30-90 days | 3-8% | 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 --- ## Supporting file: EXAMPLES.md # Retention & Churn Prevention — Examples ## Example 1: Build Churn Early Warning System ### Prompt > Design a customer health scoring system for our SaaS product. We have login data, feature usage, support tickets, and billing info. ### What the skill does 1. Designs health score with weighted signals (usage 25%, feature depth 20%, support 15%, billing 15%, engagement 15%, NPS 10%) 2. Defines thresholds: Green (80-100), Yellow (50-79), Red (0-49) 3. Creates alert triggers for each risk level with recommended CS actions 4. Proposes automated intervention playbook for Yellow and Red accounts --- ## Example 2: Win-Back Campaign ### Prompt > Design a win-back campaign for churned users. We had 340 cancellations last quarter. Top exit reasons: too expensive (40%), not using it enough (35%), switched to competitor (25%). ### What the skill does 1. Segments churned users by exit reason 2. Designs 3 win-back sequences (one per exit reason): discount offer for price-sensitive, new feature showcase for low-usage, comparison content for competitor-switched 3. Sets timing: Day 1, 7, 14, 30 cadence 4. Estimates recovery: 8-12% of price-sensitive, 5-8% of low-usage, 2-3% of competitor-switched --- ## Example 3: Cohort Retention Analysis ### Prompt > Analyze our monthly cohort retention curves. January cohort retained 68% at month 3, but March cohort only retained 52%. ### What the skill does 1. Compares cohort curves to identify where March diverges from January 2. Investigates variables: onboarding changes, product updates, traffic source mix, seasonal factors 3. Identifies root cause: March cohort had 60% from paid ads (vs January 30%) with lower intent 4. Recommends: segment retention by acquisition channel, improve paid traffic onboarding, tighten ICP targeting --- ## Supporting file: REFERENCE.md # Retention Churn Prevention Reference Reference data, benchmarks, and platform-specific details for the Retention Churn Prevention skill.