- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add borghei/Claude-Skills --skill churn-prevention -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add borghei/Claude-Skills --skill churn-prevention -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add borghei/Claude-Skills --skill churn-prevention -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add borghei/Claude-Skills --skill churn-prevention -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/borghei/Claude-Skills/tree/HEAD/business-growth/churn-prevention來自發布者
Production-grade SaaS churn reduction framework covering cancel flow architecture, dynamic save offer mapping, exit survey design, dunning sequence engineering, payment recovery optimization, win-back campaigns, and churn impact modeling. Addresses both voluntary churn (customers who decide to leave) and involuntary churn (customers who leave due to payment failure).
Before designing the churn-prevention system, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.
Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.
[Cancel Button] → [Exit Survey] → [Dynamic Save Offer] → [Confirmation] → [Post-Cancel]
Question: "What is the main reason you are cancelling?"
Present as radio buttons (not a dropdown). Maximum 8 options:
Rules:
Map each exit reason to exactly one save offer:
Offer presentation rules:
If they decline the save offer or there is no offer to make:
┌────────────────────────────────────────┐
│ We're sorry to see you go │
│ │
│ What happens when you cancel: │
│ - Your data is saved for 90 days │
│ - Access continues until [date] │
│ - You can reactivate anytime │
│ │
│ [Yes, Cancel My Account] │
│ [Wait, I Changed My Mind] │
│ │
│ No pre-checked boxes. │
│ No confusing language. │
└────────────────────────────────────────┘
Track exit survey responses monthly and calculate:
When users select "Switching to a different product":
User selects exit reason →
├── PRICE →
│ ├── Customer ARPU > median? → Offer 30% discount
│ └── Customer ARPU < median? → Offer downgrade to cheaper plan
├── LOW_USAGE →
│ ├── Last login > 30 days? → Offer pause
│ └── Last login < 30 days? → Offer usage tips + discount
├── MISSING_FEATURE →
│ ├── Feature on roadmap? → Share roadmap + workaround
│ └── Feature not planned? → Offer discount or acknowledge gap
├── COMPETITOR →
│ ├── Known competitor? → Show comparison + retention offer
│ └── Unknown competitor? → General retention offer
├── PROJECT_END →
│ └── Always → Offer pause
├── COMPLEXITY →
│ ├── Enterprise/high-value? → Offer dedicated onboarding session
│ └── SMB/low-value? → Offer guided tutorial link
└── TESTING →
└── Always → No offer, let go gracefully
Failed payments cause 20-40% of total churn. Most of it is recoverable with proper dunning.
Do not retry immediately after failure. Cards often recover within 3-7 days.
Enable automatic card updating to prevent expired card churn:
Email rules:
Day 7 Email:
Day 30 Email:
Day 60 Email:
Risk Score = Sum of (Signal Weight x Signal Present)
0-20: Low risk (monitor)
21-40: Moderate risk (proactive outreach)
41-60: High risk (intervention required)
61+: Critical risk (executive escalation)
Monthly MRR at risk = Total MRR x Monthly churn rate
Annual MRR saved by 1% churn reduction = Total MRR x 0.01 x 12
Annual MRR saved by 20% save rate = (Monthly MRR at risk x 0.20) x 12
Example:
MRR: $500,000
Monthly churn: 4% = $20,000/month lost
Reduce to 3% = $5,000/month saved = $60,000/year
Add 20% save rate on remaining = $3,000/month saved = $36,000/year
Total annual impact: $96,000
Purpose: Calculate the revenue impact of churn reduction at various improvement levels.
python scripts/churn_impact_calculator.py --mrr 500000 --churn-rate 4.0 --save-rate 20
python scripts/churn_impact_calculator.py --mrr 500000 --churn-rate 4.0 --save-rate 20 --json
Purpose: Analyze dunning email sequence effectiveness and recommend retry timing optimizations.
python scripts/dunning_sequence_analyzer.py dunning_data.json
python scripts/dunning_sequence_analyzer.py dunning_data.json --json
Input JSON format:
{
"failed_payments": [
{
"payment_id": "PAY-001",
"amount": 99.00,
"failure_reason": "expired_card",
"retry_attempts": [
{"day": 0, "recovered": false},
{"day": 3, "recovered": false},
{"day": 7, "recovered": true}
]
}
]
}
Purpose: Analyze exit survey responses to identify churn patterns, save offer effectiveness, and systemic issues.
python scripts/exit_survey_analyzer.py survey_data.json
python scripts/exit_survey_analyzer.py survey_data.json --json
>
---name: churn-preventiondescription: >---# business-growth/churn-prevention/SKILL.md常見問題
從發布者下載 business-growth/churn-prevention/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/borghei/Claude-Skills。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。