churn-prevention
SaaS churn reduction covering cancel flow design, dynamic save offers, exit survey architecture, dunning sequences, payment recovery, win-back campaigns, and churn impact modeling.
Install / Use
npx skills add borghei/Claude-Skills --skill churn-preventionInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Finance & AccountingSupported Platforms
Our assessment of churn-prevention
churn-prevention scores 92/100 on our quality scale, 22nd of 105 Finance & Accounting skills we index (top 21%).
Its SKILL.md is 22 KB long, well organised into 46 sections with 9 code examples: a thorough specification that gives an agent plenty to work with.
It has 817 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so churn-prevention is actively maintained.
- Our last check on 2026-10-28 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
churn-prevention compared with similar skills
All 4 of these similar skills score higher than churn-prevention; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| churn-prevention (this skill)by borghei | 92 | 817 | 57d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 117.6k | 9d ago | CLAUDE.md |
| Claude-Code-Game-Studiosby Donchitos | 100 | 39.9k | 8d ago | CLAUDE.md |
| x402by browser-use | 100 | 121.0k | 4d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 56d ago | SKILL.md |
Frequently asked questions
- How do I install churn-prevention?
- Run
npx skills add borghei/Claude-Skills --skill churn-prevention. The install tabs above show the steps for each supported agent. - Which AI agents does churn-prevention work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is churn-prevention safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is churn-prevention still maintained?
- The repository was last updated about 2 months ago, so churn-prevention is actively maintained.
Skill content
View source on GitHubname: churn-prevention description: > SaaS churn reduction covering cancel flow design, dynamic save offers, exit survey architecture, dunning sequences, payment recovery, win-back campaigns, and churn impact modeling. license: MIT + Commons Clause metadata: version: 1.0.0 author: borghei category: business-growth updated: 2026-03-31 tags: [churn, retention, cancel-flow, dunning, payment-recovery, win-back]
Churn Prevention
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).
Table of Contents
- Initial Assessment
- Churn Taxonomy
- Cancel Flow Architecture
- Exit Survey Design
- Dynamic Save Offer System
- Dunning Sequence Engineering
- Win-Back Campaign Framework
- Churn Health Scoring
- Metrics and Benchmarks
- Churn Impact Calculator
- Output Artifacts
- Related Skills
Clarify First
Before designing the churn-prevention system, confirm these inputs. If any is unknown or vague, ASK — do not assume:
- [ ] Voluntary vs involuntary churn split — which dominates (determines whether to build cancel flow/save offers or dunning/payment recovery)
- [ ] Existing cancel flow vs instant/support cancellation — sets build-from-scratch vs optimize mode
- [ ] Current MRR + ARPU + billing cycle — sizes the dollar impact and the save-offer budget
- [ ] Payment processor — Stripe / Braintree / Paddle / Recurly (determines card-updater and dunning retry implementation)
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the deliverable.
Initial Assessment
Required Context
| Question | Why It Matters | |----------|---------------| | Current monthly churn rate? (voluntary vs involuntary split) | Determines which lever to pull | | Do you have a cancel flow, or is cancellation instant/via support? | Determines build vs optimize mode | | What payment processor? (Stripe, Braintree, Paddle) | Affects dunning implementation | | Average contract value and billing cycle? | Sizes the save offer budget | | Current MRR? | Calculates the dollar impact of churn reduction | | SaaS model? (self-serve vs sales-assisted) | Determines intervention type | | Do you collect exit reasons today? | Data availability for save offer mapping |
Churn Taxonomy
Voluntary Churn (Customer Decides to Leave)
| Type | Signal | Addressable? | |------|--------|-------------| | Value gap | Not getting enough value for the price | Yes -- save offers, feature education | | Product-market mismatch | Wrong ICP, product does not fit their use case | Partially -- downgrade or pivot | | Competitor switch | Found a better alternative | Yes -- competitive counter-offers | | Budget cut | Cannot afford it anymore | Yes -- discount or pause | | Project completion | Seasonal or project-based need | Yes -- pause option | | Poor experience | Bad support, bugs, frustration | Yes -- human intervention | | Never activated | Signed up, never used it | Partially -- reactivation before cancel |
Involuntary Churn (Payment Fails)
| Cause | % of Failed Payments | Recoverable? | |-------|---------------------|-------------| | Expired card | 40-50% | Yes -- card updater service | | Insufficient funds | 20-30% | Yes -- smart retry timing | | Bank decline (fraud flag) | 10-15% | Sometimes -- customer must contact bank | | Account closed | 5-10% | No -- customer must provide new card | | Network error | 5-10% | Yes -- automatic retry |
Cancel Flow Architecture
The 5-Stage Cancel Flow
[Cancel Button] → [Exit Survey] → [Dynamic Save Offer] → [Confirmation] → [Post-Cancel]
Stage 1: Cancel Trigger
- Cancel option is findable (Settings > Account > Cancel). Do not hide it.
- Clicking "Cancel" starts the flow -- it does not immediately cancel the account
- Works on both desktop and mobile
Stage 2: Exit Survey (Required, 1 Question)
Question: "What is the main reason you are cancelling?"
Present as radio buttons (not a dropdown). Maximum 8 options:
| Reason | Internal Code | |--------|--------------| | Too expensive for the value I get | PRICE | | Not using it enough | LOW_USAGE | | Missing a feature I need | MISSING_FEATURE | | Switching to a different product | COMPETITOR | | My project or need ended | PROJECT_END | | Too complicated to use | COMPLEXITY | | Just testing, did not plan to keep it | TESTING | | Other (with optional text field) | OTHER |
Rules:
- Survey is required before showing the save offer (the answer determines the offer)
- One question only. No multi-page surveys.
- Optional free-text field for "Other" and as a supplement to any selection
- Track response distribution monthly to identify systemic issues
Stage 3: Dynamic Save Offer
Map each exit reason to exactly one save offer:
| Exit Reason | Save Offer | Offer Copy | |------------|-----------|------------| | PRICE | 30-50% discount for 2-3 months | "We'd like to offer you [X]% off for the next [N] months" | | LOW_USAGE | Pause account for 1-3 months | "Pause your account and come back when you need it" | | MISSING_FEATURE | Roadmap preview + workaround | "[Feature] is coming in [Q]. Here's how to achieve it now" | | COMPETITOR | Competitive comparison + discount | "Here's how we compare to [competitor]. Plus [X]% off" | | PROJECT_END | Pause option | "Pause instead of cancel -- your data stays safe" | | COMPLEXITY | Free onboarding session | "Let us set it up for you -- free 30-min session with our team" | | TESTING | No offer -- let them go | "Thanks for trying us out. You're welcome back anytime." | | OTHER | General retention offer | "Before you go -- we'd love to make this right. [Contact support]" |
Offer presentation rules:
- One clear offer per screen (not multiple choices)
- Quantify the value: "Save $120 over the next 3 months" not "Get a discount"
- CTA: "Accept Offer" vs "Continue Cancelling" (both clearly labeled)
- No countdown timers, no fake urgency
- No guilt-trip copy
Stage 4: Confirmation
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. │
└────────────────────────────────────────┘
Stage 5: Post-Cancel
| Timing | Channel | Message | |--------|---------|---------| | Immediately | Email | Cancellation confirmation + data retention policy + reactivation link | | Day 7 | Email | "We miss you" + single CTA to reactivate + what they are missing | | Day 30 | Email | Product update + relevant improvement + reactivation offer | | Day 60 | Email | Final win-back with strongest offer (if applicable) |
Exit Survey Design
Data Analysis Framework
Track exit survey responses monthly and calculate:
| Metric | Formula | Action Threshold | |--------|---------|-----------------| | Reason distribution | % of cancels per reason | Any reason > 30% = systemic issue | | Save rate by reason | Saved / Cancel attempts per reason | Any reason < 5% save rate = wrong offer | | Reason trend | Month-over-month change | Increasing trend = worsening problem | | Feature gap frequency | Count of "missing feature" with specific feature named | Top 3 missing features = product roadmap input |
Competitive Intelligence from Exit Surveys
When users select "Switching to a different product":
- Ask a follow-up: "Which product are you switching to?" (optional, free text or dropdown)
- Track the top 3 competitors winning your churners
- Feed this data into competitive-teardown skill for quarterly analysis
Dynamic Save Offer System
Offer Economics
| Offer Type | Cost to Business | Save Rate Benchmark | When Profitable | |-----------|-----------------|---------------------|----------------| | 30% discount (3 months) | 30% of 3 months revenue | 15-25% | If LTV after save > discount cost | | 50% discount (2 months) | 50% of 2 months revenue | 20-30% | If retained customer stays 6+ months | | Pause (1-3 months) | $0 (no revenue during pause) | 25-40% | If 50%+ reactivate after pause | | Free onboarding session | CS team time (~$50-100) | 10-20% | If ARPU > $100/month | | Downgrade to lower tier | Revenue reduction | 30-50% | If some revenue > no revenue | | Feature unlock | $0 (already built) | 5-15% | Always profitable |
Save Offer Decision Tree
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
Dunning Sequence Engineering
Failed payments cause 20-40% of total churn. Most of it is recoverable with proper dunning.
Smart Retry Schedule
Do not retry immediately after failure. Cards often recover within 3-7 days.
| Retry | Timing | Why This Timing | |-------|--------|-----------------| | Initial charge | Day 0 | Normal billing cycle | | Retry 1 | Day 3 | Most card issues resolve within 72 hours | | Retry 2 | Day 7 | Paycheck cycle alignment | | Retry 3 | Day 12 | Second paycheck cycle | | Retry 4 | Day 18 | Final attempt before service action | | Service action | Day 21 | Downgrade or cancel |
Card Updater Services
Enable automatic card updating to prevent expired card churn:
| Processor | Service | How to Enable | |-----------|---------|---------------| | Stripe | Automatic card updates | Enabled by default on most plans | | Braintree | Account Updater | Must enable in merchant settings | | Paddle | Built-in | Automatic | | Recurly | Account Updater | Configuration required |
Dunning Email Sequence
| Day | Subject Line | Body Focus | CTA | |-----|-------------|-----------|-----| | 0 | "Your [Product] payment didn't go through" | Factual, no blame. Card may be expired or funds unavailable. | [Update Payment Method] | | 3 | "Action needed: update your payment for [Product]" | Remind what they will lose access to. | [Update Payment Method] | | 7 | "Your [Product] account is at risk" | List features/data they have created. Mild urgency. | [Update Payment Method] | | 14 | "Final notice: your [Product] access ends in 7 days" | Clear deadline. Offer to help if bank issue. | [Update Payment Method] + [Contact Support] | | 21 | "Your [Product] account has been paused" | Account status change
Truncated for display — read the full file on GitHub.
Related Skills
taste-skill
117.6kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Claude-Code-Game-Studios
39.9kTurn Claude Code into a full game dev studio — 49 AI agents, 75 workflow skills, and a complete coordination system mirroring real studio hierarchy.
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
