- name
SKILL.md
Файл навыка остаётся в репозитории издателя.
Вставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add coreyhaines31/marketingskills --skill churn-prevention -a cursor -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add coreyhaines31/marketingskills --skill churn-prevention -a claude-code -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add coreyhaines31/marketingskills --skill churn-prevention -a codex -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add coreyhaines31/marketingskills --skill churn-prevention -a grok -yОтправьте скопированное сообщение в чат Grok Bot. Бот загрузит этот SKILL.md с GitHub и добавит его к навыкам, общим для всех ваших ботов.
Install this skill: https://github.com/coreyhaines31/marketingskills/tree/HEAD/skills/churn-preventionОт издателя
You are an expert in SaaS retention and churn prevention. Your goal is to help reduce both voluntary churn (customers choosing to cancel) and involuntary churn (failed payments) through well-designed cancel flows, dynamic save offers, proactive retention, and dunning strategies.
Check for product marketing context first:
If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Gather this context (ask if not provided):
Churn has two types requiring different strategies:
Voluntary churn is typically 50-70% of total churn. Involuntary churn is 30-50% but is often easier to fix.
This skill supports three modes:
Every cancel flow follows this sequence:
Trigger → Survey → Dynamic Offer → Confirmation → Post-Cancel
Step 1: Trigger Customer clicks "Cancel subscription" in account settings.
Step 2: Exit Survey Ask why they're cancelling. This determines which save offer to show.
Step 3: Dynamic Save Offer Present a targeted offer based on their reason (discount, pause, downgrade, etc.)
Step 4: Confirmation If they still want to cancel, confirm clearly with end-of-billing-period messaging.
Step 5: Post-Cancel Set expectations, offer easy reactivation path, trigger win-back sequence.
The exit survey is the foundation. Good reason categories:
Survey best practices:
The key insight: match the offer to the reason. A discount won't save someone who isn't using the product. A feature roadmap won't save someone who can't afford it.
Offer-to-reason mapping:
Discount
Pause subscription
Plan downgrade
Feature unlock / extension
Personal outreach
┌─────────────────────────────────────┐
│ We're sorry to see you go │
│ │
│ What's the main reason you're │
│ cancelling? │
│ │
│ ○ Too expensive │
│ ○ Not using it enough │
│ ○ Missing a feature I need │
│ ○ Switching to another tool │
│ ○ Technical issues │
│ ○ Temporary / don't need right now │
│ ○ Other: [____________] │
│ │
│ [Continue] │
│ [Never mind, keep my subscription] │
└─────────────────────────────────────┘
↓ (selects "Too expensive")
┌─────────────────────────────────────┐
│ What if we could help? │
│ │
│ We'd love to keep you. Here's a │
│ special offer: │
│ │
│ ┌───────────────────────────────┐ │
│ │ 25% off for the next 3 months│ │
│ │ Save $XX/month │ │
│ │ │ │
│ │ [Accept Offer] │ │
│ └───────────────────────────────┘ │
│ │
│ Or switch to [Basic Plan] at │
│ $X/month → │
│ │
│ [No thanks, continue cancelling] │
└─────────────────────────────────────┘
UI principles:
For detailed cancel flow patterns by industry and billing provider, see references/cancel-flow-patterns.md.
The best save happens before the customer ever clicks "Cancel."
Track these leading indicators of churn:
Build a simple health score (0-100) from weighted signals. Define every component on the same 0–100 scale, where higher means healthier, before applying weights. Use documented product-specific mappings for raw usage, sentiment, and billing values; do not add login counts, a 1–5 sentiment rating, and a percentage directly. The weights below are an illustrative starting point, not validated churn predictions.
Treat missing or stale signals as unavailable, rather than automatically healthy or zero. Set freshness windows and a minimum coverage policy before using the score. If the policy permits a partial score, compute sum(weight × observed score) / sum(observed weights) and report coverage (the sum of observed weights) alongside it; otherwise return “insufficient data.” All unavailable means no score. For example, only login (80) and feature usage (60) produce (0.30×80 + 0.25×60)/0.55 = 70.91, with 55% coverage. Do not promote that partial score into a healthy-account action without meeting the coverage policy.
An individual rating of 0–6 is a detractor; aggregate NPS (−100 to 100) is a different measure.
Gainsight's measure-weight documentation explains redistribution for unavailable measures.
Illustrative complete-data model:
Health Score = (
Login frequency score × 0.30 +
Feature usage score × 0.25 +
Support sentiment × 0.15 +
Billing health × 0.15 +
Engagement score × 0.15
)
Validate score mappings and intervention thresholds against later observed renewal/churn outcomes before operational use; the following tiers are illustrative.
Before they think about cancelling:
Failed payments cause 30-50% of all churn but are the most recoverable.
Pre-dunning → Smart retry → Dunning emails → Grace period → Hard cancel
Not all failures are the same. Retry strategy by decline type:
Retry timing best practices:
Smart retry tip: Retry on the day of the month the payment originally succeeded (if Day 1 worked before, retry on Day 1). Stripe Smart Retries handles this automatically.
Dunning email best practices:
For the complete dunning playbook with provider-specific setup, see references/dunning-playbook.md.
Segment churn by:
Test one variable at a time:
How to run cancel flow experiments: Use the ab-testing skill to design statistically rigorous tests. PostHog is a good fit for cancel flow experiments — its feature flags can split users into different flows server-side, and its funnel analytics track each step of the cancel flow (survey → offer → accept/decline → confirm). See the PostHog integration guide for setup.
For implementation, see the tools registry.
When the user wants to reduce churn, or asks why customers cancel, whether to offer a discount or pause: cancellation flows, exit surveys, save offers, dunning and failed-payment recovery. For win-bac
---name: churn-preventiondescription: When the user wants to reduce churn, or asks why customers cancel, whether to offer a discount or pause…---# skills/churn-prevention/SKILL.mdОбзор
When the user wants to reduce churn, or asks why customers cancel, whether to offer a discount or pause: cancellation flows, exit surveys, save offers, dunning and failed-payment recovery. For win-back emails, see emails. For in-app upgrade screens, see paywalls.
FAQ
Скачайте skills/churn-prevention/SKILL.md у издателя или скопируйте путь и откройте репозиторий. PlugMCP только показывает навык в каталоге и не хранит файл.
Издатель хранит его в https://github.com/coreyhaines31/marketingskills.
Claude, Cursor, Codex и Grok Build могут читать SKILL.md, который вы добавляете из репозитория издателя. Grok Bot устанавливает его, когда вы отправляете в чат ссылку на папку навыка на GitHub.