Suede Churn Prevention logo

Suede Churn Prevention

Community
JasonColapietro
suede-churn-prevention

Suede AI Churn Prevention Skills. Use when asked to "reduce subscription churn" or design cancel flows, reason-matched save offers, failed-payment recovery and win-back measurement. NOT FOR: lifecycle email copy (suede-emails), pricing architecture (suede-pricing), paywalls (suede-paywalls), or tracking implementation (suede-analytics).

Overview

PublisherJasonColapietro
Repositorysuede-creator-skills
Skill namesuede-churn-prevention
Stars
126
Forks
12
Bundled files
6
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by JasonColapietro on GitHub. Read the source before you install it.

Installation

Install the Suede Churn Prevention AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-churn-prevention
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git /tmp/suede-creator-skills
mkdir -p .claude/skills
cp -r /tmp/suede-creator-skills/skills/suede-churn-prevention .claude/skills/suede-churn-prevention
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Suede Churn Prevention in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Suede Churn Prevention on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Suede Churn Prevention is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Suede AI Churn Prevention Skills

Read the worked delivery contract for a concrete input, expected artifact, failure response and validation example.

Compatibility

Works from subscription cohorts, cancel reasons and payment-status exports; current official policy/legal sources for applicable cancellation requirements. Live billing mutations require existing authorized access.

Use this retention playbook to reduce voluntary and involuntary churn through transparent cancel flows, bounded save offers, proactive signals, and payment recovery.

Before Starting

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):

1. Current Churn Situation

  • What's your monthly churn rate? (Voluntary vs. involuntary if known)
  • How many active subscribers?
  • What's the average MRR per customer?
  • Do you have a cancel flow today, or does cancel happen instantly?

2. Billing & Platform

  • What billing provider? (Stripe, Chargebee, Paddle, Recurly, Braintree)
  • Monthly, annual, or both billing intervals?
  • Do you support plan pausing or downgrades?
  • Any existing retention tooling? (Churnkey, ProsperStack, Raaft)

3. Product & Usage Data

  • Do you track feature usage per user?
  • Can you identify engagement drop-offs?
  • Do you have cancellation reason data from past churns?
  • What's your activation metric? (What do retained users do that churned users don't?)

4. Constraints

  • B2B or B2C? (Affects flow design)
  • Which states and countries are customers in? (California and other automatic renewal laws require online cancellation; see Cancellation law below)
  • Brand tone for offboarding? (Empathetic, direct, playful)

How This Skill Works

Churn has two types requiring different strategies:

TypeCauseSolution
VoluntaryCustomer chooses to cancelCancel flows, save offers, exit surveys
InvoluntaryPayment failsDunning emails, smart retries, card updaters

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:

  1. Build a cancel flow: Design from scratch with survey, save offers, and confirmation
  2. Optimize an existing flow: Analyze cancel data and improve save rates
  3. Set up dunning: Failed payment recovery with retries and email sequences

Cancel Flow Design

The Cancel Flow Structure

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.

Exit Survey Design

The exit survey is the foundation. Good reason categories:

ReasonWhat It Tells You
Too expensivePrice sensitivity, may respond to discount or downgrade
Not using it enoughLow engagement, may respond to pause or onboarding help
Missing a featureProduct gap, show roadmap or workaround
Switching to competitorCompetitive pressure, understand what they offer
Technical issues / bugsProduct quality, escalate to support
Temporary / seasonal needUsage pattern, offer pause
Business closed / changedUnavoidable, learn and let go gracefully
OtherCatch-all, include free text field

Survey best practices:

  • 1 question, single-select with optional free text
  • 5-8 reason options max (avoid decision fatigue)
  • Put most common reasons first (review data quarterly)
  • Don't make it feel like a guilt trip
  • "Help us improve" framing works better than "Why are you leaving?"

Dynamic Save Offers

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:

Cancel ReasonPrimary OfferFallback Offer
Too expensiveDiscount (20-30% for 2-3 months)Downgrade to lower plan
Not using it enoughPause (1-3 months)Free onboarding session
Missing featureRoadmap preview + timelineWorkaround guide
Switching to competitorCompetitive comparison + discountFeedback session
Technical issuesEscalate to support immediatelyCredit + priority fix
Temporary / seasonalPause subscriptionDowngrade temporarily
Business closedSkip offer (respect the situation)n/a

Save Offer Types

Discount

  • 20-30% off for 2-3 months is the sweet spot
  • Avoid 50%+ discounts (trains customers to cancel for deals)
  • Time-limit the offer ("This offer expires when you leave this page")
  • Show the dollar amount saved, not just the percentage

Pause subscription

  • 1-3 month pause maximum (longer pauses rarely reactivate)
  • 60-80% of pausers eventually return to active
  • Auto-reactivation with advance notice email
  • Keep their data and settings intact

Plan downgrade

  • Offer a lower tier instead of full cancellation
  • Show what they keep vs. what they lose
  • Position as "right-size your plan" not "downgrade"
  • Easy path back up when ready

Feature unlock / extension

  • Turn on a premium feature they haven't tried
  • Extend trial of a higher tier
  • Works best for "not getting enough value" reasons

Personal outreach

  • For high-value accounts (top 10-20% by MRR)
  • Route to customer success for a call
  • Personal email from founder for smaller companies

Cancellation law (checked October 2026)

  • Federal: the FTC's 2024 "click-to-cancel" amendments to the Negative Option Rule were vacated by the Eighth Circuit on July 8, 2025, before their compliance date. The Restore Online Shoppers' Confidence Act (ROSCA) still requires simple cancellation for online negative-option offers, and the FTC keeps enforcing it.
  • California: the amended Automatic Renewal Law (AB 2863), effective July 1, 2025, requires online cancellation through a prominent direct link or button for subscriptions sold online, and a save offer may appear only if the customer is told they can still cancel and can do so without engaging with it.
  • Other states have their own automatic renewal laws. Treat the strictest one in your market as the floor.

Design rule that satisfies all of the above: one save offer, a visible "continue to cancel" control on every screen, and a cancellation that completes online in the same session. Legal review decides edge cases, not this skill.

Sources: Mayer Brown, "Click-to-Cancelled: Eighth Circuit Vacates FTC's Revised Negative Option Rule" (July 18, 2025); Lowenstein Sandler, "FTC Click-to-Cancel Rule on Hold, but California's Automatic Renewal Law Remains Intact" (July 16, 2025).

Cancel Flow UI Patterns

UI principles:

  • Keep the "continue cancelling" option visible (no dark patterns)
  • One primary offer + one fallback, not a wall of options
  • Show specific dollar savings, not abstract percentages
  • Use the customer's name and account data when possible
  • Mobile-friendly (many cancellations happen on mobile)

Read references/cancel-flow-patterns.md before designing a flow: it carries the patterns by industry and billing provider, the segment-specific variants, the post-cancel sequence, and screen mockups of the survey and offer steps.


Churn Prediction & Proactive Retention

The best save happens before the customer ever clicks "Cancel."

Risk Signals

Track these leading indicators of churn:

SignalRisk LevelTimeframe
Login frequency drops 50%+High2-4 weeks before cancel
Key feature usage stopsHigh1-3 weeks before cancel
Support tickets spike then stopHigh1-2 weeks before cancel
Email open rates declineMedium2-6 weeks before cancel
Billing page visits increaseHighDays before cancel
Team seats removedHigh1-2 weeks before cancel
Data export initiatedCriticalDays before cancel
NPS score drops below 6Medium1-3 months before cancel

Health Score Model

Build a simple health score (0-100) from weighted signals:

Health Score = (
  Login frequency score × 0.30 +
  Feature usage score   × 0.25 +
  Support sentiment     × 0.15 +
  Billing health        × 0.15 +
  Engagement score      × 0.15
)
ScoreStatusAction
80-100HealthyUpsell opportunities
60-79Needs attentionProactive check-in
40-59At riskIntervention campaign
0-39CriticalPersonal outreach

Proactive Interventions

Before they think about cancelling:

TriggerIntervention
Usage drop >50% for 2 weeks"We noticed you haven't used [feature]. Need help?" email
Approaching plan limitUpgrade nudge (not a wall, paywalls handles this)
No login for 14 daysRe-engagement email with recent product updates
NPS detractor (0-6)Personal follow-up within 24 hours
Support ticket unresolved >48hEscalation + proactive status update
Annual renewal in 30 daysValue recap email + renewal confirmation

Involuntary Churn: Payment Recovery

Failed payments cause 30-50% of all churn but are the most recoverable.

The Dunning Stack

Pre-dunning → Smart retry → Dunning emails → Grace period → Hard cancel

Pre-Dunning (Prevent Failures)

  • Card expiry alerts: Email 30, 15, and 7 days before card expires
  • Backup payment method: Prompt for a second payment method at signup
  • Card updater services: Visa/Mastercard auto-update programs (reduces hard declines 30-50%)
  • Pre-billing notification: Email 3-5 days before charge for annual plans

Smart Retry Logic

Not all failures are the same. Retry strategy by decline type:

Decline TypeExamplesRetry Strategy
Soft decline (temporary)Insufficient funds, processor timeoutRetry on the canonical schedule below
Hard decline (permanent)Card stolen, account closedDon't retry: ask for new card
Authentication required3D Secure, SCASend customer to update payment

Canonical retry schedule: one schedule governs this skill: the manual retry table in references/dunning-playbook.md §Retry Schedule by Provider (Day 1 / 3 / 5 / 7 / 10, fifth attempt last before the grace period ends). Read it before configuring retries and do not restate a different schedule anywhere.

Dunning Email Sequence

Four emails on Day 0 / 3 / 7 / 10. The timing, tone, and full copy for each live in references/dunning-playbook.md §Dunning Email Sequence: read it before writing or configuring the sequence.

Dunning email best practices:

  • Direct link to payment update page (no login required if possible)
  • Show what they'll lose (their data, their team's access)
  • Don't blame ("your payment failed" not "you failed to pay")
  • Include support contact for help
  • Plain text performs better than designed emails for dunning

Recovery Benchmarks

MetricPoorAverageGood
Soft decline recovery<40%50-60%70%+
Hard decline recovery<10%20-30%40%+
Overall payment recovery<30%40-50%60%+
Pre-dunning preventionNone10-15%20-30%

These bands are industry ranges for calibrating a recommendation. Never assert them as this product's result.

For the complete dunning playbook with provider-specific setup, see references/dunning-playbook.md.


Metrics & Measurement

Key Churn Metrics

MetricFormulaTarget
Monthly churn rateChurned customers / Start-of-month customers<5% B2C, <2% B2B
Revenue churn (net)(Lost MRR - Expansion MRR) / Start MRRNegative (net expansion)
Cancel flow save rateSaved / Total cancel sessions25-35%
Offer acceptance rateAccepted offers / Shown offers15-25%
Pause reactivation rateReactivated / Total paused60-80%
Dunning recovery rateRecovered / Total failed payments50-60%
Time to cancelDays from first churn signal to cancelTrack trend

Cohort Analysis

Segment churn by:

  • Acquisition channel: Which channels bring stickier customers?
  • Plan type: Which plans churn most?
  • Tenure: When do most cancellations happen? (30, 60, 90 days?)
  • Cancel reason: Which reasons are growing?
  • Save offer type: Which offers work best for which segments?

Cancel Flow A/B Tests

Test one variable at a time:

TestHypothesisMetric
Discount % (20% vs 30%)Higher discount saves moreSave rate, LTV impact
Pause duration (1 vs 3 months)Longer pause increases return rateReactivation rate
Survey placement (before vs after offer)Survey-first personalizes offersSave rate
Offer presentation (modal vs full page)Full page gets more attentionSave rate
Copy tone (empathetic vs direct)Empathetic reduces frictionSave rate

How to run cancel flow experiments: Route the hypothesis, sample, duration, and stopping rule to suede-ab-testing. Use an authorized experimentation system that can assign users consistently and read each funnel step (survey → offer → accept/decline → confirm). Verify the system's current official implementation guidance, assignment behavior, and event readback before launch.


Common Mistakes

  • No cancel flow at all: Instant cancel leaves money on the table. Even a simple survey + one offer saves 10-15%
  • Not tracking save offer LTV: A "saved" customer who churns 30 days later wasn't really saved
  • No post-cancel path: Make reactivation easy and trigger win-back emails, because some churned users will want to come back

Tool Integrations

This pack does not ship retention, billing, or analytics connectors. Select an authorized system from the user's actual stack and verify its current official documentation, account plan, test mode, and rollback path before configuration.

Capability Checklist

  • Cancel-flow routing, survey capture, and an unobstructed final cancel action
  • Stable experiment assignment and step-level event readback
  • Pause, downgrade, and save-offer rules with explicit eligibility
  • Payment-retry state, card-updater state, and customer-notification controls
  • Audit history, test mode, role controls, and rollback or disable behavior

Implementation Routing

  • Route message writing to suede-emails.
  • Route event schemas and readback to suede-analytics.
  • Route test design to suede-ab-testing.
  • Treat billing retries, discounts, subscription changes, and activation as separately authorized mutations.

Halt Format for Billing Mutations

Before any change to a live billing object (retry rules, discounts, plan changes, pauses, cancellations, subscription state, or customer-facing billing messages), stop and emit this block, then wait. Inferred consent is not authorization, and "the user asked for a cancel flow" is not authorization to configure one.

HALT: billing mutation requires authorization

Mutation: <the exact change, e.g. "enable 5-attempt retry rule">
Objects touched: <provider, environment, subscriptions/customers/coupons affected, count>
Reversible by: <the exact rollback, or "not reversible">

Options:
1. Proceed in test mode only
2. Proceed on live objects as specified
3. Narrow the scope to <smaller set> and proceed
4. Abandon this mutation

Waiting for your choice.

Boundaries

  • Do not obstruct cancellation, hide downgrade paths, manufacture urgency, or use deceptive retention friction.
  • Do not change subscriptions, retry rules, discounts, billing objects, or customer messaging without explicit authorization.
  • Do not claim saved revenue or churn reduction without a defined cohort, window, denominator, and verified payment state.
  • Do not decide which individual customer should receive a sensitive offer from protected traits or unsupported inference.

Routing

  • Need retention, dunning, or win-back messages -> use suede-emails.
  • Need plan structure or offer economics -> use suede-pricing or suede-offers.
  • Need paywall or trial-expiry UX -> use suede-paywalls.
  • Need churn events or a controlled retention test -> use suede-analytics or suede-ab-testing.
  • From those skills, route cancellation and payment-recovery strategy back to suede-churn-prevention.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Suede Churn Prevention AI skill do?

Suede AI Churn Prevention Skills. Use when asked to "reduce subscription churn" or design cancel flows, reason-matched save offers, failed-payment recovery and win-back measurement. NOT FOR: lifecycle email copy (suede-emails), pricing architecture (suede-pricing), paywalls (suede-paywalls), or tracking implementation (suede-analytics).

Why use Suede Churn Prevention on TypingMind?

Because you install it once and use it with any model. Suede Churn Prevention is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Suede Churn Prevention in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-churn-prevention. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Suede Churn Prevention?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Suede Churn Prevention?

As many as you like. As long as a model supports skills, you can use Suede Churn Prevention with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Suede Churn Prevention AI skill free?

Yes. It is published on GitHub by JasonColapietro under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇