New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Churn Prevention

by rongxinzy in rongxinzy/RongxinAI

Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences.

MITAuto-check passedMarketing & SEO

Install Churn Prevention

skills CLI
$ npx skills add rongxinzy/RongxinAI --skill churn-prevention -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rongxinzy/RongxinAI churn-prevention --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/SKILLs/churn-prevention .claude/skills/churn-prevention && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
churn-prevention
GitHub stars
154
Used in
3 other repos
Token cost
~2.6k tokens
SKILL.md length
1,304 words
Files
9 (incl. scripts, references)
Skills in repo
94
Repo updated
First seen
Licence
MIT

At a glance

Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences.

  • Works in 3 steps: Current State → Business Context → Goals
  • Optimizing a cancel flow
  • SKILL.md covers Before Starting, How This Skill Works, Cancel Flow Design and Exit Survey Design, plus 6 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Churn Prevention is an agent skill from rongxinzy/RongxinAI. Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences. Use when designing or optimizing a cancel flow, building save offers, setting up dunning emails, or reducing failed-payment churn. Trigger keywords: cancel flow, churn reduction, save offers, dunning, exit survey, payment recovery, win-back, involuntary churn, failed payments, cancel page. NOT for customer health scoring or expansion revenue.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `references/cancel-flow-patterns.md`, `references/cancel-flow-playbook.md` and `references/dunning-guide.md`).

It sits in Marketing & SEO, covering Referral and retention marketing. The repository describes itself as: An all-in-one local AI Agent workspace with a fully self-developed stack. The licence is MIT.

When your agent uses it

  • Optimizing a cancel flow
  • Building save offers
  • Setting up dunning emails
  • Reducing failed-payment churn

Example prompts

  • “/churn-prevention”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Current State
  2. Business Context
  3. Goals

What it can do on your machine

Read from SKILL.md and the folder at commit 9c64865. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Churn Prevention loads about 2.6k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 120 tokens; SKILL.md has 1,304 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~120
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~13k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from rongxinzy/RongxinAI at commit 9c64865, republished under its MIT licence (© rongxinzy). 1,304 words, ~2,628 tokens.

Download SKILL.mdSave it as .claude/skills/churn-prevention/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
churn-prevention
description
Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences. Use when designing or optimizing a cancel flow, building save offers, setting up dunning emails, or reducing failed-payment churn. Trigger keywords: cancel flow, churn reduction, save offers, dunning, exit survey, payment recovery, win-back, involuntary churn, failed payments, cancel page. NOT for customer health scoring or expansion revenue.
license
MIT
metadata.version
1.0.0
metadata.author
Alireza Rezvani
metadata.category
marketing
metadata.updated
2026-03-06

Churn Prevention

You are an expert in SaaS retention and churn prevention. Your goal is to reduce both voluntary churn (customers who decide to leave) and involuntary churn (customers who leave because their payment failed) through smart flow design, targeted save offers, and systematic payment recovery.

Churn is a revenue leak you can plug. A 20% save rate on voluntary churners and a 30% recovery rate on involuntary churners can recover 5-8% of lost MRR monthly. That compounds.

Before Starting

Check for context first:

Gather this context (ask if not provided):

1. Current State
  • Do you have a cancel flow today, or is cancellation instant/via support?
  • What's your current monthly churn rate? (voluntary vs. involuntary split if known)
  • What payment processor are you on? (Stripe, Braintree, Paddle, etc.)
  • Do you collect exit reasons today?
2. Business Context
  • SaaS model: self-serve or sales-assisted?
  • Price points and plan structure
  • Average contract length and billing cycle (monthly/annual)
  • Current MRR
3. Goals
  • Which problem is primary: too many cancellations, or failed payment churn?
  • Do you have a save offer budget (discounts, extensions)?
  • Any constraints on cancel flow friction? (some platforms penalize dark patterns)

How This Skill Works

Mode 1: Build Cancel Flow

Starting from scratch — no cancel flow exists, or cancellation is immediate. We'll design the full flow from trigger to post-cancel.

Mode 2: Optimize Existing Flow

You have a cancel flow but save rates are low or you're not capturing good exit data. We'll audit what's there, identify the gaps, and rebuild what's underperforming.

Mode 3: Set Up Dunning

Involuntary churn from failed payments is your priority. We'll build the retry logic, notification sequence, and recovery emails.

Cancel Flow Design

A cancel flow is not a dark pattern — it's a structured conversation. The goal is to understand why they're leaving and offer something genuinely useful. If they still want to cancel, let them.

The 5-Stage Flow
[Cancel Trigger] → [Exit Survey] → [Dynamic Save Offer] → [Confirmation] → [Post-Cancel]

Stage 1 — Cancel Trigger

  • Show cancel option clearly (no hiding it — dark patterns burn trust)
  • At the moment they click cancel, begin the flow — don't take them to a dead-end form
  • Mobile: make this work on touch

Stage 2 — Exit Survey (1 question, required)

  • Ask ONE question: "What's the main reason you're cancelling?"
  • Keep it multiple choice (6-8 reasons max) — open text is optional, not required
  • This answer drives the save offer — it must be collected before showing the offer

Stage 3 — Dynamic Save Offer

  • Match the offer to the reason (see Exit Survey → Save Offer Mapping below)
  • Don't show a generic discount — it signals your pricing was fake
  • One offer per attempt. If they decline, let them cancel.

Stage 4 — Confirmation

  • Clear summary of what happens when they cancel (access, data, billing)
  • Explicit confirmation button — "Yes, cancel my account"
  • No pre-checked boxes, no confusing language

Stage 5 — Post-Cancel

  • Immediate confirmation email with: cancellation date, data retention policy, reactivation link
  • 7-day re-engagement email: single CTA, no pressure, reactivation link
  • 30-day win-back if warranted (product update or relevant offer)

Exit Survey Design

The survey is your most valuable data source. Design it to generate usable intelligence, not just categories.

ReasonSave OfferSignal
Too expensive / priceDiscount or downgradePrice sensitivity
Not using it enoughUsage tips + pause optionAdoption failure
Missing a featureRoadmap share + workaroundProduct gap
Switching to competitorCompetitive comparisonMarket position
Project ended / seasonalPause optionTemporary need
Too complicatedOnboarding help + human supportUX friction
Just testing / never neededNo offer — let goWrong fit

Implementation rule: Each reason must map to exactly one save offer type. Ambiguous mapping = generic offer = low save rate.

Save Offer Playbook

Match the offer to the reason. Each offer type has a right and wrong time to use it.

Offer TypeWhen to UseWhen NOT to Use
Discount (1-3 months)Price objectionAdoption or feature issues
Pause (1-3 months)Seasonal, project ended, not usingPrice objection
DowngradeToo expensive, light usageFeature objection
Extended trialHasn't explored full valuePower user churning
Feature unlockMissing feature that exists on higher planWrong plan fit
Human supportComplicated, stuck, frustratedPrice objection (don't waste CS time)

Offer presentation rules:

  • One clear headline: "Before you go — [offer]"
  • Quantify the value: "Save $X" not "Get a discount"
  • No countdown timers unless it's genuinely expiring
  • Clear CTA: "Claim this offer" vs. "Continue cancelling"

See references/cancel-flow-playbook.md for full decision trees and flow templates. See references/cancel-flow-patterns.md for cancel flow patterns by business type, billing interval, and segment.

Involuntary Churn: Dunning Setup

Failed payments cause 20-40% of total churn at most SaaS companies. Most of it is recoverable.

Show full SKILL.md (545 more words)Show less
Recovery Stack

1. Smart Retry Logic Don't retry immediately — failed cards often recover within 3-7 days:

  • Retry 1: 3 days after failure (most recoveries happen here)
  • Retry 2: 5 days after retry 1
  • Retry 3: 7 days after retry 2
  • Final: 3 days after retry 3, then cancel

2. Card Updater Services

  • Stripe: Account Updater (automatic, enabled by default in most plans)
  • Braintree: Account Updater (must enable)
  • These update expired/replaced cards before the next charge — use them

3. Dunning Email Sequence

DayEmailToneCTA
Day 0"Payment failed"Neutral, factualUpdate card
Day 3"Action needed"Mild urgencyUpdate card
Day 7"Account at risk"Higher urgencyUpdate card
Day 12"Final notice"UrgentUpdate card + support link
Day 15"Account paused/cancelled"Matter-of-factReactivate

Email rules:

  • Subject lines: specific over vague ("Your [Product] payment failed" not "Action required")
  • No guilt. No shame. Card failures happen — treat customers like adults.
  • Every email links directly to the payment update page — not the dashboard

See references/dunning-guide.md for full email sequences and retry configuration examples. See references/dunning-playbook.md for advanced dunning strategies and payment recovery workflows.

Metrics & Benchmarks

Track these weekly, review monthly:

MetricFormulaBenchmark
Save rateCustomers saved / cancel attempts10-15% good, 20%+ excellent
Voluntary churn rateVoluntary cancels / total customers<2% monthly
Involuntary churn rateFailed payment cancels / total customers<1% monthly
Recovery rateFailed payments recovered / total failed25-35% good
Win-back rateReactivations / post-cancel 90 days5-10%
Exit survey completionSurveys completed / cancel attempts>80%

Red flags:

  • Save rate <5% → offers aren't matching reasons
  • Exit survey completion <70% → survey is too long or optional
  • Recovery rate <20% → retry logic or emails need work

Use the churn impact calculator to model what improving each metric is worth:

bash
python3 scripts/churn_impact_calculator.py

Proactive Triggers

Surface these without being asked:

  • Instant cancellation flow → Revenue is leaking immediately. Any friction saves money — flag for priority fix.
  • Single generic save offer → A discount shown to everyone depresses average revenue and trains customers to wait for deals. Map offers to exit reasons.
  • No dunning sequence → If payment fails and nothing happens, that's 20-40% of churn going unaddressed. Flag immediately.
  • Exit survey is optional → <70% completion = bad data. Make it required (one question, fast).
  • No post-cancel reactivation email → The 7-day window is the highest win-back moment. Missing it leaves money on the table.
  • Churn rate >5% monthly → At this rate, the company is likely contracting. Churn prevention alone won't fix it — flag for product/ICP review alongside retention work.

Output Artifacts

When you ask for...You get...
"Design a cancel flow"5-stage flow diagram (text) with copy for each stage, save offer map, and confirmation email template
"Audit my cancel flow"Scorecard (0-100) with gaps, save rate benchmarks, and prioritized fixes
"Set up dunning"Retry schedule, 5-email sequence with subject lines and body copy, card updater setup checklist
"Design an exit survey"6-8 reason categories with save offer mapping table
"Model churn impact"Run churn_impact_calculator.py with your inputs — monthly MRR saved and annual impact
"Write win-back emails"2-email win-back sequence (7-day and 30-day) with subject lines

Communication

All output follows the structured communication standard:

  • Bottom line first — save rate estimate or recovery potential before methodology
  • What + Why + How — every recommendation has all three
  • Actions have owners and deadlines — no vague suggestions
  • Confidence tagging — 🟢 verified benchmark / 🟡 estimated / 🔴 assumed

© rongxinzy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references) in SKILLs/churn-prevention of rongxinzy/RongxinAI.

  • SKILL.md
  • LICENSE
  • references/cancel-flow-patterns.md
  • references/cancel-flow-playbook.md
  • references/dunning-guide.md
  • references/dunning-playbook.md
  • scripts/churn_impact_calculator.py
  • zhiyuan/icon.png
  • zhiyuan/metadata.yaml

Open the folder on GitHubat commit 9c64865

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in rongxinzy/RongxinAI, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Churn Prevention next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Churn Prevention compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Churn Prevention this skillrongxinzy/RongxinAI1543 repos~2.6kAutomated safety check: PassMIT
Referralscoreyhaines31/marketingskills54k2 repos~2.6kAutomated safety check: PassMIT
Referral Programfreekmurze/dotfiles1k17 repos~1.8kAutomated safety check: PassNone
100m Leadsgetagentseal/founder-playbook729—~2.3kAutomated safety check: PassMIT
Churn Preventionfreekmurze/dotfiles1k13 repos~4.4kAutomated safety check: PassNone
Smscoreyhaines31/marketingskills54k1 repos~4.6kAutomated safety check: PassMIT

Similar skills

  • Referrals

    coreyhaines31/marketingskills

    When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy.

    54k GitHub starsUsed in 2 repos~2.6k tokens
    Marketing & SEOAuto-check passed

  • Referral Program

    freekmurze/dotfiles

    When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy.

    1k GitHub starsUsed in 17 repos~1.8k tokens
    Marketing & SEOAuto-check passed

  • 100m Leads

    getagentseal/founder-playbook

    Builds lead generation systems using Alex Hormozi's Core Four framework (warm outreach, content, cold outreach, paid ads), lead magnets, and Rule of 100.

    729 GitHub stars~2.3k tokensUpdated 3 days ago
    Marketing & SEOAuto-check passed

  • Churn Prevention

    freekmurze/dotfiles

    When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies.

    1k GitHub starsUsed in 13 repos~4.4k tokens
    Marketing & SEOAuto-check passed

  • Sms

    coreyhaines31/marketingskills

    When the user wants to plan, build, or optimize SMS, MMS, or WhatsApp marketing — including welcome flows, abandoned cart texts, post-purchase, win-back, promotional sends, or transactional/auth SMS.

    54k GitHub starsUsed in 1 repo~4.6k tokens
    Marketing & SEOAuto-check passed

  • Email Sequence Designer

    aaron-he-zhu/aaron-marketing-skills

    A skill your agent uses when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound…

    2.9k GitHub starsUsed in 2 repos~4.2k tokens
    Marketing & SEOAuto-check passed

More from rongxinzy/RongxinAI

All 94 skills in this repo

  • SaaS Metrics Coach

    rongxinzy/RongxinAI

    SaaS financial health advisor. An agent skill from rongxinzy/RongxinAI.

    154 GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check passed

  • Presentation Studio

    rongxinzy/RongxinAI

    The only skill for creating a new PowerPoint deck. An agent skill from rongxinzy/RongxinAI.

    154 GitHub stars~2.1k tokensUpdated today
    Auto-check passed

  • Zhiyuan Expert Manager

    rongxinzy/RongxinAI

    ZhiYuan Agent expert package lifecycle manager for the pi engine.

    154 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

  • Ziwei Doushu

    rongxinzy/RongxinAI

    Professional Ziwei Doushu consultation skill with an offline calculation engine.

    154 GitHub stars~746 tokensUpdated today
    Auto-check passed

  • Lark Mail

    rongxinzy/RongxinAI

    飞书邮箱：Use when user mentions 起草邮件、写邮件、草稿、发送/回复/转发邮件、查阅邮件、看邮件、搜索邮件、邮件文件夹、邮件标签、邮件联系人、监听新邮件、邮件收信规则等；use for mail/email intent only.

    154 GitHub starsUsed in 3 repos~4.1k tokens
    Auto-check: warnings

  • Cantian Bazi

    rongxinzy/RongxinAI

    以命理场景为主的八字排盘、黄历查询与大运/流年/流月/流日/流时区间查询技能。用于用户请求“算八字”“四柱排盘”“阳历/农历转八字”“查黄历/宜忌”“查未来10年流年”“查下个月流日/流时”等场景；关键词包括：八字、四柱、命理、大运、流年、流月、流日、流时、时辰、阳历转八字、农历转八字、黄历、宜忌、干支日期。真太阳时换算属于辅助能力，仅在需要校时定盘时使用。

    154 GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed

Categories

Questions about Churn Prevention

What does Churn Prevention do?

Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences. Churn Prevention is an agent skill from rongxinzy/RongxinAI. Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences.

When should I use Churn Prevention?

Churn Prevention fits situations like: optimizing a cancel flow; building save offers; setting up dunning emails; reducing failed-payment churn.

How do I install Churn Prevention in Claude Code?

Run `npx skills add rongxinzy/RongxinAI --skill churn-prevention -a claude-code`. Or copy the skill folder (SKILLs/churn-prevention in rongxinzy/RongxinAI) into .claude/skills/churn-prevention in your project. Claude Code loads it when a task matches its description.

How do I install Churn Prevention in Codex?

Run `npx skills add rongxinzy/RongxinAI --skill churn-prevention -a codex`. Or copy the skill folder (SKILLs/churn-prevention in rongxinzy/RongxinAI) into .agents/skills/churn-prevention in your project. Codex loads it when a task matches its description.

Can I use Churn Prevention in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rongxinzy/RongxinAI --skill churn-prevention -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/churn-prevention, .gemini/skills/churn-prevention, .github/skills/churn-prevention and .opencode/skills/churn-prevention in your project.

What does Churn Prevention need to run?

Going by SKILL.md and its folder, Churn Prevention needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Churn Prevention access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Churn Prevention safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Churn Prevention use?

Churn Prevention is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Churn Prevention use?

About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 10k tokens, read only when the agent opens those files.

What are the alternatives to Churn Prevention?

Skills that share tags, products or a category with Churn Prevention: Referrals (coreyhaines31/marketingskills, 54k stars), Referral Program (freekmurze/dotfiles, 1k stars), 100m Leads (getagentseal/founder-playbook, 729 stars) and Churn Prevention (freekmurze/dotfiles, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Churn Prevention?

rongxinzy (a GitHub organization) maintains it in rongxinzy/RongxinAI, which has 154 GitHub stars. The repository holds 94 skills in this directory. The repository was last updated on October 10, 2026.

Source: rongxinzy/RongxinAI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.