Build Cancellation Flow logo

Build Cancellation Flow

Community
khadinakbarlabs
build-cancellation-flow

Build a cancellation / churn-interception flow with an exit survey, reason-matched save offers, and graceful exit — preserving rating and recovering 10–35% of cancellations. Use when the user says 'cancellation flow', 'cancel survey', 'save offer', 'prevent churn', 'subscription cancel', 'downgrade flow', or 'retention offer'.

Overview

Publisherkhadinakbarlabs
Repositoryexpo-mobile-app-builder
Skill namebuild-cancellation-flow
Stars
3
Forks
0
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Build Cancellation Flow 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/khadinakbarlabs/expo-mobile-app-builder/tree/main/skills/build-cancellation-flow
  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/khadinakbarlabs/expo-mobile-app-builder.git /tmp/expo-mobile-app-builder
mkdir -p .claude/skills
cp -r /tmp/expo-mobile-app-builder/skills/build-cancellation-flow .claude/skills/build-cancellation-flow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Build Cancellation Flow 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 Build Cancellation Flow 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 Build Cancellation Flow 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.

Build a cancellation flow

The screen a user sees when they hit "cancel subscription" is one of the highest-leverage revenue surfaces in a subscription app. A well-designed flow saves 10–35% of cancellations (offer acceptance 15–25%, pause reactivation 60–80%); even a simple survey + one offer saves 10–15% over an instant cancel. This skill designs it.

The canonical structure

text
Trigger (user taps Cancel)
  → Survey (why are you leaving?)
    → Reason-matched save offer
      → Accept (saved) | Defer (pause) | Confirm cancel (graceful exit)
        → Post-cancel: win-back eligibility + email capture

The exit survey

5–8 reason options + free text. Framing matters: "Help us improve" beats "Why are you leaving?" — it reduces defensiveness and raises completion.

Typical reasons (match these to the product):

  • Too expensive
  • Not using enough
  • Missing a feature
  • Found an alternative
  • Technical issues / bugs
  • Just needed it temporarily
  • Hard to use
  • Other (free text)

Capture the reason in your analytics (instrument-growth-funnel) tied to the user. The reason is also the input to the save offer and to product roadmap prioritization.

Reason-matched save offers

Don't show every canceler the same offer. Match the offer to the reason:

Cancel reasonPrimary offerFallback
Too expensive20–30% off for 2–3 monthsDowngrade to a cheaper tier
Not using enoughPause 1–3 months (keeps access, stops billing)Free onboarding / usage nudge
Missing featureRoadmap + timeline for the requested featureA workaround or alternative path
Technical issuesEscalate to support immediately; credit + priority fixFree month while they wait
Found alternativeDifferentiated value recap + offerGraceful exit (don't badger)
Temporary usePause or annual at a discount for next cycleGraceful exit

Discount guardrails (avoid training cancel-for-deals)

  • Sweet spot: 20–30% off for 2–3 months. Enough to matter, short enough to not devalue.
  • Avoid routine >50% off. Trains users to cancel expecting a deal; they'll repeat the cycle.
  • Show the dollar amount, not just the percentage. "$4 off for 3 months" lands better than "25% off."
  • Time-limit the offer. "Claim by [date]" — but only a real deadline, not a fake countdown (Apple rejects fake urgency).
  • One offer per cancel session. Don't cascade discounts if they reject the first.

Pause as an alternative to cancel

A "pause for 1–3 months" option (billing stops, access preserved or reduced) reactivates at 60–80% vs much lower reactivation after a full cancel. Where the billing systems support it, offer pause prominently. StoreKit 2 doesn't have a native "pause," but you can implement it via a free-trial/promotional-offer bridge or by letting the subscription lapse and re-engaging. Google Play supports pausing natively in some configurations.

Graceful exit (non-negotiable for your rating)

Keep "Continue cancelling" visible and one tap away at every step. No dark patterns. The FTC's Click-to-Cancel rule requires cancellation to be at least as easy as sign-up. A user who feels trapped by a cancellation flow leaves a 1-star review. See build-review-routing — the same unhappy-user principle applies.

After confirming cancel:

  • Capture an email (if not already on file) for win-back. See build-win-back-flow.
  • Keep premium access until the period ends (they paid for it).
  • Subscribe to server notifications (SUBSCRIPTION_CANCELED) to distinguish cancel-but-active from genuinely lapsed.

Implementation (RevenueCat)

RevenueCat exposes customer info and entitlement state. Build the survey + offer UI yourself; present the offer as a StoreKit promotional offer or a RevenueCat-managed discount:

tsx
import Purchases from 'react-native-purchases';

// On cancel-reason selected, present the matched offer
async function presentSaveOffer(reason: CancelReason) {
  const offer = matchOfferToReason(reason); // your mapping
  // present the offer as a promotional offer / discounted package
  const offerings = await Purchases.getOfferings();
  const pkg = offerings.all?.[`save_${reason}`];
  // show pkg in a save-offer sheet; if accepted:
  // const { customerInfo } = await Purchases.purchasePackage(pkg);
}

Track the funnel: cancel_started, cancel_survey_completed {reason}, save_offer_presented {type}, save_offer_accepted, cancel_confirmed, cancel_paused.

What not to do

  • No multi-step mazes that make cancel hard. FTC Click-to-Cancel + App Review both penalize this.
  • No fake countdowns on the save offer.
  • No guilt-trip copy ("Are you sure you want to give up on your goals?"). Confirmshaming is a dark pattern and a rating killer.
  • No repeated discount escalation if they reject the first offer.
  • No blocking the cancel behind a support chat (chat is fine as one option, not a gate).

Pair with

  • integrate-revenuecat-rn — entitlement state and promotional offers.
  • app-store-server-notifications / app-store-server-notifications-android — cancel vs lapsed signals.
  • build-win-back-flow — the post-cancel recovery arm.
  • pricing-strategy — discount guardrails.
  • instrument-growth-funnel — measuring save rate by reason.

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 Build Cancellation Flow AI skill do?

Build a cancellation / churn-interception flow with an exit survey, reason-matched save offers, and graceful exit — preserving rating and recovering 10–35% of cancellations. Use when the user says 'cancellation flow', 'cancel survey', 'save offer', 'prevent churn', 'subscription cancel', 'downgrade flow', or 'retention offer'.

Why use Build Cancellation Flow on TypingMind?

Because you install it once and use it with any model. Build Cancellation Flow 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 Build Cancellation Flow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/khadinakbarlabs/expo-mobile-app-builder/tree/main/skills/build-cancellation-flow. 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 Build Cancellation Flow?

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 Build Cancellation Flow?

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

Is the Build Cancellation Flow AI skill free?

Yes. It is published on GitHub by khadinakbarlabs 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 👇