This is taking longer than expected.

Try againBrowse the library
AI Blocks

All AI specialists

Hire an AI subscriber cancellation and retention reviewer

Review when subscribers cancel and what they said. Compare earlier changes and propose a focused retention fix.

What you give

  • Last month's cancels with date, order number and reason
  • Each email you sent to subscribers, with the cancels and starts that followed
  • Your save rate from the cancel portal

What you get

  • A score out of 100 in four parts, against last month
  • Cancels by days since the first order, with the biggest spike named
  • A verdict on last month's fix, helped, no change or worse
  • One fix, written and ready for you to approve

An example

You sell subscriptions and want one monthly check on where people leave.

You ask: “Review when subscribers cancel and what they said. Use the material I attach and ask for anything essential that is missing.”

You get back:

  • This month. Your churn score out of 100 and the four part scores, each shown against last month.
  • Last month's fix. Whether the part you fixed helped, made no change or got worse, with the numbers.
  • Where subscribers leave. Cancels grouped by days since the first order, with the biggest spike named.

An example, not your task.

Hire this specialist

It is free and needs no account. Download the pack, give it to your AI and tell it the job. Your AI asks for anything it is missing, then does the work and checks it.

Download the specialist

Related specialists

Skills and workflows for this job: Keep customers coming back

Details

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

  • A score out of 100 in four parts, against last month
  • Cancels by days since the first order, with the biggest spike named
  • A verdict on last month's fix, helped, no change or worse
  • One fix, written and ready for you to approve
  • The one number to watch next month

How it does the job well

  • Write for one named audience and one action. Each asset has a single job.
  • Use the customer's own words from reviews, calls or surveys before inventing language.
  • Every claim needs proof the business can show. Leave unproven claims out or mark them.
  • Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

  • Scoring or chasing monthly churn alone. Show it, but fix the part that explains it.
  • Trusting the benchmarks as promises. They come from daily products such as supplements and drinks. Compare with the store's own history.
  • Fixing three parts at once. You cannot tell which one worked.
  • Offering discounts as saves without the owner's margin limit.
  • Generic copy that could fit any brand.
  • Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.

What a good result looks like

An example, not your task: You sell subscriptions and want one monthly check on where people leave.

  • This month. Your churn score out of 100 and the four part scores, each shown against last month.
  • Last month's fix. Whether the part you fixed helped, made no change or got worse, with the numbers.
  • Where subscribers leave. Cancels grouped by days since the first order, with the biggest spike named.
  • The fix chosen. The weakest part, the skill that ran for it and why it was picked.
  • Changes to approve. Each change, where it goes and why, with the most important first.
  • Watch next month. The one number that shows whether the fix worked.

How the work is checked

  • Every score change shows both months and the sum.
  • Only the lowest part was fixed, plus onboarding only when most cancels fall in days 0 to 14.
  • Every threshold is marked as the source's or ours, as the audit marks them.
  • No claim of what a fix will save is made. Say what to watch instead.
  • States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

  • Check it is worth running. With fewer than a few hundred subscribers the day-by-day chart is too thin, so it marks its findings as guesses.
  • Read last time. Opens last month's saved scores and the fix it chose.
  • Run the audit. Scores where subscribers leave in four parts and shows the change in each.
  • Check the last fix. Says whether the part you fixed moved the right way. A small move counts as no change.
  • Choose the one fix. Takes the weakest part and runs the matching skill. Billing emails, a cancel flow, send rules or a page check.
  • Add early-days help. If most cancels come in the first 14 days, it also writes an onboarding plan.
  • Save and hand back. Saves a summary and stops for your yes.

How the role works

  1. Checks your task, context and available tools.
  2. Picks the methods needed and prepares a work plan.
  3. Carries out supported tasks, with each method's limits and review gates.
  4. Checks the real deliverables and corrects supported faults.
  5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id subscription-churn-watcher only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/subscription-churn-watcher/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

  • Last month's cancels with date, order number and reason
  • Revenue per customer by month and a first-order subscription flag, if you have them
  • Each email you sent to subscribers, with the cancels and starts that followed
  • Your save rate from the cancel portal
  • Your products, brand file and offer limits, for the emails

Helpful context (optional)

  • A note of every change you made to subscription emails or settings last month
  • The dates and contents of every campaign sent to subscribers

Tools and access

  • Claude Code: It can keep the keeper folder, read last month's files and run on a monthly schedule.
  • Your subscription app: Export cancels with date, order number and reason, and the save rate from the cancel portal.
  • Skio or Recharge: Paid subscription apps; use the one you already have. Their exports give cancel dates, order numbers and reasons.
  • Klaviyo: Paid email service that needs an account. It gives sends and the cancels that follow each one when you connect your subscription app.
  • Any good chat AI: Any current chat AI that reads a spreadsheet can run the audit.
  • Klaviyo: It can pull next order date, items and order number into the email and build a different version for each rebill number. It is a paid service.
  • Skio or Recharge: Your subscription app supplies the one-click delay, skip, swap and manage links. Both are paid apps.
  • Shopify: Your plan decides whether you can turn off the built-in order confirmation. You need a paid Shopify plan.
  • Klaviyo: Paid email service that needs an account and a connected subscription app. It lets you leave active subscribers out of segments and shows cancels after each send when you connect your subscription app.
  • Skio or Recharge: Paid subscription apps; use the one you already have. Your subscription app holds churn by order number and the add-on to a next order.
  • Any good chat AI: Any current chat AI can turn your numbers into the plan.
  • Skio: It supports a splash screen, branching by reason and flows by payment type failure. It is a paid app.
  • Recharge: It has a customer portal with cancel flows and skip and delay settings. It is a paid app.
  • Klaviyo: It sends the post-cancel, win-back and failed-payment emails and texts. It is a paid service.
  • Klaviyo: Paid subscription. It can send on the delivered event (step 10), branch subscribers from one-time buyers and run email and SMS from one flow. The delivered-event trigger may need a paid plan.
  • Any good chat AI: Any current chat AI can write the copy once you give it the facts.
  • A subscription app such as Skio or Recharge: Paid subscription. It tells you who is a subscriber and when the next order ships (steps 4 and 8).
  • Any good chat AI: Any current chat AI that reads images can score the screens. Attach phone and desktop views.
  • Shopify: Paid plan needed. Your theme editor or a split-testing app shows which version of the page each buyer saw.
  • Skio or Recharge: Paid subscription apps; the fixes land in the one you already use. Your subscription app sets the default selection, the plans shown and the cart upgrade, so the fixes land there.

Functions and deliverables

  • Subscriber cancellation and retention reviewer: Review when subscribers cancel and what they said. Compare earlier changes and propose a focused retention fix.
    • A score out of 100 in four parts, against last month
    • Cancels by days since the first order, with the biggest spike named
    • A verdict on last month's fix, helped, no change or worse
    • One fix, written and ready for you to approve
    • The one number to watch next month
  • Subscription churn auditor: Find where subscribers cancel with a subscription churn audit. Give it your cancel data. You get a score out of 100 and your top three fixes.
    • A score out of 100 and the four numbers behind it
    • A chart of cancels by days since sign-up, with spikes labelled
    • A list of emails that caused more cancels than starts
    • The top three fixes, each pointing to the right skill
  • Billing reminder and confirmation writer: Share subscription plans, gift timing and email tools. Get billing reminders, order emails, link setup steps and a test plan.
    • A billing reminder template, with a version for each rebill number (1 to 6)
    • An order confirmation template for first orders, rebills and one-time orders
    • A link setup list: one-click delay, skip, swap and manage, and where cancel sits
    • An A/B test plan against your current emails
  • Subscriber retention calendar planner: Plan gifts and sends to keep subscribers. Give it your churn and gift costs. You get a subscriber retention calendar with send rules and a sale offer.
    • An order-by-order plan: gift, reminder version and any message
    • Subscriber send rules: exclusions, a cap and content types
    • A calendar of one to three campaigns a month for subscribers
    • A subscriber-only add-on offer for your next sale
  • Subscription cancel flow builder: Build a subscription cancel flow with one save offer per cancel reason, delay rules and a failed-payment plan, from your reasons and portal limits.
    • A cancel flow map: start screen, reason question, one action for each reason
    • Offer copy for each branch, and skip and delay settings
    • A proactive pause email, post-cancel emails, and a win-back test plan
    • A failed-payment flow for each payment type, and a tracking sheet for save rate by reason
  • New customer onboarding sequence writer: Write a new customer onboarding email sequence and SMS plan for days 0 to 14, plus a 100-day touch map, from your product facts.
    • A day-by-day send plan for days 0 to 14 (email and SMS) and a touch map out to day 100
    • Full copy for about six emails and four texts
    • A pre-arrival sequence and a welcome insert
    • A review and referral timing rule for each product, and a survey to find the habit linked to staying
  • Subscription signup page reviewer: Check your subscription page for the fixes that raise how many first orders pick subscription. Get a score out of 100 and a test plan.
    • A score out of 100, with the rule each point came from
    • A list of conflicts between pop-up, page and cart
    • Ranked fixes, with the one change most likely to raise take rate
    • A short test plan for the top two fixes
  • Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
    • A folder of eight plain files, from a start file for your AI to a claims list and a change log
    • A tag on every fact, and every claim marked approved, pending or banned
    • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
    • A short slice for your next step, if you name one

Tasks you can use it for

  • You sell subscriptions and want one monthly check on where people leave.
  • Churn moved and you do not know which part changed.
  • You made a change last month, such as new billing emails, and want to know if it helped.

Limits to check before starting

  • You have only a few hundred subscribers or fewer: the day-by-day chart is too thin, so treat the result as a rough guess or run the Subscription churn auditor alone.
  • You sell one-off orders with no repeat billing: use a plain repeat-purchase check in your shop reports instead.
  • You want emails sent or your subscription app changed for you: this agent only lists changes, so make them yourself in your own tools.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

  • Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run this month's check.
  • Export last month's cancels and your sends to subscribers from your subscription app and email tool. Put them in one folder, or attach them in the chat.
  • Add your cancel reasons in your customers' own words if you can. A cancel flow needs them.
  • Read the fix and the change list. Make the changes you agree with in your tools. Nothing goes out until you do.
  • Run it again next month. It compares against its saved summary.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/subscription-churn-watcher for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.