The growth-advisor skill answers “what should I test next?” from your own subscription numbers. Your AI coding tool reads your analytics, placements, paywalls, and products through the Adapty CLI, follows the biggest signal down to a cause, and returns a short list of hypotheses to A/B test, ranked by the purchases each one puts at stake.

What you can ask

Ask the way you’d brief a colleague. You don’t need to name the skill:

Audit my app. What should I test next to grow revenue?

Revenue dropped last month. Why?

My A/B test on the onboarding paywall ended and the new version won. What now?

I have three ideas: a weekly plan, a trial on annual, and a second placement.
Which one should I test first?

Which country refunds the most, and do people who start a trial renew better?

We launch next month and have no data yet. Where should we start?

A question about your numbers gets an answer from your numbers, with no audit attached. An app with no data yet gets a starting plan built from market medians in Adapty’s State of Paywalls 2026 report, with every number labeled as an estimate.

growth-advisor

>

Revenue dropped last month. Why?

⏺Ran 4 read-only commands

• adapty analytics chart --chart revenue --compare-from 2026-08-01 --compare-to 2026-08-31
• adapty analytics chart --chart revenue --group-by store
• adapty analytics chart --chart subscriptions_new --group-by store
• adapty analytics chart --chart subscriptions_expired --group-by cancellation_reason

⏺

Your revenue dropped because fewer people renewed on Google Play, not because fewer people bought.

New subscriptions held steady in September. Renewals on Google Play fell by a third, while the App Store didn’t change. Most of the lost renewals are monthly subscribers whose payment failed.

Next steps

1. You: did anything change in your Google Play billing setup in early September?
2. Me: suggest hypotheses to win back the monthly subscribers who left. Want me to?

>

Before you start

• An Adapty account with data: The skill reads the same analytics your dashboard shows. Without data, it can only give you a starting plan.
• An AI tool that can run the Adapty CLI: For example, Claude Code, Codex, Copilot CLI, or Gemini CLI, or the Claude app after you set up the CLI there. The skill reads your data through the CLI. With only the Adapty MCP server, the skill offers to set up the CLI first. Without the CLI, it skips the reads that need it and names them.

Install the skill

growth-advisor is part of the adapty-skills plugin.

To install the plugin, in your terminal, run:

npx adapty skills install

Restart your agent to load the skills. For other installation methods, see the plugin README.

Claude Code doesn’t update the plugin on its own. To get new skills as they ship, in Claude Code, run /plugin, open Marketplaces, select adapty, and choose Enable auto-update. For the update command in other agents, see the plugin README.

How the audit works

When you ask what to do without a specific question, the skill runs an audit. It reads your numbers and your placement setup, works out what you’ve already tried, and follows the biggest change down to the store, channel, country, or placement that explains it. Before it says anything about a screen, it looks at the live flow, or asks you for a screenshot of a paywall your app draws itself.

What you get back

The skill replies with a short answer, then a list of hypotheses grouped by placement, in the order to test them. Each hypothesis says why your app needs it, what result to expect and where that estimate comes from, how long the A/B test would take, and who does what. A hypothesis can target everyone at a placement or one segment, such as former subscribers.

growth-advisor

>

Audit my app. What should I test next to grow revenue?

⏺Ran 9 read-only commands

• adapty apps list
• adapty analytics chart --chart revenue --group-by country
• adapty analytics chart --chart revenue --group-by duration
• adapty analytics chart --chart subscriptions_new --group-by placement_id
• adapty analytics chart --chart subscriptions_expired --group-by cancellation_reason
• adapty analytics conversion --conversion trial-paid --granularity month
• adapty placements list
• adapty flows list
• adapty flows config get <flow-id>

⏺

Most of your revenue comes from the onboarding paywall, and almost everyone there buys the weekly plan.

From your data: two onboarding paywalls ran side by side in July, and you kept “Main”. Annual is on the screen but took 6% of purchases in September. Most subscriptions end with users switching off renewal, and no placement shows former subscribers anything different.

Suggested hypotheses

On the onboarding placement:

1. Pre-select the annual plan on “Main”

• Why: Weekly is pre-selected on “Main”, so most buyers never weigh the yearly price.
• Expected: ARPU up 25–40%, judged by revenue per paywall view. This is one of the most reliable wins in Adapty’s library of real subscription A/B tests.
• Time: About 3 weeks at your purchase volume.
• Who: Me: build the flow copy and set up the A/B test. You: publish the copy.

On the settings placement:

2. Show former subscribers a win-back paywall

• Why: 71% of endings in September were users switching off renewal, and they see the same paywall as everyone else when they come back.
• Expected: Untested in Adapty’s library, so treat it as a bet. Judged by purchases from the segment.
• Time: About 8 weeks.
• Who: Me: build the win-back flow, create the “Former subscribers” segment, and set up the A/B test for it. You: publish the flow.

Next steps

1. You: which one do you want to start with? I’d pick 1, because every new user sees it.
2. Me: build a copy of “Main” with the annual plan pre-selected. Want me to?

>

Go with 1.

Create a flow copy

Create Main – annual pre-selected, a copy of “Main” with the annual plan pre-selected? Nothing else changes, and the live flow stays as it is.

1. Yes
2. No, change something first

>

You pick which hypothesis to start with. If you’re not sure, the skill names its own pick and why. The skill keeps no backlog, so save the reply if you want to come back to the other hypotheses later.

From hypothesis to A/B test

For every hypothesis, the skill suggests an A/B test and offers to set it up. Before it does, it verifies that everything the test needs exists, and names what is missing and who makes it:

The test needs	Who makes it
A changed flow: a new design, copy, or product set	The skill builds a copy of the flow through the flow-generator skill, with one change per hypothesis, so the test shows what that change did. Before you publish the copy, the skill offers to review the copy with the flow-audit skill. A flow joins a test only once it is published.
A new plan length, trial, or offer	You create the product in App Store Connect or Google Play Console and add it to Adapty. On the App Store, a trial needs a new product; on Google Play, it’s an offer on the existing plan. You set the price.
A paywall from products already in Adapty	The skill creates it.
A paywall with a new design	You make it in the Paywall Builder.
A segment	The skill creates it through the audiences skill.
A new placement	The skill creates it after you approve its developer ID. Your app needs a code change and a release to fetch it.

Each piece the skill makes waits for your yes. When a piece is yours to make, the skill’s Next steps list says so, and the skill sets up the test once you tell it the piece is ready. It never sets up a test with a piece that doesn’t exist yet.

When every piece exists, the ab-tests skill creates the test as a draft. Before it starts the test, it shows you exactly who sees what. An A/B test is the default, and the only way to measure what the change did.

To show the change without a test, ask for that. The skill can show it on a new placement, or to some or all users of an existing placement. Before the skill changes an existing placement, it saves the placement to a file so you can restore it. It also names any A/B test that runs on the placement. The change doesn’t affect that test.

When an A/B test ends, tell the skill which version won. It offers to stop the test with that winner if the test is still live. Then it suggests the next hypothesis.

Limits

• No pricing analysis yet: The skill doesn’t read, compare, or suggest prices. When your numbers point at price, it says so and says that pricing analysis isn’t supported yet.
• No A/B test results: The skill doesn’t read A/B test results. It infers past tests from paywalls that ran side by side, and relies on you to say which version won.
• No ad spend: The skill can split installs, trials, and revenue by attribution channel, but not spend or ROAS. For those, use the adapty-attribution skill.

To query your analytics yourself, without the skill, see the CLI analytics reference. To pull analytics from a server or a scheduled job, where no one can log in through a browser, use the Export Analytics API with a secret API key.