Guided Journey · Grow × App

Grow an App

Retention-first app growth

Takes you from an app people sign up for and then quietly abandon to a sealed retention engine with a habit loop, an activated first run, and one metric the whole team trusts. It orchestrates its eight skills phase by phase, asking you the decision questions at every step and recording every result in your project's docs/ folder so the journey resumes across sessions.

Updated 8 phases Free & MIT-licensed

What is the Grow an App journey?

Retention comes before acquisition here — buying users into a leaky app only costs more. Eight phases audit the habit loop, fix activation, install weekly discovery, choose which bets to build, settle on one honest metric and keep engagement intrinsic, recording each decision in docs/ so the journey resumes later.

Grow an App Retention-First

Users sign up, poke around, and vanish. Buying more of them won't help.

Our app's retention is too low — users sign up, poke around, and vanish. Run the grow-app journey — habit loops, activation, weekly discovery, and the One Metric That Matters — before any acquisition spend.

Use grow-app skill.
  • docs/PRODUCT.md
  • docs/CUSTOMER.md
  • docs/EXPERIMENTS.md
  • docs/METRICS.md
  • docs/DESIGN.md
  • docs/GROW-APP-PLAN.md journey tracker — stop anytime, resume any session

One prompt runs it

Every phase asks before it acts, and every decision lands in your project’s docs/ folder as a living document — quit anytime, resume in any session.

  • Grow an app whose retention can't yet support acquisition
  • Design ethical habit loops and fix activation friction
  • Replace opinion-driven roadmaps with weekly discovery
  • Choose the One Metric That Matters for your stage
  • Sustain engagement with intrinsic motivation, not gimmicks
npx skills add wondelai/skills/grow-app --global

This skill is compatible with Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent, and other agentskills.io-compatible agents.

Example prompts for the Grow an App journey

Users sign up and vanish — grow this app the retention-first way. using grow-app skill

Start the journey

Run the grow-app journey; start with the habit-loop audit. using grow-app skill

Habit-loop audit

Continue our app growth journey from the tracker. using grow-app skill

Resume journey

When to use Grow an App — and when not to

Reach for it when

  • Grow an app whose retention can't yet support acquisition
  • Design ethical habit loops and fix activation friction
  • Replace opinion-driven roadmaps with weekly discovery
  • Choose the One Metric That Matters for your stage
  • Sustain engagement with intrinsic motivation, not gimmicks

Reach for something else when

  • You want only a habit-loop teardown — Hooked UX gives you trigger, action, reward and investment on its own.
  • The app frustrates users in ways they can point at — Improve an App fixes usability, hierarchy and copy first.
  • Retention already holds and demand is the gap — Grow a Business builds the acquisition engine instead.
  • There is no shipped app yet to retain anyone — Create an App validates and builds one first.

Frequently asked questions

How do I install the Grow an App journey?

Run npx skills add wondelai/skills/grow-app --global. It takes about 30 seconds and needs no account. The Grow an App skill then works in Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw and Hermes Agent — anything that reads the open agentskills.io format — and your agent loads it on its own when a task calls for it. It is free and MIT-licensed, and the source is at https://github.com/wondelai/skills.

Which skills does the Grow an App journey run, and what does it produce?

It orchestrates 8 skills across 8 phases — Hooked UX, Improve Retention, Continuous Discovery, Lean UX, Inspired, Lean Analytics, Microinteractions, Drive Motivation — asking you one decision question per phase. Each answer is written to your project's docs/ folder (docs/PRODUCT.md, docs/CUSTOMER.md, docs/EXPERIMENTS.md, docs/METRICS.md, docs/DESIGN.md, docs/GROW-APP-PLAN.md), so the journey survives across sessions and you keep the reasoning, not just the output.

Why does acquisition never appear in this journey?

Deliberately. Eight phases in you have a habit loop, an activated first run, a discovery cadence and one metric — the conditions under which paid acquisition stops being a leaky bucket. Spending before that buys users who leave and hides the retention problem behind a rising signup chart. The journey’s position is that acquisition is a decision for after these eight phases, not during them.

Hooked and Drive both write to docs/PRODUCT.md and seem to disagree.

They are the check and the balance. Hooked UX designs the trigger-action-reward-investment loop that brings people back; Drive Motivation asks, in the final phase, whether that engagement will last or curdle into something users resent. Running them at opposite ends is the point — the last phase reviews what the first one built, and docs/PRODUCT.md carries both the loop and the honest verdict on it.

We already do user research. Is the discovery phase redundant?

Probably not, but say so and it will be short. Continuous Discovery is about cadence more than technique — weekly touchpoints with users, opportunity mapping, and assumption tests small enough to finish inside a sprint. If you already interview weekly, the phase confirms it and moves on to Lean UX. If research happens quarterly in one big burst, this is the phase that changes the most.

Does this work for a B2B tool people are told to use?

Yes, with one adjustment. The habit loop still applies — the trigger is often a colleague’s message rather than a notification — but the Drive Motivation phase carries more weight, because mandated software is exactly where extrinsic motivation runs out. Expect Continuous Discovery to be the hardest phase to staff: reaching users weekly is harder when they are someone else’s employees.

Install Grow an App

Free, open-source, and ready in 30 seconds.

npx skills add wondelai/skills/grow-app --global

MIT Licensed · Works with Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent & other agentskills.io agents · No account needed

Work with us

We build the skills you already use. Now we’ll build yours.

Custom skills · Subagents · MCP integrations — shipped to production, not demoed.

Sprints from $3K · shipped to production, or you don’t pay the final milestone.