grow-app
Guided journey 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. Orchestrates eight skills phase by phase - hooked-ux, improve-retention, continuous-discovery, lean-ux, inspired-product, lean-analytics, microinteractions, drive-motivation - asking the user questions at every decision point and recording results in the project docs/ folder (PRODUCT.md, METRICS.md, GROW-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to lift activation and retention, de
npx skills add wondelai/skills --skill grow-app --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides a team through an eight-phase retention-focused growth journey for an app, asking questions at each decision point and recording outcomes in docs/ for continuity across sessions. It sequences phases from Hooked-UX to Drive-Motivation to fix activation and retention before acquisition, and ties each phase to specific artifacts in the docs/ folder.
How it works
- It starts by reading existing plan and artifacts in docs/ and resumes a tracker state if present; otherwise it creates a GROW-APP-PLAN.md and populates phase statuses.
- It invokes a phase by its slug (e.g., hooked-ux, improve-retention, continuous-discovery, lean-ux, inspired-product, lean-analytics, microinteractions, drive-motivation) with explicit instructions to elicit decisions, capture outcomes, and extend the relevant docs files.
- It asks concrete questions under Decide with the user, records decisions in the tracker, and presents draft artifact content for sign-off before writing into docs/ files.
- If a phase’s dedicated skill is unavailable, it proposes a fallback using a global install command:
npx skills add wondelai/skills/<slug> --global; if declined, it runs the phase from its Brief as a minimum viable method. - It enforces artifact discipline by creating or extending uppercase docs/ files with checkboxes or table rows, preserving existing content.
- It emphasizes retention before acquisition and uses a structured intake to set a baseline and update a single metric ( lean-analytics phase) and subsequent artifacts.
When to use it
Use when the user wants to lift activation and retention, design a habit loop, fix a leaky onboarding funnel, or when users sign up and disappear. It should not be used to fix broken UX or performance that engagement cannot salvage—run improve-app first; if there is no app yet, use create-app.
What it can touch
- Invokes phase skills by slug (e.g.,
hooked-ux,improve-retention,continuous-discovery,lean-ux,inspired-product,lean-analytics,microinteractions,drive-motivation). - Creates and extends docs/ files (e.g.,
docs/GROW-APP-PLAN.md,docs/PRODUCT.md,docs/METRICS.md,docs/EXPERIMENTS.md,docs/DESIGN.md,docs/CUSTOMER.md,docs/EXPERIMENTS.md,docs/OPPORTUNITY SOLUTION TREE NOTESand others as specified by phase). - Records decisions in the tracker and updates phase statuses and next actions.
Caveats
- The approach relies on explicit user confirmation at each phase entry and sign-off before writing artifacts.
- The backbone is eight phases; it explicitly instructs not to skip gating phases except where allowed (GATE deferment). It requires the user to confirm the plan before proceeding.
- It requires access to a docs/ folder with specific uppercase files and a tracker mechanism to persist state across sessions.
# Grow an App Your app has users who sign up and then quietly disappear — cohorts decay, daily actives are flat, the activation funnel leaks where it always has, and nothing looks obviously broken. This journey seals the bucket: it turns first-time users into activated, then habitual, then would-miss-it users across eight interactive phases. The agent asks before every decision and records the outcome in `docs/`, so the work resumes across sessions instead of restarting. Growth here is an engineering and design problem, not a bigger ad budget. ## Core Principle **Fix the leaky bucket before pouring in acquisition: habit, activation, and retention come before any growth spend.** This skill sequences the eight phases, asks every decision question, and records each choice in `docs/`. The constituent skills carry the method — invoke them rather than improvising their frameworks. ## Journey Map | Phase | Skill | Question it answers | Artifact | |---|---|---|---| | 1 | hooked-ux | Why do users come back without us paying? | Extends docs/PRODUCT.md | | 2 | improve-retention | Why don't new users reach the loop? | Extends docs/PRODUCT.md | | 3 | continuous-discovery | What do our own users
- Core Principle
- Journey Map
- Operating Rules
- Intake
- Phases
- Phase 1 — Design the habit loop that brings users back (hooked-ux)
- Phase 3 — Run continuous discovery so you stop guessing (continuous-discovery)
- Phase 4 — Replace debate with cheap experiments (lean-ux)
- Phase 5 — Build the right things with an empowered team (inspired-product)
- Phase 6 — Measure the one number that actually matters (lean-analytics)
- Phase 7 — Polish the micro-moments that make it feel alive (microinteractions)
- Phase 8 — Sustain engagement with intrinsic motivation (drive-motivation)
- Optional Phases
- Common Mistakes
What does the grow-app skill do?
Guided journey 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. Orchestrates eight skills phase by phase - hooked-ux, improve-retention, continuous-discovery, lean-ux, inspired-product, lean-analytics, microinteractions, drive-motivation - asking the user questions at every decision point and recording results in the project docs/ folder (PRODUCT.md, METRICS.md, GROW-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to lift activation and retention, de
How do I install it?
Run `npx skills add wondelai/skills --skill grow-app --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From wondelai/skills, a repository with 1,835 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.
