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, design a habit loop, fix a leaky onboarding funnel, or says 'users sign up then disappear'. Do not use to fix broken UX or performance that no engagement mechanic can paper over - run improve-app first; if there is no app yet, use create-app. For one framework in isolation, invoke that skill directly.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, well-structured orchestration skill with exemplary workflow sequencing, validation gates, and concrete per-phase instructions. Its main weakness is conciseness — the fallback briefs restate known frameworks — and a modest progressive-disclosure footprint with most phase detail inlined.

Suggestions

Tighten or relocate the per-phase 'Brief (fallback)' framework restatements (Hook Model, B=MAP, Lean Analytics stages, AMP) into a references file, since Claude already knows these; keep only the operative fallback steps inline.

Consider splitting the eight phase blocks into a per-phase reference file (e.g. references/phases.md) so SKILL.md reads as a tighter overview with the Journey Map as the navigation hub.

Add an explicit error-recovery loop for the case where a constituent skill fails to load and the fallback brief is insufficient (e.g. defer the phase and record the gap in the tracker).

Dimension	Reasoning	Score
Conciseness	The body is information-dense and well-organized, but the per-phase 'Brief (fallback)' sections restate frameworks Claude largely already knows (Hook Model, B=MAP, Lean Analytics stages, AMP) and could be tightened or moved to references.	3 / 5
Actionability	Highly actionable instruction-level guidance — exact skill slugs, exact docs/ section headings, specific 'Decide with the user' options, a concrete 'npx skills add' fallback command, and explicit done-when criteria — with a minor gap from depending on constituent skills that may be absent.	4 / 5
Workflow Clarity	Eight phases are sequenced via the Journey Map and Operating Rules, each with explicit 'Done when' validation gates, a Rule 6 sign-off-before-write feedback loop, GATE markers, and a final completion checklist.	5 / 5
Progressive Disclosure	Clear section structure with a well-signaled one-level reference (references/artifact-templates.md, verified present) and constituent skills loaded on demand; the per-phase briefs are inline, which is defensible for orchestration but is substantial inline content.	4 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A rich, well-scoped meta-skill description that concretely names its eight constituent skills, gives explicit positive and negative trigger conditions, and proactively disambiguates from neighboring skills. The only weakness is a slightly metaphorical opening framing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (orchestrates eight named skills, asks questions at decision points, records results in docs/, builds a habit loop, activated first run, one metric), though the opening 'sealed retention engine' framing is metaphorical rather than a literal action.	4 / 5
Completeness	Explicitly answers both what (an eight-phase guided journey that orchestrates skills and records in docs/) and when (a concrete 'Use when...' clause with multiple trigger phrases), plus negative-scope guidance.	5 / 5
Trigger Term Quality	Strong natural triggers — 'lift activation and retention', 'design a habit loop', 'fix a leaky onboarding funnel', and the quoted user phrase 'users sign up then disappear' — with good but not exhaustive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Clear niche as a retention/activation orchestrator with explicit disambiguation routing to improve-app, create-app, and individual framework skills, minimizing conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wondelai/skills
Path: grow-app/SKILL.md
Commit: c172996

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.