← 开源
adamlyttleapps

claude-skill-app-onboarding-questionnaire

A Claude Code skill that designs and builds high-converting questionnaire-style app onboarding flows — modelled on proven conversion patterns from top subscription apps like Mob, Headspace and Noom

AI EngineeringPrompt & ScaffoldBuild agent workflow (SDK)
在 GitHub 打开
增长势头
+-124 小时新增 Star-0.1%
1.22k
Star
117
Fork
+3
本周
1
贡献者
创建于 2026-04-06 · 更新于 2026-10-15 · 今日第 18918 名
主要开发者
adamlyttleapps

adamlyttleapps/claude-skill-app-onboarding-questionnaire 排名第 18,918,有 1,218 个星标。

同类别比较

adamlyttleapps/claude-skill-app-onboarding-questionnaire 排名第 18,918,此处有 8 个同类条目;microsoft/RecAI 排名第 18,922。

同类别比较
名称排名指标
rinadelph/Agent-MCP18,899
语言:
TypeScript
星标数:
1,302
分叉数:
183
简介:
Agent-MCP is a framework for creating multi-agent systems that enables coordinated, efficient AI collaboration through the Model Context Protocol (MCP). The system is designed for developers building AI applications that benefit from multiple specialized agents working in parallel on different aspects of a project.
ScalingIntelligence/KernelBench18,903
语言:
Jupyter Notebook
星标数:
1,292
分叉数:
198
简介:
KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
sums001/Windows-Copilot-API18,910
语言:
Python
星标数:
1,253
分叉数:
405
简介:
Reverse engineered Windows Copilot into an OpenAI-compatible API. Access GPT-4 and GPT-5 models through a simple REST interface without API keys or billing.
stanford-iris-lab/meta-harness-tbench2-artifact18,912
语言:
Python
星标数:
1,234
分叉数:
169
简介:
Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)
microsoft/RecAI18,922
语言:
Jupyter Notebook
星标数:
1,203
分叉数:
130
简介:
Bridging LLM and Recommender System.
clacky-ai/openclacky18,924
语言:
Ruby
星标数:
1,201
分叉数:
114
简介:
The most Token-efficient open-source AI Agent
mrkrsl/web-search-mcp18,929
语言:
TypeScript
星标数:
1,180
分叉数:
161
简介:
A simple, locally hosted Web Search MCP server for use with Local LLMs
parcadei/llm-tldr18,931
语言:
Python
星标数:
1,166
分叉数:
114
简介:
95% token savings. 155x faster queries. 16 languages. LLMs can't read your entire codebase. TLDR extracts structure, traces dependencies, and gives them exactly what they need.
关键参数与规格
关键参数与规格
参数值
类别AI Engineering
子类别Prompt & Scaffold,Build agent workflow (SDK)
关键词Context engineering, Design, Prompt engineering, Writing
星标数1,218
分叉数117
贡献者1
创建日期2026-04-06
更新日期2026-10-15
1 天星标数-1
7 天星标数3
排名18,918
上次排名4,081
排名变化-14,837
7 天星标排名7,017
上次 7 天星标排名5,622
7 天星标排名变化-1,395
总星标排名9,591
上次总星标排名9,573
总星标排名变化-18
国家Australia
README 摘录

What It Does Run from your app project and the skill will: 1. **Analyse your codebase** to understand what your app does, who it's for, and what permissions it needs 2. **Design a screen-by-screen blueprint** using a proven 14-screen psychological framework 4. **Build the onboarding flow** in your app's native framework (SwiftUI, React Native, Flutter, etc. What Makes This Different Most onboarding generators stop at the questionnaire. They DO something and get a tangible result back. This

is where organic growth comes from. ) and creates benefit-framed priming screens that convert at 70-80%+ vs ~40% for cold system prompts. Come back tomorrow and pick up where you left off. Installation Option 1: Add to your Claude Code skills directory Option 2: Add as a dependency in your project's Usage From your app's project directory in Claude Code: The skill will analyse your codebase and walk you through each phase interactively. Reference The framework is based on

analysis of the Mob recipe app's onboarding flow (19 screens), which is widely regarded as one of the best-converting onboarding experiences in the App Store.

常见问题

记录了多少星标和分叉?

adamlyttleapps/claude-skill-app-onboarding-questionnaire 有 1,218 个星标和 117 个分叉。

仓库排名是多少?

adamlyttleapps/claude-skill-app-onboarding-questionnaire 排名第 18,918。

哪个仓库排名最接近?

adamlyttleapps/claude-skill-app-onboarding-questionnaire 与 microsoft/RecAI 比较,后者排名第 18,922,有 1,203 个星标。

README

App Onboarding Questionnaire

A Claude Code skill that designs and builds high-converting questionnaire-style onboarding flows for your app — modelled on proven conversion patterns from top subscription apps like Mob, Headspace, Noom, and Duolingo.

What It Does

Run /app-onboarding-questionnaire from your app project and the skill will:

  1. Analyse your codebase to understand what your app does, who it's for, and what permissions it needs
  2. Define the user transformation — the before/after story that drives your onboarding narrative
  3. Design a screen-by-screen blueprint using a proven 14-screen psychological framework
  4. Draft all the copy — headlines, questions, options, CTAs, social proof
  5. Build the onboarding flow in your app's native framework (SwiftUI, React Native, Flutter, etc.)

No marketing expertise required. The skill handles the conversion psychology — you just answer questions about your app.

The Framework

The onboarding follows a proven psychological sequence used by the highest-converting subscription apps:

# Screen Purpose
1 Welcome Hook — show the end state, create desire
2 Goal Question "What are you trying to achieve?" — creates psychological investment
3 Pain Points "What prevents you?" — surfaces frustrations, builds empathy
4 Social Proof Testimonials matched to user personas
5 Tinder Cards Swipe agree/disagree on pain statements — interactive self-identification
6 Personalised Solution Mirror their pains back with stats showing how the app solves each one
7 Comparison Table Life with vs without the app (optional)
8 Preferences Functional personalisation that feeds the upcoming demo
9 Permission Priming Benefit-framed pre-sell before system permission dialogs (auto-detected)
10 Processing Moment "Building X just for you..." — anticipation builder
11 App Demo User actually USES the core app mechanic — not a tour, a real interaction
12 Value Delivery Tangible output from their demo + share/viral moment
13 Account Gate Optional sign-in to unlock what they just created
14 Paywall Hard paywall with trial, social proof, and pricing

Not every app needs every screen — the skill adapts based on your app's complexity.

What Makes This Different

Most onboarding generators stop at the questionnaire. This skill goes further:

  • App Demo Screen — Builds a functional mini-version of your app's core interaction inside the onboarding. Users pick recipes, choose exercises, categorise transactions — whatever your core loop is. They DO something and get a tangible result back.
  • Viral Moment — The demo output is designed to be shareable. This is where organic growth comes from.
  • Permission Priming — Auto-detects permissions from your codebase (Info.plist, AndroidManifest, etc.) and creates benefit-framed priming screens that convert at 70-80%+ vs ~40% for cold system prompts.
  • Resumable — Progress is saved to Claude Code's memory system. Come back tomorrow and pick up where you left off.

Installation

Option 1: Add to your Claude Code skills directory

cd ~/.claude/skills
git clone https://github.com/adamlyttleapps/claude-skill-app-onboarding-questoinnaire.git app-onboarding-questionnaire

Option 2: Add as a dependency in your project's .claude/settings.json

{
  "skills": [
    "github:adamlyttleapps/claude-skill-app-onboarding-questoinnaire"
  ]
}

Usage

From your app's project directory in Claude Code:

/app-onboarding-questionnaire

The skill will analyse your codebase and walk you through each phase interactively.

Reference

The framework is based on analysis of the Mob recipe app's onboarding flow (19 screens), which is widely regarded as one of the best-converting onboarding experiences in the App Store.

License

MIT

排名相邻
同类项目