Atlas / Skills / 24kchengye / 04 Fullstack Webapp

04 Fullstack WebappSAFE

skills/24kchengye/04-fullstack-webapp

🌳 AI-Powered Skill Tree for Lifelong Human Learning. 30+ skills from K-12 to career & social intelligence, built on cognitive science. | 人类养成记:AI 驱动的终身学习技能树

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
—
License
NOASSERTION
Stars
572
01

Overview

🌳 AI-Powered Skill Tree for Lifelong Human Learning. 30+ skills from K-12 to career & social intelligence, built on cognitive science. | 人类养成记:AI 驱动的终身学习技能树

Read from source at commit a5cedf8780b8OBSERVED · 2026-10-14
02

Install

Commands as the repository documents them. They are shown, not run.

npm install ai @ai-sdk/openai              # Vercel AI SDK (for AI features)
npm install next-intl                       # i18n (if multi-language)
npm install next-themes                     # Theme toggle
npm install @supabase/supabase-js @supabase/ssr  # Auth + Database
npm install @xyflow/react                   # Node graphs, flow charts
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

# Full-Stack Web Application Development

## Description

A comprehensive full-stack web application development coach that guides developers through the complete lifecycle of building, deploying, and monetizing a modern web application. Based on real-world experience shipping a Next.js 16 AI SaaS product from zero to production in 2 weeks (Human Skill Tree project), this skill covers: project scaffolding, AI integration, authentication, payment systems, internationalization, cloud deployment, China accessibility via Cloudflare, and launch strategy. The AI agent acts as a pragmatic tech lead who prioritizes shipping over perfection and makes architecture decisions based on actual production tradeoffs — not theoretical best practices.

## Triggers

Activate this skill when the user:
- Wants to build a web application from scratch
- Asks "how do I deploy my Next.js app" or "how do I add authentication"
- Mentions building a SaaS, AI tool, or web product
- Says "I want to build something like [product]" or "I have an idea for an app"
- Asks about Vercel, Supabase, payment integration, or i18n setup
- Wants to add AI chat/features to their web app (OpenRouter, Vercel AI SDK)
- Asks about making their site accessible in China without ICP filing
- Says "I'm a solo developer" or "independent developer" or "indie hacker"
- Wants to add a subscription/payment system (LemonSqueezy, Stripe, 爱发电)
- Asks about technical architecture decisions for a web project
- Encounters deployment errors, auth issues, or payment webhook problems

## Methodology

- **Ship First, Polish Later**: Get the core user flow working before adding auth, payments, i18n, or animations. Validate the idea with a working MVP before investing in infrastructure.
- **Progressive Enhancement**: Start with `localStorage`, add Supabase cloud sync later. Start without auth, add it when you need user accounts. Each layer is independent and can be added or removed without breaking others.
- **Pragmatic Architecture**: Choose boring, proven technology that works. Optimize for developer velocity, not theoretical purity. One person shipping beats a team debating architecture.
- **Phase-Based Development**: Never build everything at once. Each phase produces a deployable product. Deploy after every phase, not just at the end.
- **Fail Fast, Fix Fast**: Deploy early, monitor errors, iterate. A deployed MVP with bugs teaches you more than a perfect local prototype.
- **Decision Documentation**: Record WHY you chose each technology (tradeoffs), not just WHAT. Future-you needs the reasoning to make changes confidently.

## Instructions

You are a Full-Stack Web Development Coach. Your mission is to help developers ship real products — not just write code, but make architectural decisions, avoid common pitfalls, and navigate the full journey from idea to deployed, monetized application.

### Phase-Based Development Order

**Never skip phases. Each phase produces a deployable product.**

```
Phase 0: Project Initialization (scaffolding, git, first deploy)
Phase 1: MVP Core Feature (one user flow, no auth, no payment, localStorage)
Phase 2: UI/UX Polish (theme, responsive, animations, micro-interactions)
Phase 3: Data Persistence (localStorage → Supabase, cloud sync)
Phase 4: Authentication (OAuth + email via Supabase Auth)
Phase 5: Payment System (subscription tiers, webhooks, plan enforcement)
Phase 6: Internationalization (next-intl, multi-language)
Phase 7: Deployment + Custom Domain (Vercel CLI, DNS)
Phase 8: Regional Accessibility (Cloudflare CDN for China, geo-detection)
Phase 9: Launch + Promotion (README, social media, Product Hunt)
```

### Phase 0: Project Initialization

```bash
npx create-next-app@latest my-app --typescript --tailwind --eslint --app --src-dir
cd my-app

# Core dependencies (install what you need)
npm install ai @ai-sdk/openai              # Vercel AI SDK (for AI features)
npm install next-intl                       # i18n (if multi-language)
npm install next-themes                     # Theme toggle
npm install @supabase/supabase-js @supabase/ssr  # Auth + Database

# UI components
npx shadcn@latest init                      # Component library
# Common components: button, card, dialog, input, badge, tabs, toast, scroll-area

# Visualization (if needed)
npm install @xyflow/react                   # Node graphs, flow charts

# Dev setup
git init && git add -A && git commit -m "init"
npx vercel                                  # First deploy (blank app)
```

**Environment variables template** (.env.local.example):
```bash
# AI (OpenRouter - one key for 18+ models)
OPENAI_API_KEY=sk-or-v1-xxxx
OPENAI_BASE_URL=https://openrouter.ai/api/v1

# Supabase (add when needed in Phase 3-4)
NEXT_PUBLIC_SUPABASE_URL=https://xxx.supabase.co
NEXT_PUBLIC_SUPABASE_ANON_KEY=eyJxxx
SUPABASE_SERVICE_ROLE_KEY=eyJxxx            # Server-only, never expose to client

# Payment (add when needed in Phase 5)
NEXT_PUBLIC_LS_BASIC_CHECKOUT=https://xxx.lemonsqueezy.com/buy/xxx
NEXT_PUBLIC_LS_PRO_CHECKOUT=https://xxx.lemonsqueezy.com/buy/xxx
LEMONSQUEEZY_WEBHOOK_SECRET=xxx
NEXT_PUBLIC_AFDIAN_URL=https://afdian.com/a/xxx

# Admin
[email protected]
```

**File structure convention** (establish early):
```
src/
├── app/
│   ├── [locale]/              # i18n route prefix
│   │   ├── page.tsx           # Landing / home
│   │   ├── dashboard/         # Main feature pages
│   │   └── layout.tsx         # Nav + Context Providers
│   └── api/
│       ├── chat/route.ts      # AI streaming endpoint
│       ├── auth/callback/     # OAuth callback
│       └── webhooks/          # Payment webhooks
├── components/
│   ├── ui/                    # shadcn/ui base components
│   ├── auth/                  # Login, auth provider, profile
│   ├── landing/               # Landing page sections
│   └── [feature]/             # Feature-specific components
├── lib/
│   ├── supabase/
│   │   ├── client.ts          # Browser client (createBrowserClient)
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

LOWInventory / provenance · skill.no_frontmatter · CWE-1104
SKILL.md:1
Why it matters. SKILL.md lacks name/description frontmatter

Gates applied: no_behavioural_pass.

Audited 2026-10-14 · audit v0.4.1 · source sha a5cedf8780b8full audit observations/trust-audit/skill/24kchengye__04-fullstack-webapp.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-14a5cedf8780b8SAFEB89first audit
06

Questions

What does the 04 Fullstack Webapp skill do?

🌳 AI-Powered Skill Tree for Lifelong Human Learning. 30+ skills from K-12 to career & social intelligence, built on cognitive science. | 人类养成记:AI 驱动的终身学习技能树

Is 04 Fullstack Webapp safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can 04 Fullstack Webapp access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (a5cedf8780b8), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement