tukuaiai/vibe-coding-cn

★ 13,486PythonAudience · vibe coderComplexity · 1/5LicenseSetup · easy

Mindmap

mindmap
  root((repo))
    What it does
      AI coding tutorials
      Chinese language guide
      Beginner to advanced
    Five Layers
      Prompts
      Skills
      Workflows
      Context management
      Quality gates
    Tools Covered
      Claude Code
      Cursor
      Codex
    Audience
      Vibe coders
      Chinese developers
      Founders

mindmap root((repo)) What it does AI coding tutorials Chinese language guide Beginner to advanced Five Layers Prompts Skills Workflows Context management Quality gates Tools Covered Claude Code Cursor Codex Audience Vibe coders Chinese developers Founders

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Follow the five-layer framework to go from ad-hoc AI prompting to a reliable, repeatable system for building software with AI tools.

USE CASE 2

Use the included prompt templates and workflow guides to keep an AI coding assistant on track across long, complex projects.

USE CASE 3

Learn how to set up quality checks so that AI-generated code is actually correct and maintainable before you ship it.

Tech stack

Python

Getting it running

Difficulty · easy Time to first run · 30min

Content is in Chinese, you will also need a separate AI coding tool such as Claude Code or Cursor to follow along.

Open-source license, exact terms were not specified in the explanation.

In plain English

This repository is a Chinese-language tutorial and resource collection for "vibe coding", a way of building software by describing what you want in plain language and letting an AI assistant write most of the code. The name comes from computer scientist Andrej Karpathy, who coined the term for this natural-language-first approach to development. The project aims to take someone from complete beginner to a structured, production-ready workflow for AI-assisted coding. It breaks the process down into five layers: writing prompts (one-off instructions for single tasks), skills (reusable capabilities for repeated tasks), workflows (step-by-step processes for complex projects), context management (keeping the AI's memory coherent across long sessions), and quality gates (tests and checks that ensure AI output is actually correct and maintainable). The repository works with AI coding tools including Claude Code, Cursor, Codex, and similar assistants. It is primarily documentation and learning materials, not a deployable application, and includes templates, prompt collections, example workflows, and guides for avoiding common pitfalls like the AI losing context, producing unmaintainable code, or silently making wrong assumptions. You would use this if you are a Chinese-speaking developer or founder who wants a systematic framework for getting reliable, clean results from an AI coding assistant, rather than just ad-hoc prompting. The README notes the full content is longer than what was provided. The project is written in Python and released under an open-source license.

Copy-paste prompts

Prompt 1

I want to use the vibe-coding-cn five-layer framework with Claude Code. Explain what each layer does and give me a starter template for the Workflows layer.

Prompt 2

I keep losing context when I use Cursor on a long project and the AI starts making wrong assumptions. Show me the context management techniques from this framework.

Prompt 3

I am a Chinese-speaking founder with no coding background and want to build a small web app using AI. Walk me through the vibe-coding-cn beginner path step by step.

Prompt 4

Give me a quality gate checklist I can paste into Claude Code to verify that the code it wrote for me is correct and will not break in production.

Open on GitHub → Explain another repo

← tukuaiai on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.