Always updating

AI Coding · Viable Coding

Make AI-written code actually work: from vibe prototype to runnable, tested, shippable, maintainable code.

20curated resources

What is Viable Coding

What is Viable Coding

Vibe Coding lets anyone with a prompt ship a prototype, but AI-generated code often will not run, has no tests and is hard to maintain. Viable Coding adds engineering discipline on top: making AI-written code truly runnable, testable, shippable and maintainable.

This page breaks the journey into 4 stages: build a foundation and understand the limits, learn to feed context correctly, use engineering methods to let agents work autonomously, then polish a prototype into a product.

The 20 curated GitHub repos below are grouped by topic, paired with companion SOPs that turn each stage into step-by-step, executable actions.

4-Stage Learning Path

From zero to one — take AI coding from "it generates" to "it ships".

01

Foundation · Vibe Coding Basics

Get prototypes running with prompts first, and learn where AI code breaks — what it can do and where it fails.

Start learning
02

Context · Context Engineering

Feed AI your architecture constraints, specs and relevant files so it writes correctly on the first pass, cutting guesswork and rework.

Start learning
03

Engineering · Agentic Engineering

Use plan-first, test-driven and subagent division of labor to let agents complete bigger, more reliable tasks.

04

Delivery · Polish to Viable

A pre-launch polish checklist — tests, error handling, performance, security and maintainability — so the code actually ships.

Start learning

Curated GitHub Resources

20 high-quality repos by topic, covering fundamentals, context, agentic engineering and polish.

Getting Started4

Tutorials and courses to start Vibe Coding from scratch, in Chinese and English.

Context Engineering4

How to feed context to AI: project memory, specs and file references.

Agentic Engineering4

Best practices for AI agents to plan and execute engineering tasks.

Polish in Practice4

Practical templates and checklists for turning prototypes into shippable products.

Awesome Lists4

One-stop resource collections, continuously updated.

Related Workflows (SOPs)

Step-by-step SOPs that turn these methods into executable actions.

View all workflows

Plan G: AI Coding Workflow (Requirements to Delivery)

Clarify requirements → technical plan → scaffold → incremental coding → test & debug → review & commit

Time：
1-4 hours / feature
Cost：
Medium
Difficulty：
Advanced

Plan AX: Context Engineering — Feed the Right Context, Get It Right the First Time

Document project memory → spec first → give enough relevant files → iterative feedback → verify & commit

Time：
1-3 hours / task
Cost：
Low
Difficulty：
Advanced

Plan AY: From Vibe Prototype to Viable Product — Pre-Launch Polish Checklist

Lock down requirements → make it testable → error handling → performance → maintainability → documentation

Time：
0.5-2 days
Cost：
Medium
Difficulty：
Advanced

Plan AZ: AI Coding Security & Testing Checkup — Mandatory Before Shipping

Input validation → secret management → dependency audit → automated tests → review checklist

Time：
1-2 hours / delivery
Cost：
Low
Difficulty：
Advanced