Build Your Own X logo

Build Your Own X

Organization
NeverSight
build-your-own-x

Master programming by recreating your favorite technologies from scratch. Based on the 529K+ star GitHub repo codecrafters-io/build-your-own-x, this skill indexes 200+ step-by-step tutorials across 30+ tech domains — 3D renderer, AI model, blockchain, database, Docker, emulator, game engine, Git, OS, programming language, neural network, Shell, web server, and more. Triggers on: build your own, from scratch, byox, learn by building, recreate, 从零实现, 手写, 造轮子.

Overview

PublisherNeverSight
Repositorylearn-skills.dev
Skill namebuild-your-own-x
Stars
210
Forks
38
Bundled files
12
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 12 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by NeverSight on GitHub. Read the source before you install it.

Installation

Install the Build Your Own X AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git /tmp/learn-skills.dev
mkdir -p .claude/skills
cp -r /tmp/learn-skills.dev/data/skills-md/0sakura721/build-your-own-x-skill/build-your-own-x .claude/skills/build-your-own-x
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Build Your Own X in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Build Your Own X on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Build Your Own X is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Build Your Own X — 从零构建一切

"What I cannot create, I do not understand." — Richard Feynman

基于 codecrafters-io/build-your-own-x(529K+ ⭐),精心整理的 200+ 篇「从零重建技术」教程合集。

Use this guide when someone asks

  • "我想从零实现一个 XXX" / "I want to build a XXX from scratch"
  • "怎么手写/手搓一个 XXX" / "How to recreate XXX"
  • "想理解 XXX 底层原理" / "How does XXX work under the hood?"
  • "build your own XXX" / "from scratch" / "byox"
  • "不用框架/库,纯手写 XXX" / "No frameworks, just raw code"

When NOT to use

  • Simple how-to-use guides for existing frameworks/libraries
  • Pure theory discussions without coding
  • Already-known standalone tutorials (this is an index, not a replacement)

How to Use

Step 1: Clarify what to build

Ask:

  • What technology? (database, game, OS, language…)
  • What language? (Python, Go, Rust, C, JS…)
  • Time budget? (one afternoon vs. multi-week deep dive)
  • Minimal (< 500 lines) or full-featured?

Step 2: Match a tutorial

Find the best match from the index below. Prioritize language + difficulty + domain.

Step 3: Guide through the tutorial

  • Open the tutorial link, extract key steps and code snippets
  • Plan the coding flow, guide the user step by step
  • If there's a companion code repo, point them to clone it
  • Verify compilation/execution at each step

教程索引 / Tutorial Index

🎮 3D 渲染器 (3D Renderer)

语言教程特点
C++Ray Tracing in One Weekend经典入门,周末搞定
C++TinyRenderer500 行 OpenGL
C++Physically Based Rendering教科书级
C# / JS3D soft engine from scratch从 C# 到 JS 多语言
Java / JSBuild your own 3D renderer从零光线追踪
PythonA 3D Modeller500 Lines or Less
C++Rasterization: Practical Implementation光栅化实战

🤖 AI 模型 (AI Model)

语言教程特点
PythonLLMs from scratch从零实现大语言模型
PythonDiffusion Models for Image GenerationHuggingFace 官方
PythonRAG from ScratchLangChain 出品

⛓️ 区块链 / 加密货币 (Blockchain)

语言教程特点
GoBuilding Blockchain in Go系列教程
PythonLearn Blockchains by Building One经典入门
JavaScriptNaivecoin<1500 行
TypeScriptNaivecoinStakePoS 版本
JavaScriptBuild your own Blockchain in JS纯 JS

🗄️ 数据库 (Database)

🐳 Docker

🕹️ 模拟器 / 虚拟机 (Emulator / VM)

🎮 游戏 (Game)

语言教程特点
CHandmade Hero传奇级,从零写游戏
CHow to Program an NES game in CNES 游戏
COn Tetris and Reimplementation俄罗斯方块
JavaScript2D breakout game using PhaserMDN 官方
JavaScriptHow to Make Your First RoguelikeRoguelike
PythonPygame TutorialPygame 入门
PythonRoguelike Tutorial RevisedRoguelike 经典
RustRoguelike Tutorial in Rust + tcodRust + tcod

🔧 Git

语言教程特点
JavaScriptGitletGit in JS
JavaScriptBuild GIT - Learn GIT学习 Git 内部
PythonWrite yourself a Git!最完整
Pythonugit: Learn Git Internals by Building Git Yourself精简易懂
PythonJust enough of a Git client最小 Git

🧠 神经网络 (Neural Network)

语言教程特点
PythonA Neural Network in 11 lines of Python11 行入门
PythonBuild Deep Learning From Scratch34 阶段重写 PyTorch
PythonNeural Networks: Zero to HeroKarpathy 视频
PythonSlowTorch纯 Python 实现 PyTorch
GoBuild a multilayer perceptron with GolangGo 写 MLP
JavaScriptNeural networks from scratch for JS linguistsJS 党入门

💻 操作系统 (Operating System)

📝 编程语言 (Programming Language)

🔍 正则表达式引擎 (Regex Engine)

语言教程特点
CA Regular Expression MatcherRob Pike 经典
JavaScriptBuild a Regex Engine in <40 Lines of Code<40 行
PythonBuild Your Own Regex EnginesNFA/DFA/回溯

🔎 搜索引擎 (Search Engine)

🐚 Shell

🌐 Web 服务器 (Web Server)

🖥️ 前端框架 / 库 (Front-end Framework)

语言教程特点
JavaScriptWTF is JSX (Let's Build a JSX Renderer)理解 JSX
JavaScriptBuild your own React手写 React
JavaScriptGooact: React in 160 lines of JavaScript160 行 React
JavaScriptBuild Yourself a Redux手写 Redux
JavaScriptBuilding a frontend framework完整框架
JavaScriptHow to write your own Virtual DOM虚拟 DOM

📡 网络栈 (Network Stack)

🖊️ 文本编辑器 (Text Editor)

🧩 模板引擎 (Template Engine)

语言教程特点
JavaScriptJS template engine in just 20 lines20 行
PythonA Template Engine500L 系列

🧰 命令行工具 (Command-Line Tool)

🔩 其他 (Uncategorized)


学习路线 / Learning Pathways

🟢 入门 (Beginner) — 周末速成 (Weekend projects)

适合刚入门、想快速有成就感 / Quick wins:

  1. Shell (C) — 一个下午
  2. Regex Engine (JS, <40 行) — 一小时
  3. Neural Network (Python, 11 行) — 一小时
  4. Blockchain (Python) — 一个下午
  5. Web Server (Python/Node.js) — 一个下午

🟡 进阶 (Intermediate) — 深入理解 (Deep understanding)

有基础、想深入系统 / Solid foundations, deeper systems:

  1. Git (Python) — 1 天
  2. Database (Go/C) — 2-3 天
  3. Container/Docker (Go) — 1 天
  4. 3D Renderer (C++, Ray Tracing) — 周末
  5. Emulator (C, Chip-8) — 周末
  6. Programming Language (mal Lisp) — 3-5 天

🔴 专家 (Expert) — 终极挑战 (The deep end)

推自己到极限 / Push your limits:

  1. Operating System (C/Rust) — 数周到数月
  2. Compiler (Crafting Interpreters) — 2-4 周
  3. Game Engine (C, Handmade Hero) — 数月
  4. Browser Engine (Rust) — 数周
  5. Linux from Scratch — 数天到数周

小贴士 / Tips

  • 从入门路线开始建立信心,再迈入进阶领域
  • 每个项目建一个 Git 仓库记录进展
  • 卡住时直接看教程评论区/Issues
  • 有多个语言版本时先选你最熟悉的那门

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Build Your Own X AI skill do?

Master programming by recreating your favorite technologies from scratch. Based on the 529K+ star GitHub repo codecrafters-io/build-your-own-x, this skill indexes 200+ step-by-step tutorials across 30+ tech domains — 3D renderer, AI model, blockchain, database, Docker, emulator, game engine, Git, OS, programming language, neural network, Shell, web server, and more. Triggers on: build your own, from scratch, byox, learn by building, recreate, 从零实现, 手写, 造轮子.

Why use Build Your Own X on TypingMind?

Because you install it once and use it with any model. Build Your Own X is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Build Your Own X in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/0sakura721/build-your-own-x-skill/build-your-own-x. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Build Your Own X?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Build Your Own X?

As many as you like. As long as a model supports skills, you can use Build Your Own X with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Build Your Own X AI skill free?

It is published on GitHub by NeverSight. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇