AI Engineering from Scratch

An open AI engineering course with tutor skills: the agent places you, teaches lessons in the terminal and quizzes you

SkillLow risk

rohitg00/ai-engineering-from-scratch

Install

npx skills add rohitg00/ai-engineering-from-scratch

The installer asks for the agent and install scope: user or project.

This is third-party code. Review the repository files before installing.

What it does

The repository holds a free AI engineering curriculum and a set of skills that turn a coding agent into a tutor. start-learning and find-your-level place you and save a personal plan to LEARNING.md. learn teaches one lesson per call: it walks through sections, has you run things, asks questions and records progress. check-understanding quizzes you on a phase, course-guide finds the lesson for a topic you are stuck on, and learn-mcp and learn-agent-skills run short tracks on MCP and Agent Skills. Lessons load from the repository, so cloning is optional.

Who it is for. For developers who want to learn AI engineering, MCP and skills systematically, studying right inside their agent.

Good fit when

  • You want to take an AI engineering course interactively instead of reading pages
  • You need to get up to speed on MCP or writing Agent Skills quickly
  • You want to test yourself on a topic you covered

Not a fit when

  • You need a skill for production work rather than learning
  • You need a course in Russian

Example request

/start-learning, I want to understand MCP, I am a backend developer

Limitations

Course materials are in English. Installation needs Node.js and npx, and hands-on labs need python3. The skills are tied to this curriculum and only useful for studying it.

How to disable. Delete the course skill folders (learn, start-learning, check-understanding and others) from the agent's skills directory.

Security check

  • The skills are instructions that read lessons from a public repository and write only a progress file

README in short

The README describes a multi-phase course from fundamentals to tools and protocols, where each lesson ends with a reusable artifact: a prompt, a skill, an agent or an MCP server. It offers fast tracks for MCP and Agent Skills, an invocation table for Codex, Claude Code and other agents, and a one-command skill install with npx skills add. The course is also on a website, MIT licensed.

SKILL.md

---
name: learn
version: 1.0.0
description: >
  Interactive lesson tutor for the AI Engineering from Scratch curriculum.
  Reads LEARNING.md, fetches the next lesson, teaches it section by section
  in the terminal, quizzes at the end, and records progress. Works cloned or
  entirely over raw.githubusercontent.com — no setup required.
  Trigger phrases: "next lesson", "teach me", "continue the course",
  "let's learn", "resume learning"
tags: [tutor, curriculum, ai-engineering, interactive-learning]
---

# Learn

You are the tutor for the **AI Engineering from Scratch** curriculum. One
invocation = one lesson, taught interactively: the learner should type,
answer, and run things — never just scroll. Works with any agent.

## Host invocation contract

Skill names are portable, but invocation syntax belongs to the host. Render
every suggested next action in the correct form:

- Codex: `learn`, `start-learning`, `check-understanding 13`, and other
  `skill-name` forms, or tell the learner to choose the skill from `/skills`.
- Claude Code: `/learn`, `/start-learning`, `/check-understanding 13`, and
  other `/skill-name` forms.
- Other compatible hosts: natural language such as `Use start-learning to
  build my course plan.` or `Use check-understanding to quiz me on Phase 13.`

FAQ

How do I invoke the skills in different agents?

In Claude Code use /start-learning and /learn, in Codex use the skill name or pick it from /skills, elsewhere ask to use start-learning by name.

Do I need to clone the repository?

No, the tutor reads lessons straight from GitHub. A clone is only needed for hands-on labs.

Editors’ pick

Open-source personal AI assistant on your own machine: answers in Telegram, Slack, Discord and WhatsApp, extended with skills and plugins

CLIHigh risk389.7K
Editors’ pick

A self-improving agent from Nous Research with a TUI, messaging gateway, cron jobs and skills it writes itself

CLIHigh risk245.5K
Editors’ pick

An open source coding agent for the terminal and desktop with build and plan modes

CLIHigh risk207.4K
Editors’ pick

Open prompt library with a Claude Code plugin, MCP server and CLI: search, fetch and improve prompts and skills from an agent

PluginMedium risk170.3K