fancydirty

Learn Agent Engineering — AI skill for Claude Code

AI community

12-course AI agent curriculum: Claude Code to production systems.

How to install Learn Agent Engineering

This entry records only its repository, not the path inside it, so there is no exact command to give. Open fancydirty/learn-agent-engineering and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Learn Agent Engineering does

12-course AI agent curriculum: Claude Code to production systems. Six languages. MIT licensed.

Alternatives in AI

Hindsight — State-of-the-art long-term memory for AI agents by Vectorize 6.7k ★
Open Dots — Open-source, self-hosted AI agent workspace and alternative to OpenAI Dots, Meta Muse, Grok Bot, Instinct, Man 5.5k ★
Project Next 14 AI Prompt Sharing — Next.js recently became the official React framework as outlined in React docs 3k ★

README

Learn Agent Engineering

A 12-course curriculum teaching AI agent development from first principles to production systems. Covers Claude Code fundamentals, tool calling, workflows, context management, multi-agent orchestration, observability, and harness design.

**Live at [learn.agentmentor.dev](https://learn.agentmentor.dev)** · Available in English, 中文, 日本語, 한국어, Español, Português (BR)

What You'll Learn

Claude Code Skills — Your first agentic prompt and how Claude Code executes it
Agent Workflows — Sequential, parallel, and conditional execution patterns
Prompt Engineering — System prompts, few-shot examples, and chain-of-thought
Tool Calling — Design interfaces, handle errors, and compose multi-tool chains
Memory & State — Persistent storage, context windows, and state machines
Multi-Agent Collaboration — Delegation, specialization, and coordination
Agent Harness — Runtime controls, safety gates, and turn budgets
Context Engineering — Efficient prompting under token constraints
State Persistence — Making long tasks survive interruptions
Verification — Testing agents, eval sets, and LLM-as-judge
Observability — Logging, tracing, and debugging agent behavior
Orchestration — Building graphs, review loops, and deterministic pipelines

Each course includes:

6 lessons with hands-on exercises
Real code you can run locally
Capstone projects demonstrating production patterns
Sources cited throughout

How It Was Built

This curriculum was generated by the [Agent Mentor skill](https://agentmentor.dev) — a $4.99 Claude Code skill that writes pedagogically sound courses with exercises, citations, and multi-locale glossaries. The skill was invoked 12 times (once per course) via Claude Code, producing the entire path without direct human authoring.

**Why mention this?** It demonstrates what systematic agent workflows can produce when properly constrained: structured learn