Claude Code Tutorial: From Zero to Productive in 30 Minutes
A step-by-step tutorial for getting started with Claude Code, from installation to your first real task, plus how to add domains for specialized professional workflows.
Leopoldo Editorial
A step-by-step tutorial for getting started with Claude Code, from installation to your first real task, plus how to add domains for specialized professional workflows.
Leopoldo Editorial
This tutorial takes you from zero to a productive Claude Code setup in under 30 minutes. By the end, you will have Claude Code installed, configured, and working on real tasks in your projects, plus an understanding of how domains extend it into a specialist.
Open your terminal and run a single command:
**npm install -g @anthropic-ai/claude-code**
This installs Claude Code globally on your machine. It requires Node.js (version 18 or later) and works on macOS 13+, Windows 10+, and most Linux distributions.
Claude Code needs access to Claude's models. You have two options:
Navigate to any project directory in your terminal and type **claude** to start a session. Claude Code immediately reads your project structure (source files, configuration, dependencies, git history) and builds a context map.
You do not need to describe your project. Claude Code figures it out by reading it.
Start with something concrete:
**Explain the codebase.** Ask Claude to explain your project architecture. It will read through your files and give you a structured overview.
**Fix a bug.** Point Claude at a bug or error message. It will read the relevant files, trace the issue, propose a fix, and implement it.
**Refactor a module.** Ask Claude to refactor a messy file or function. It reads the code, identifies improvements, and makes the changes.
**Add a feature.** Describe a feature in plain language. Claude will plan the implementation and produce working code.
**Project instructions.** Create a CLAUDE.md file in your project root with key information. Claude Code reads this file automatically at the start of every session.
**Focused context.** When working on a specific area, tell Claude which files or directories matter.
**Session continuity.** Within a session, Claude remembers everything you have discussed.
Claude Code has native git support. It can stage changes, write commit messages, create branches, and manage your workflow. The git integration is especially powerful because Claude understands the semantic meaning of your changes, not just the text diff.
At this point, you have a working Claude Code setup that handles general development tasks. The next step is making it a domain specialist.
Leopoldo (leopoldo.ai) provides managed domains that add deep expertise to Claude Code. Each domain is a complete kit (agents, orchestrators, and hooks) purpose-built for a specific professional vertical.
1. Download a free domain from GitHub or request access at hello@leopoldo.ai 2. Download the domain archive 3. Extract it to your project root 4. Claude Code auto-discovers the domain contents
Explore all domains at leopoldo.ai/domains. Full Stack is free on GitHub. Specialized domains available on request at hello@leopoldo.ai.
Run npm install -g @anthropic-ai/claude-code in your terminal. You need Node.js installed. Claude Code works on macOS 13+, Windows 10+, and Ubuntu 20.04+. After installation, authenticate with your Anthropic API key or Claude subscription.
Yes. Claude Code offers both a terminal interface and a native VS Code extension. The VS Code extension provides a sidebar panel with inline diffs so you can see Claude's changes in real time.
Download a free domain from GitHub or request access at hello@leopoldo.ai. Extract the archive to your project root. Claude Code auto-discovers the domain contents immediately.
Claude Code operates natively in your terminal with direct access to your file system, shell, and git. It can read your entire codebase, execute commands, make changes across multiple files, run tests, and commit code. ChatGPT generates text in a browser. It cannot take action in your environment.