Getting started with Claude Code
Complete guide to get started with Claude Code: from installation to your first project. Everything you need to know to begin with Anthropic's AI assistant.
What is Claude Code?
Claude Code is a command-line AI assistant built by Anthropic. It lives in your terminal and understands your work context: files, directory structure, Git history, and much more.
Unlike a typical chatbot, Claude Code acts in your real environment. It can create files, run commands, analyze your code, and guide you through projects from start to finish.
Who is this guide for?
This guide is for experienced developers and complete beginners alike. Every concept is explained with simple analogies and hands-on examples.
Why use Claude Code?
Here are the key benefits:
- Time savings: automate repetitive tasks and speed up your workflow
- Learning: Claude explains every step and helps you understand the code
- Quality: code review, automated testing, and built-in best practices
- Accessibility: you don't need to be a developer to build real projects
The three pillars of Claude Code
1. The Terminal
Claude Code runs in your terminal. That's its natural environment, where it's most powerful. It can read your files, run commands, and interact with your system.
2. MCPs (Model Context Protocol)
MCPs are connectors that extend Claude Code's capabilities. Connect it to GitHub, Slack, Gmail, your databases, and dozens of other tools.
3. Skills
Skills are reusable recipes that guide Claude Code to execute complex tasks in a reproducible way. Create your own or use community-made ones.
Next steps
Now that you know the basics, move on to installation in the Getting Started guide or jump straight into MCPs and Skills.
Terminology
Throughout this guide, we use the English terms Skills and MCP as they are the official names used by Claude Code.