wesammustafa/Claude-Code-Everything-You-Need-to-Know

A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, slash commands, skills, hooks, subagents, agent teams, and MCP servers. Beginner path to power-user depth. Featured in Awesome Claude Code.

Claude Code – A Practical Guide

What it is – This repository is a step‑by‑step tutorial for Claude Code, Anthropic’s official command‑line interface that lets you run Claude (the company’s large language model) directly from your terminal. The guide walks you through installing the CLI, authenticating, prompting Claude to read and edit your code, and extending the tool with custom Skills, Hooks, Sub‑agents, Workflows and MCP servers.

Who it’s for –

  • New users who have never used Claude Code can follow the “Setup → Prompt Engineering → First Skill” path in ~15 minutes.
  • Experienced users can dive into the deeper sections on Skills, Hooks, and the Model‑Context‑Protocol (MCP).
  • Team leads / automation engineers can learn how to build multi‑agent teams, dynamic workflows, and the BMAD framework for larger projects.

Key concepts covered

Feature What it does Where the files live
Skills (slash commands) Reusable markdown prompts that Claude can invoke with /skill‑name. Ideal for repeating tasks (e.g., opening a PR, running tests). .claude/commands/*.md
Hooks Scripts that run automatically on events such as session start, tool use, or sub‑agent termination. .claude/settings.json (wires to Python scripts in .claude/hooks/)
Sub‑agents Isolated Claude sessions with their own context, useful for large subtasks. .claude/agents/*.md
Workflows JavaScript files that orchestrate multiple agents and tools to solve complex jobs. .claude/workflows/*.js
MCP (Model‑Context‑Protocol) servers Enables Claude to call external services (browsers, databases, APIs) from the CLI. Configured per project. Project‑specific config files (not a fixed path)

How the repo helps you

  • The .claude/ directory is a ready‑to‑copy example project containing one of each extension point (7 slash skills, 5 sub‑agents, a dynamic workflow, Python hooks, etc.).
  • Detailed markdown guides (docs/skills.md, docs/reference/effort‑levels.md, etc.) explain the mental models behind effort levels, prompt engineering, and the BMAD method for building AI‑agent frameworks.
  • Cheat‑sheet links and tables make it easy to pick the right model (Sonnet 5, Opus 4.8, Fable 5, etc.) and the appropriate effort level (low → ultracode).

Why it matters – Claude Code brings LLM‑powered coding assistance into the developer’s native shell workflow, allowing the model to:

  1. Read the whole repository (file tree, imports, grep results) instead of only pasted snippets.
  2. Edit files in place and run your test suite automatically, giving you immediate feedback.
  3. Compose with your existing tooling via slash commands, hooks, and external MCP services.

By providing concrete, copy‑and‑pasteable examples, this guide lowers the barrier for teams to adopt AI‑driven automation without locking them into a specific editor or IDE.

Quick start

npm install -g @anthropic-ai/claude-code   # install the CLI
claude                                    # authenticate (opens browser)
cd my‑project && claude                    # start a Claude session
/explain what this codebase does           # sample prompt

Related

  • Project
    ghuntley/how-to-build-a-coding-agent

    A Go‑based workshop that incrementally builds a Claude‑powered coding assistant, adding tools for file reading, directory listing, shell execution, file editing, and code search.

  • Dispatch
    Claude Code Best Practices Guide

    Anthropic provides a comprehensive set of best practices for optimizing Claude Code, an agentic coding environment, focusing on context window management and autonomous verification.

  • Project
    davila7/claude-code-templates

    A comprehensive collection of ready-to-use agents, commands, and MCP integrations designed to extend the functionality of Anthropic's Claude Code.

  • Project
    shareAI-lab/learn-claude-code

    A 17‑lesson tutorial that teaches you how to build the surrounding “harness” code for an LLM‑based coding agent (Claude). It walks through adding tools, permissions, context management, memory, task scheduling, multi‑agent coordination, and goal‑driven termination, all around a simple agent‑loop that lets the model decide when to call tools.

  • Dispatch
    Claude Developer Platform Advanced Tool Use

    Anthropic has introduced Tool Search Tool, Programmatic Tool Calling, and Tool Use Examples to enable Claude agents to manage thousands of tools and large datasets without overloading the context window.