zebbern/claude-code-guide

Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!

What it solves

Claude Code is a command-line interface that allows you to interact with Claude directly within your terminal to automate coding tasks, manage project files, and execute development workflows. It bridges the gap between your local codebase and AI, enabling you to perform complex tasks like code reviews, issue triage, and project-wide refactoring without leaving your command line.

How it works

Once installed, you run claude in your project directory to start an interactive session. It uses your existing Claude account (Pro, Team, or Enterprise) to provide AI assistance. You can control it using slash commands (like /add-dir or /branch) and configure its behavior through environment variables or local configuration files. It supports advanced features like "Plan Mode" for complex tasks, "Auto Mode" for autonomous execution, and "MCP" (Model Context Protocol) to integrate with external tools and data sources.

Who it’s for

It is designed for developers who want to integrate AI directly into their terminal-based development workflow. It requires a paid Anthropic account and is suitable for those who prefer managing projects via CLI, need to automate repetitive coding tasks, or want to enforce project-specific coding standards through shared instruction files.

Highlights

  • Native CLI Experience: Available as a native binary for macOS, Linux, and Windows, with no Node.js requirement for the primary installer.
  • Context-Aware Instructions: Uses CLAUDE.md and .claude/rules/ files to apply project-specific coding standards, architecture rules, and team preferences.
  • Advanced Agentic Features: Includes support for sub-agents, background task processing, and automated PR reviews.
  • Flexible Configuration: Offers granular control via environment variables, interactive /config settings, and managed policy files for enterprise environments.
  • Extensible Architecture: Supports the Model Context Protocol (MCP) and custom skills to connect with third-party tools and services.

Related

  • Project
    markusschanta/awesome-jupyter

    A curated directory of tools, libraries, and resources that extend the functionality of Jupyter notebooks for data science, development, and research.

  • Project
    convex/chef

    Chef is an open‑source AI‑driven app builder that uses Convex’s reactive database to generate full‑stack web apps from natural‑language prompts. It includes an agentic loop for LLM code generation, built‑in auth, real‑time UI, and a CLI, and can be run locally or on Convex’s hosted platform.

  • Project
    liustack/modlens

    ModLens is a lightweight vision plug‑in for DeepSeek Harness that lets you paste images directly into a chat with a text‑only LLM. It routes the picture to one of several built‑in or reusable vision services (Gemini, OpenAI‑compatible, Anthropic, Antigravity‑CLI, Claude‑CLI, Kimi‑CLI) and returns a structured description for the model to use. Installation is a single command, and the plugin works without extra proxies or config changes.

  • Project
    duoan/TorchCode

    An interactive coding platform for practicing PyTorch implementations of operators and architectures from scratch to prepare for ML engineering interviews.