Getting Started with Claude Code: Installation, Switching to Chinese LLMs, and Git Workflows Explained

The Evolution from a CLI Tool to an AI Collaborator

Claude Code has become one of the hottest AI programming tools around today. Whether you're an individual developer or part of an engineering team, everyone is exploring the best way to integrate it into their daily development workflow. To truly understand why it has garnered such widespread attention, we need to look back at its evolutionary path.

Claude Code originally had only a command-line version—a pure CLI conversational tool that could analyze project code, understand dependencies between files, modify code, and offer optimization suggestions. With rapid version iterations, today's Claude Code is vastly different from its early incarnation, adding a wealth of powerful tools and significantly strengthening its core capabilities.

The most critical changes manifest in two dimensions:

• Upgraded context awareness: Evolving from understanding only a single file to being able to directly analyze an entire project structure and answer deep questions about module relationships and architectural design.
• Clear engineering orientation: Expanding from pure code generation to implementing complete engineering scenarios such as SDD (Spec-Driven Development) and automated testing.

In other words, Claude Code has gradually evolved from a "programming assistant" into a genuine "work partner"—humans set goals, define constraints, make decisions, and steer direction, while the AI takes on execution, analysis, comparison, and absorbing repetitive labor.

Practical Value for Different Roles

Programming beginners: Claude Code can help you quickly understand unfamiliar open-source project code, pinpoint the root causes of errors, and even discover legacy bugs and performance bottlenecks while offering fix solutions.

Independent developers: Significantly compress development time across the full front-end and back-end workflow. Through multi-agent orchestration, you can have Claude Code simultaneously play multiple roles—product, development, testing, operations—allowing one person to deliver team-level engineering output.

Development teams: Unify standards and reduce collaboration friction. Common pain points such as inconsistent code style, slow onboarding for newcomers, and time-consuming code reviews can all be addressed by building Skills to accumulate experience—for example, using CLAUDE.md to codify development standards, automatically analyze issues, and enforce code style checks.

Installing Claude Code and Switching to Chinese Models

Claude Code currently comes in three main versions:

1. Web version: Use directly in the browser, suitable for lightweight conversational scenarios
2. CLI (command-line) version: The only version in the early days; its basic commands are still worth mastering
3. IDE plugin version: Integrated into mainstream editors like VS Code, Cursor, and PyCharm/IDEA

For daily project development, the IDE plugin version and CLI version see the most frequent use.

CLI Installation Steps

CLI installation is very simple and can be completed with a single command:

• Mac / Linux / WSL: Use the official one-click installation command
• Windows: Use the corresponding irm installation command

After installation, run claude -v to check the version number. If you can see the version information, the installation was successful.

Before installing, make sure you've configured your Node.js environment (version 22.x or higher is recommended), and run node -v to confirm. If you encounter network issues, you can switch to a domestic mirror repository and install via npm. For future updates, simply run claude update—the tool itself will also prompt for automatic upgrades.

How to Switch to a Chinese LLM

Due to network constraints, access to the official models is often unstable. We recommend using the CC Switch tool to quickly switch to Chinese LLMs such as DeepSeek, Kimi (Moonshot), and Tongyi Qianwen.

The configuration process is as follows:

1. Download the appropriate version from the CC Switch project page (the portable version is recommended for Windows; be careful to distinguish between ARM / AMD64 architectures)
2. Obtain the API key for the target model
3. Add a new model configuration in CC Switch and enter the API key (other addresses generally need no modification)
4. Click enable, and check "local routing" in the settings
5. Restart Claude Code for the changes to take effect

After switching, use the /model slash command to view and select models like DeepSeek. Chinese models work exactly the same way as the official models—the only difference lies in a certain gap in performance, but stability is actually better guaranteed.

A Detailed Look at Claude Code's Core Workflows

Once you've mastered the basic installation and configuration, you can move on to actual project development.

Quick Reference for Common Commands

Claude Code's commands fall into two categories—internal slash commands and external CLI commands:

• /help: Query all available commands
• claude --resume (or claude -r): Show a list of conversation history and select a specific session to resume
• claude --continue (or claude -c): Directly resume the last conversation without picking from a list
• /clear: Clear the current conversation record and start a fresh session

Interestingly, you can simply ask in natural language, "Which command should I use to resume a conversation," and Claude Code will give you the answer—no need to consult the official documentation.

Step One: Use Claude Code to Analyze Project Structure

For enterprise-level project development, the first step is usually to have Claude Code analyze the entire project structure. Faced with an unfamiliar Java project, it can quickly identify the tech stack (for example, a Ruoyi-based Vue front-end admin management system) and analyze it module by module.

This is especially useful for newly onboarded developers—even without project documentation, they can quickly build an understanding of the overall architecture.

Code Modification Workflow

Every modification made by Claude Code follows a clear process:

1. Locate the file: Automatically find the relevant files in the project that need modification
2. Present the changes: Show the specific changes and wait for developer approval
3. Execute and confirm: You can approve item by item, or choose to accept everything

Once the code is complete, Claude Code automatically runs tests to verify the results, truly achieving a closed loop from development to validation.

Conversational Git Workflow: Making Version Control More Natural

One of Claude Code's most practical capabilities is integrating Git operations into natural-language conversation. Developers don't need to memorize complex commands—they simply describe their needs.

Pull, Commit, and Push

Through conversation, you can complete the full Git operation chain:

• Use natural language to have it pull (clone) a remote repository
• Move local files into the project and complete the commit and push
• Query the project's commit history in table format

Throughout the process, Claude Code automatically calls the corresponding Git commands in the background to complete all operations.

Automated Issue Discovery and Fix Loop

Going a step further, Claude Code can complete an automated closed loop of "discover the problem—organize the problem—fix the problem":

1. Create a new dev branch, implement various sorting algorithms, and push
2. Have Claude Code analyze the problems in that branch's code and output them to issue.md (covering correctness issues, mismatches between documentation and implementation, design portability issues, etc.)
3. Referencing the issue file, have it fix all the problems, then re-commit and push

The entire process requires no manual code editing—everything is done through conversation: code writing, test verification, and Git commit/push, all in one seamless flow.

Headless Mode

Beyond the interactive conversation window, you can also use claude -p (headless mode) to directly execute a single task in command form. For example:

claude -p "分析 Test 目录的项目结构"

There's no need to enter the interactive interface—the results are output directly to the console, making it ideal for integration into scripting and CI/CD automation scenarios.

Conclusion

Claude Code's core competitive edge lies in completing the leap from a "command-line code assistant" to an "engineering-oriented AI collaborator." Whether it's helping beginners understand complex projects, boosting independent developers' delivery efficiency, or helping teams unify development standards, it can provide tangible help.

For developers in China, switching to Chinese LLMs like DeepSeek and Kimi via CC Switch is a reliable way to sidestep network restrictions. But the real key to unleashing this tool's productivity lies in mastering its conversational Git workflow and automated problem-fixing capabilities—that's what truly sets Claude Code apart from ordinary code-completion tools.