# How to Set Up a Complete Claude Code Dev Environment From Zero
**作者**: Guri Singh
**日期**: 2026-04-17T18:35:27.000Z
**来源**: [https://x.com/heygurisingh/status/2045209540313178527](https://x.com/heygurisingh/status/2045209540313178527)
---
(The 15-Minute Stack That Replaced My Entire Toolchain)
Most developers install Claude Code, type one prompt, get impressed, and never configure it properly.
They're using a Ferrari in first gear.
Claude Code with a proper setup, a CLAUDE.md that knows your project, five skills that fire automatically, hooks that enforce your standards, and MCP servers that connect your tools, is a fundamentally different experience from Claude Code out of the box.
I know because I ran both versions for 30 days. The unconfigured version was good. The configured version replaced my entire development toolchain. Cursor, Copilot, Grammarly, my linter dashboard, my PR review process. All of it.
This guide takes you from zero to a fully configured Claude Code environment in 15 minutes. Every step has the exact command. Every skill has the exact .md file. Nothing is theoretical.
By the end, you'll have a setup that 95% of Claude Code users don't know exists.
Let's build it.
Step 1: Install Claude Code (2 minutes)
The native installer is now the recommended method. No Node.js required. It auto-updates in the background.
macOS:
Open Terminal and paste:
curl -fsSL https://cli.claude.com/install.sh | sh
Linux (Ubuntu/Debian):
curl -fsSL https://cli.claude.com/install.sh | sh
Windows (PowerShell):
irm https://cli.claude.com/install.ps1 | iex
Windows (CMD):
curl -fsSL https://cli.claude.com/install.bat | cmd
Verify it worked:
claude --version
You should see a version number. That's it. Installation is done.
Important: You need a Claude Pro subscription ($20/month) or higher. The free tier does not include Claude Code.
If you're already paying $20/month for Claude chat, you already have Claude Code access. You just haven't used it yet.
Authenticate:
Navigate to any project folder and type:
claude
Follow the browser prompts to log in. Takes 30 seconds.
Step 2: Create Your CLAUDE.md (3 minutes)
This is the single most important file most people never create.
CLAUDE.md is your project's institutional memory. Claude reads it at the start of every session. It tells Claude your project's conventions, architecture, tech stack, and preferences. Without it, Claude starts from zero every time. With it, Claude already knows your project before you type a single prompt.
Think of it this way: CLAUDE.md is the difference between hiring a contractor who's never seen your codebase and onboarding a teammate who's read all the docs.
Navigate to your project root and create the file:
touch CLAUDE.md
Or even better, let Claude write it for you:
claude
"Analyze this codebase and generate a CLAUDE.md file that
describes the project structure, tech stack, conventions,
and any patterns you find in the code."
Claude will scan your files and generate a CLAUDE.md tailored to your project. Review it, edit it, commit it to your repo.
Here's what a good CLAUDE.md includes:
- Project overview: what this is, what it does, who it's for.
- Tech stack: language, framework, database, deployment target.
- Directory structure: where things live and why.
- Conventions: naming patterns, file organization, test strategy.
- Do's and don'ts: "Always use TypeScript strict mode." "Never use any type." "Tests go in __tests__/ next to the file they test."
- Common commands: how to run the dev server, run tests, deploy.
Example CLAUDE.md for a Next.js project:
# Project: InvoiceFlow
## Overview
SaaS invoicing app built with Next.js 14, TypeScript,
Supabase, and Stripe. Deployed on Vercel.
## Stack
- Next.js 14 (App Router)
- TypeScript (strict mode, no `any`)
- Supabase (auth, database, storage)
- Stripe (payments, subscriptions)
- Tailwind CSS (no custom CSS files)
- Vitest for testing
## Conventions
- Components: PascalCase, one component per file
- API routes: /app/api/[resource]/route.ts
- Server actions: /app/actions/[name].ts
- Tests: colocated in __tests__/ folders
- Commits: conventional commits (feat:, fix:, etc.)
## Commands
- Dev: pnpm dev
- Test: pnpm test
- Build: pnpm build
- Lint: pnpm lint
Commit this file. Every developer on your team who uses Claude Code will inherit the same conventions automatically.
Step 3: Install Your First Five Skills (5 minutes)
Skills are persistent .md files that teach Claude how to do specific types of work. They fire automatically when the task matches. No prompting. No re-explaining. Claude just knows.
Here are the five skills every developer should install on day one, in order of impact.
Skill 1: Skill Creator
The skill that builds skills. Install this first because you'll use it to build every custom skill after.
npx skills@latest add anthropics/skills/skill-creator
Once installed, just tell Claude: "Use the skill-creator to help me build a skill for [your task]." It interviews you, writes the SKILL.md, and saves it.
Skill 2: TDD (Test-Driven Development)
Forces a strict red-green-refactor loop. Writes failing tests first, then minimal code to pass them, then refactors. Prevents the "it works but nobody knows why" problem.
npx skills@latest add mattpocock/skills/tdd
Skill 3: Systematic Debugging
A 4-phase debugging methodology that stops random "just try changing stuff" edits. Reproduce, narrow the root cause, apply a single fix, verify with tests.
Install from the Superpowers repo:
git clone https://github.com/obra/superpowers
cp -r superpowers/skills/systematic-debugging .claude/skills/
Skill 4: Code Review
Runs systematic security, performance, error handling, and architecture checks. Ask for a "security-first review" or "performance-first review" or a full checklist pass.
Available in the Anthropic skills repo. Add it manually or install via:
npx skills@latest add anthropics/skills/code-review
Skill 5: Auto-Commit Messages
Reads your staged diff and generates a conventional commit message with type, scope, and body. No more writing "fix stuff" at 2am.
npx skills@latest add anthropics/skills/auto-commit
Where skills live:
Skills install to your .claude/skills/ folder. They persist across sessions. They work in every project where Claude Code runs. You install once and they compound forever.
The 3-conversation rule:
If you've typed the same instructions more than three times, that's a skill begging to be built. Stop retyping. Use the skill-creator to build it once.
Step 4: Set Up Git Guardrails (1 minute)
This is not optional if you're using Claude Code on production repos.
Claude is fast and helpful until it isn't. Git guardrails block dangerous commands like push --force, reset --hard, and clean before they execute.
npx skills@latest add mattpocock/skills/git-guardrails-claude-code
This sets up Claude Code hooks that intercept git commands and ask for confirmation before anything destructive runs. It takes one minute and it will save your codebase eventually.
Step 5: Connect MCP Servers (2 minutes)
MCP (Model Context Protocol) turns Claude Code from "coding assistant" into "coding assistant with direct access to your databases, APIs, and team tools."
Without MCP, Claude can only see your files. With MCP, Claude can query your database, read your GitHub issues, check your Slack messages, and interact with your APIs.
Create a .claude/.mcp.json in your project root:
{
"mcpServers": {
"github": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your-token-here"
}
Popular MCP servers to start with:
- GitHub: Read issues, create PRs, review code. The most useful server for most developers.
- Filesystem: Give Claude access to directories outside your project root. Essential for monorepos.
- PostgreSQL / Supabase: Let Claude query your database directly instead of guessing at schema.
- Slack: Claude can search messages, read channels, and post updates.
Commit your .claude/.mcp.json to the repo. Every team member who pulls the project inherits the same tool setup automatically.
Step 6: Add Your First Hook (2 minutes)
Hooks let you inject custom scripts at lifecycle events. Think of them as git hooks but for Claude Code.
The most immediately useful hook: auto-format on every file save.
Create .claude/hooks/pre-tool-use.sh:
#!/bin/bash
# Run prettier on any file Claude edits
if [ "$TOOL_NAME" = "file_edit" ]; then
npx prettier --write "$FILE_PATH" 2>/dev/null
fi
Make it executable:
chmod +x .claude/hooks/pre-tool-use.sh
Other hooks teams use:
- post-tool-use: Run linter after every code edit.
- on-session-start: Load project-specific environment variables.
- pre-commit: Validate code quality before Claude commits.
Hooks are the enforcement layer. Skills teach Claude how to work. Hooks ensure it follows your rules even when you're not watching.
What You Just Built
In 15 minutes you now have:
- Claude Code installed with auto-updates.
- CLAUDE.md giving Claude persistent memory of your project's stack, conventions, and commands.
- Five skills: skill-creator, TDD, systematic debugging, code review, and auto-commit. All firing automatically when relevant.
- Git guardrails protecting your production branches from destructive commands.
- MCP servers connecting Claude to GitHub (and optionally your database, Slack, and APIs).
- A formatting hook that auto-runs Prettier on every file Claude edits.
This is not the same tool as vanilla Claude Code. This is a configured development environment that compounds. Every skill you add, every hook you write, every convention you document in CLAUDE.md makes every future session better.
Most developers are running Claude Code like a chatbot. You're now running it like an engineering platform.
What to Do Next: The First 7 Days
Day 1-2: Use the default stack.
Don't add anything else yet. Run real tasks. Notice where Claude already knows your conventions (because of CLAUDE.md) and where it doesn't.
Day 3-4: Build your first custom skill.
Identify the task you've prompted for three times already. Use the skill-creator: "Help me build a skill for [that task]." Claude interviews you, drafts the SKILL.md, and you install it. Ten minutes, permanent result.
Day 5-6: Add planning skills.
Install Grill Me (forces relentless clarifying questions before you build the wrong thing) and Write a PRD (creates product requirement docs through interactive interview):
npx skills@latest add mattpocock/skills/grill-me
npx skills@latest add mattpocock/skills/write-a-prd
Day 7: Audit and expand.
By now you'll have a clear picture of what your stack is missing. Browse SkillsMP (skillsmp.com) for community skills. Check the Anthropic skills repo for official ones. Add what solves a real problem. Ignore everything else.
The Honest Part Nobody Tells You
Day 3 is where most people quit.
The initial excitement fades. A skill fires when you don't want it to. The CLAUDE.md has a convention that's slightly wrong and Claude keeps following it. You'll think "this is more work than just prompting."
It is more work. On day 3. By day 10, it's dramatically less work. By day 30, you've forgotten what it felt like to re-explain your project every session.
That's the compounding. The setup cost is real. The payoff is permanent.
Rate limits are also real.
On Claude Pro ($20/month), you'll hit rate limits during heavy coding sessions. The community consensus is: Pro handles 80% of workflows. If you're coding 6+ hours a day, the Max plan at $100/month removes most limits. Start with Pro. Upgrade only when you actually hit the ceiling.
The 15-Minute Challenge
You just read 2,500 words about setting up Claude Code. Here's what I want you to do in the next 15 minutes:
- Install Claude Code (2 minutes).
- Let Claude generate your CLAUDE.md (3 minutes).
- Install the five starter skills (5 minutes).
- Add git guardrails (1 minute).
- Connect one MCP server (2 minutes).
- Add the Prettier hook (2 minutes).
Then open a real project and give Claude a real task. Not "write hello world." Something you'd actually work on today.
The difference between that first session and the Claude Code experience you had before won't be subtle.
It will be obvious. And it will be permanent.
Send this to the developer on your team who installed Claude Code once, tried one prompt, and went back to Cursor. They didn't see the real tool. Now they will.
## 相关链接
- [Guri Singh](https://x.com/heygurisingh)
- [@heygurisingh](https://x.com/heygurisingh)
- [4.6K](https://x.com/heygurisingh/status/2045209540313178527/analytics)
- [https://cli.claude.com/install.sh](https://cli.claude.com/install.sh)
- [https://cli.claude.com/install.sh](https://cli.claude.com/install.sh)
- [https://cli.claude.com/install.ps1](https://cli.claude.com/install.ps1)
- [https://cli.claude.com/install.bat](https://cli.claude.com/install.bat)
- [https://github.com/obra/superpowers](https://github.com/obra/superpowers)
- [@modelcontextprotocol/server-github](https://x.com/@modelcontextprotocol/server-github)
- [skillsmp.com](https://skillsmp.com/)
- [Upgrade to Premium](https://x.com/i/premium_sign_up)
- [2:35 AM · Apr 18, 2026](https://x.com/heygurisingh/status/2045209540313178527)
- [4,637 Views](https://x.com/heygurisingh/status/2045209540313178527/analytics)
---
*导出时间: 2026/4/18 11:06:18*
---
## 中文翻译
# 如何从零搭建完整的 Claude Code 开发环境
**作者**：Guri Singh
**日期**：2026-04-17T18:35:27.000Z
**来源**：[https://x.com/heygurisingh/status/2045209540313178527](https://x.com/heygurisingh/status/2045209540313178527)
---
（取代我整个工具链的 15 分钟配置方案）
大多数开发者安装 Claude Code 后，输入一个提示词，觉得惊艳，然后就再也不去正确配置它了。
他们开着一辆法拉利却只用一档。
配置得当的 Claude Code——有一个了解你项目的 CLAUDE.md、五个自动触发的技能、强制执行你规范的钩子（hooks）、以及连接你工具的 MCP 服务器——和开箱即用的 Claude Code 是完全不同的体验。
我清楚这一点，因为我把两种版本都用了 30 天。未配置的版本已经很好了。配置好的版本则取代了我的整个开发工具链：Cursor、Copilot、Grammarly、我的 linter 仪表盘、我的 PR 审查流程。全部。
本指南将带你用 15 分钟从零搭建一个完整配置的 Claude Code 环境。每一步都有确切的命令，每个技能都有确切的 .md 文件。没有任何理论空谈。
看完之后，你将拥有一个 95% 的 Claude Code 用户都不知道存在的配置方案。
开始吧。
第 1 步：安装 Claude Code（2 分钟）
原生安装程序现在是推荐方式。无需 Node.js。它会在后台自动更新。
macOS：
打开终端并粘贴：
curl -fsSL https://cli.claude.com/install.sh | sh
Linux（Ubuntu/Debian）：
curl -fsSL https://cli.claude.com/install.sh | sh
Windows（PowerShell）：
irm https://cli.claude.com/install.ps1 | iex
Windows（CMD）：
curl -fsSL https://cli.claude.com/install.bat | cmd
验证安装是否成功：
claude --version
你应该能看到一个版本号。就这样，安装完成。
重要提示：你需要 Claude Pro 订阅（$20/月）或更高等级。免费版不包含 Claude Code。
如果你已经为 Claude 聊天每月支付 $20，那你已经拥有 Claude Code 的使用权限了，只是还没用过而已。
身份验证：
进入任意项目文件夹并输入：
claude
按照浏览器提示登录。只需 30 秒。
第 2 步：创建你的 CLAUDE.md（3 分钟）
这是大多数人从未创建过的最重要的一份文件。
CLAUDE.md 是你项目的“机构记忆”。Claude 在每次会话开始时都会读取它。它告诉 Claude 你项目的约定、架构、技术栈和偏好。没有它，Claude 每次都从零开始。有了它，Claude 在你输入第一个提示词之前就已经了解你的项目了。
可以这样理解：CLAUDE.md 的区别，就像雇用一个从没见过你代码库的外包人员，和一个读过所有文档、已完成入职培训的队友。
进入项目根目录并创建该文件：
touch CLAUDE.md
或者更好的做法，让 Claude 替你写：
claude
"分析这个代码库，并生成一个 CLAUDE.md 文件，
描述项目结构、技术栈、约定，
以及你在代码中发现的任何模式。"
Claude 会扫描你的文件并生成一个为你的项目量身定制的 CLAUDE.md。审查它、编辑它，然后提交到你的仓库。
一份好的 CLAUDE.md 应包含：
- 项目概述：这是什么、做什么用、面向谁。
- 技术栈：语言、框架、数据库、部署目标。
- 目录结构：各文件放在哪里以及为什么。
- 约定：命名模式、文件组织、测试策略。
- 该做与不该做：“始终使用 TypeScript 严格模式。”“绝不使用 any 类型。”“测试放在被测文件旁的 __tests__/ 目录中。”
- 常用命令：如何启动开发服务器、运行测试、部署。
一个 Next.js 项目的 CLAUDE.md 示例：
# 项目：InvoiceFlow
## 概述
基于 Next.js 14、TypeScript、Supabase 和 Stripe 构建的
SaaS 发票应用。部署在 Vercel 上。
## 技术栈
- Next.js 14（App Router）
- TypeScript（严格模式，不用 `any`）
- Supabase（身份验证、数据库、存储）
- Stripe（支付、订阅）
- Tailwind CSS（不使用自定义 CSS 文件）
- Vitest 用于测试
## 约定
- 组件：PascalCase，每个文件一个组件
- API 路由：/app/api/[resource]/route.ts
- Server Actions：/app/actions/[name].ts
- 测试：与代码放在一起，放在 __tests__/ 文件夹中
- 提交：约定式提交（feat:、fix: 等）
## 命令
- 开发：pnpm dev
- 测试：pnpm test
- 构建：pnpm build
- 代码检查：pnpm lint
提交这个文件。团队中每个使用 Claude Code 的开发者都会自动继承相同的约定。
第 3 步：安装你的前五个技能（5 分钟）
技能是持久的 .md 文件，教 Claude 如何完成特定类型的工作。当任务匹配时它们会自动触发。无需提示词，无需反复解释。Claude 自己就知道。
以下是每个开发者第一天就应该安装的五个技能，按影响力排序。
技能 1：Skill Creator（技能创建器）
用来创建技能的技能。优先安装它，因为你之后会用它来构建每一个自定义技能。
npx skills@latest add anthropics/skills/skill-creator
安装后，只需告诉 Claude：“使用 skill-creator 帮我为 [你的任务] 构建一个技能。”它会采访你、编写 SKILL.md 并保存。
技能 2：TDD（测试驱动开发）
强制执行严格的“红-绿-重构”循环。先编写失败的测试，然后编写最少量的代码使其通过，再进行重构。避免“能跑但没人知道为什么”的问题。
npx skills@latest add mattpocock/skills/tdd
技能 3：Systematic Debugging（系统化调试）
一套 4 阶段调试方法论，杜绝随意的“改改试试”式编辑。复现问题、定位根本原因、应用单一修复、用测试验证。
从 Superpowers 仓库安装：
git clone https://github.com/obra/superpowers
cp -r superpowers/skills/systematic-debugging .claude/skills/
技能 4：Code Review（代码审查）
运行系统化的安全性、性能、错误处理和架构检查。可以要求“安全优先审查”、“性能优先审查”或完整的清单检查。
可在 Anthropic 技能仓库中获取。可手动添加，或通过以下方式安装：
npx skills@latest add anthropics/skills/code-review
技能 5：自动提交信息
读取你的暂存区差异（diff），并生成包含类型、作用范围和正文的规范提交信息。再也不用在凌晨 2 点写"fix stuff"了。
npx skills@latest add anthropics/skills/auto-commit
技能存放在哪里：
技能会安装到你的 .claude/skills/ 文件夹。它们会跨会话持久保存。在运行 Claude Code 的每个项目中都能使用。你只需安装一次，它们就会永久复利增值。
三次对话规则：
如果你已经输入了同样的指令超过三次，那就是一个亟待构建的技能。别再重复输入了。用 skill-creator 把它构建一次即可。
第 4 步：设置 Git 防护栏（1 分钟）
如果你要在生产环境仓库上使用 Claude Code，这一步不是可选项。
Claude 一向快速且乐于助人，直到它不再如此。Git 防护栏会在 push --force、reset --hard 和 clean 等危险命令执行之前将其拦截。
npx skills@latest add mattpocock/skills/git-guardrails-claude-code
这会设置 Claude Code 钩子（hook），拦截 git 命令，并在任何破坏性操作运行之前请求确认。这只需一分钟，但最终会挽救你的代码库。
第 5 步：连接 MCP 服务器（2 分钟）
MCP（模型上下文协议）能把 Claude Code 从"编码助手"变成"可以直接访问你的数据库、API 和团队工具的编码助手"。
没有 MCP，Claude 只能看到你的文件。有了 MCP，Claude 可以查询你的数据库、读取你的 GitHub issues、查看你的 Slack 消息，并与你的 API 交互。
在项目根目录创建一个 .claude/.mcp.json：
{
"mcpServers": {
"github": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your-token-here"
}
推荐的入门 MCP 服务器：
- GitHub：读取 issue、创建 PR、审查代码。对大多数开发者而言是最有用的服务器。
- Filesystem：让 Claude 访问项目根目录之外的目录。对于 monorepo 至关重要。
- PostgreSQL / Supabase：让 Claude 直接查询你的数据库，而不是猜测数据库结构。
- Slack：Claude 可以搜索消息、阅读频道并发送更新。
把 .claude/.mcp.json 提交到仓库。每个拉取该项目的团队成员都会自动继承相同的工具配置。
第 6 步：添加你的第一个钩子（2 分钟）
钩子让你可以在生命周期事件中注入自定义脚本。可以把它们理解为 git 钩子，但面向 Claude Code。
最立竿见影的钩子：每次保存文件时自动格式化。
创建 .claude/hooks/pre-tool-use.sh：
#!/bin/bash
# 对 Claude 编辑的任何文件运行 prettier
if [ "$TOOL_NAME" = "file_edit" ]; then
npx prettier --write "$FILE_PATH" 2>/dev/null
fi
给它添加可执行权限：
chmod +x .claude/hooks/pre-tool-use.sh
团队使用的其他钩子：
- post-tool-use：每次代码编辑后运行 linter。
- on-session-start：加载项目特定的环境变量。
- pre-commit：在 Claude 提交之前验证代码质量。
钩子是执行层。技能教会 Claude 如何工作。钩子确保即使你不在盯着，它也会遵守你的规则。
你刚刚构建了什么
在 15 分钟内，你现在拥有了：
- 安装了 Claude Code 并开启了自动更新。
- CLAUDE.md 赋予 Claude 对项目技术栈、规范和命令的持久记忆。
- 五项技能：skill-creator、TDD、系统化调试、代码审查和自动提交。所有技能都会在相关时自动触发。
- Git 防护栏保护你的生产分支免受破坏性命令的影响。
- MCP 服务器将 Claude 连接到 GitHub（以及可选的数据库、Slack 和 API）。
- 一个格式化钩子，在 Claude 编辑每个文件时自动运行 Prettier。
这和原生的 Claude Code 已经不是同一个工具了。这是一个会不断复利增值的、配置好的开发环境。你添加的每一项技能、编写的每一个钩子、在 CLAUDE.md 中记录的每一条规范，都会让未来的每次会话变得更好。
大多数开发者把 Claude Code 当聊天机器人来用。而你现在把它当工程平台来用。
接下来该做什么：最初的 7 天
第 1-2 天：使用默认配置。
暂时不要添加任何其他东西。运行真实的任务。留意 Claude 在哪些地方已经了解你的规范（因为 CLAUDE.md），在哪些地方不了解。
第 3-4 天：构建你的第一个自定义技能。
找出你已经提示过三次的任务。使用 skill-creator："帮我为【那个任务】构建一个技能。" Claude 会对你进行访谈、起草 SKILL.md，然后你安装它。十分钟，一劳永逸。
第 5-6 天：添加规划技能。
安装 Grill Me（在你要错方向之前逼你回答一连串澄清性问题）和 Write a PRD（通过交互式访谈创建产品需求文档）：
npx skills@latest add mattpocock/skills/grill-me
npx skills@latest add mattpocock/skills/write-a-prd
第 7 天：审计并扩展。
到这时，你对自己的配置缺什么会有清晰的认识。到 SkillsMP（skillsmp.com）浏览社区技能。查看 Anthropic 技能仓库中的官方技能。添加能解决实际问题的，忽略其余一切。
没人告诉你的真相
大多数人是在第 3 天放弃的。
最初的新鲜感消退了。一个技能在你不想让它触发的时候触发了。CLAUDE.md 里有一条稍有偏差的规范，而 Claude 一直遵循它。你会想："这比直接提示还费事。"
确实更费事——在第 3 天。但到第 10 天，它会大幅减少工作量。到第 30 天，你已经忘了每次会话都要重新解释一遍项目是什么感觉。
这就是复利。设置成本是真实的，回报也是永久的。
速率限制也是真实存在的。
在 Claude Pro（每月 20 美元）上，你在高强度编码时会遇到速率限制。社区的共识是：Pro 能应对 80% 的工作流。如果你每天编码 6 小时以上，每月 100 美元的 Max 套餐可以解除大部分限制。从 Pro 开始，只有当你真正撞到上限时再升级。
15 分钟挑战
你刚读完 2500 字关于设置 Claude Code 的内容。接下来 15 分钟里，我希望你做以下事情：
- 安装 Claude Code（2 分钟）。
- 让 Claude 生成你的 CLAUDE.md（3 分钟）。
- 安装五个入门技能（5 分钟）。
- 添加 git 防护措施（1 分钟）。
- 连接一个 MCP 服务器（2 分钟）。
- 添加 Prettier 钩子（2 分钟）。
然后打开一个真实项目，给 Claude 一个真实的任务。不是“写个 hello world”，而是你今天真正要做的工作。
那第一次会话与你之前体验的 Claude Code 之间的差别不会是细微的。
它将是显而易见的。而且将是永久性的。
把这篇文章发给你团队里那位曾安装过 Claude Code、试了一个提示词、然后又回到 Cursor 的开发者。他们之前没有看到真正的工具。现在他们会看到了。
## 相关链接
- [Guri Singh](https://x.com/heygurisingh)
- [@heygurisingh](https://x.com/heygurisingh)
- [4.6K](https://x.com/heygurisingh/status/2045209540313178527/analytics)
- [https://cli.claude.com/install.sh](https://cli.claude.com/install.sh)
- [https://cli.claude.com/install.sh](https://cli.claude.com/install.sh)
- [https://cli.claude.com/install.ps1](https://cli.claude.com/install.ps1)
- [https://cli.claude.com/install.bat](https://cli.claude.com/install.bat)
- [https://github.com/obra/superpowers](https://github.com/obra/superpowers)
- [@modelcontextprotocol/server-github](https://x.com/@modelcontextprotocol/server-github)
- [skillsmp.com](https://skillsmp.com/)
- [升级到 Premium](https://x.com/i/premium_sign_up)
- [2026年4月18日 凌晨2:35](https://x.com/heygurisingh/status/2045209540313178527)
- [4,637 次浏览](https://x.com/heygurisingh/status/2045209540313178527/analytics)
---
*导出时间： 2026/4/18 11:06:18*
