claude-code-setup

Original source / Raw SKILL.md

---
name: claude-code-setup
description: Setup production-grade .claude/ AI collaboration layer for projects. Use when an agent starts using Claude Code for development, enters a new project directory, or when user mentions "Claude Code", ".claude config", "AI collaboration layer", or "project standards".
license: MIT
metadata:
  author: Eave
  version: "1.0.1"
---

# Claude Code Setup

Setup production-grade \`.claude/\` AI collaboration layer for projects.

## Overview

This skill ensures projects have a proper \`.claude/\` configuration before agents start development work with Claude Code. It acts as a supervisor to maintain and enforce project standards.

## Important: Target Project Directory

**.claude/ must be created in the target project directory, NOT in your workspace root.**

Example:
- ❌ Wrong: `/home/user/workspace-xiaolong/.claude/` (workspace root)
- ✅ Correct: `/home/user/eave-web/.claude/` (actual project being developed)

Always identify which project you're working on first, then check/create `.claude/` in **that** directory.

## When to Use

- Starting a new development task with Claude Code
- Entering a new project directory  
- User mentions "Claude Code", ".claude", "AI collaboration layer", or "project standards"

## Workflow

### Step 1 — Check First

Always check if \`.claude/\` directory already exists **in the target project directory**:

\`\`\`bash
ls -la .claude/ 2>/dev/null
\`\`\`

### Step 2 — If Missing → Create

If the project doesn't have \`.claude/\` directory, **create it first** before development:

\`\`\`bash
node ~/.openclaw/skills/claude-code-setup/index.js
\`\`\`

### Step 3 — If Exists → Supervise

If \`.claude/\` already exists:
- ✅ **DO NOT overwrite** existing files
- ✅ **DO NOT recreate** the structure
- ✅ Let Claude Code naturally maintain and update during development

### Step 4 — Be a Supervisor

Your role is **supervisor**, not executor:
- Ensure Claude Code follows rules in \`.claude/\`
- During development, let Claude Code update configs based on actual code
- Periodically review if \`.claude/\` content matches the project reality

## Core Principles

1. **CLAUDE.md is core** — Highest priority project instructions
2. **Modular** — Separate rules/skills/context
3. **Clear directives** — Use MUST/ALWAYS/NEVER
4. **Project context** — Must include project overview and tech stack
5. **Don't reinvent** — Reuse and maintain existing configs

## .claude/ Directory Structure

\`\`\`
.claude/
├── CLAUDE.md              # ⭐ Project-level global instructions (most important)
├── rules/                 # Team rule library
│   ├── frontend.md
│   ├── typescript.md
│   └── commit.md
├── context/               # Project context knowledge
│   ├── project.md
│   └── stack.md
├── skills/                # Project-private skills
│   └── generate-crud.md
└── prompts/               # Reusable prompt templates
    └── review.md
\`\`\`

## Common Mistakes to Avoid

❌ Writing as requirements doc or README  
❌ Vague rules ("try to", "should")  
❌ Only CLAUDE.md without modularity  
❌ Missing project context  
❌ Overwriting existing configs  
❌ Redundant recreation

## Collaboration with Claude Code

When using Claude Code:

1. **Before starting**: Ensure \`.claude/\` exists
2. **During development**: Let Claude Code reference rules in \`.claude/\`
3. **After completion**: Update \`.claude/\` with any new standards learned

## Template Files

See \`index.js\` for template definitions.


---

## Skill Companion Files

> Additional files collected from the skill directory layout.

### README.md

```markdown
# claude-code-setup

为项目创建生产级 `.claude/` AI 协作层配置。

## 快速开始

```bash
# 在项目根目录运行
openclaw skill claude-code-setup
```

## 生成的目录结构

```
.claude/
├── CLAUDE.md              # ⭐ 项目级全局指令（最重要）
├── rules/                 # 团队规则库
│   ├── frontend.md        # React/Vue 组件规范
│   ├── typescript.md      # TypeScript 类型规则
│   └── commit.md          # Git 提交规范
├── context/               # 项目上下文知识
│   ├── project.md         # 项目概述和模块
│   └── stack.md           # 技术栈详情
├── skills/                # 项目私有技能
│   └── generate-crud.md   # CRUD 生成工作流
└── prompts/               # 可复用 Prompt 模板
    └── review.md          # 代码审查清单
```

## 核心文件说明

### CLAUDE.md

权重最高的项目指令，Claude Code 每次工作都会优先读取。

**关键内容：**
- AI 角色定义
- 技术栈声明
- 编码规则（MUST/ALWAYS/NEVER）
- 代码生成要求

### rules/

团队硬规则，AI 必须遵守的约束。

**规则示例：**
- `NEVER use any type`
- `ALWAYS include error handling`
- `MUST use functional components`

### context/

项目知识库，让 Claude 真正理解你的项目。

**包含：**
- 项目概述
- 核心模块
- 技术栈详情

### skills/

可复用的工作流模板。

**示例：**
- CRUD 生成流程
- API 设计规范
- 测试编写流程

## 最佳实践

### ✅ 必做

1. **CLAUDE.md 控总规则** - 定义 AI 行为和约束
2. **rules/ 放硬约束** - 使用 MUST/ALWAYS/NEVER
3. **context/ 放项目知识** - 让 AI 理解项目背景
4. **skills/ 放稳定工作流** - 复用最佳实践

### ❌ 避免

1. 写成需求文档或 README
2. 规则太模糊（"尽量"、"建议"）
3. 只有 CLAUDE.md 没有模块化
4. 缺少项目上下文
5. 写太长废话

## 自定义

编辑生成的文件以适配你的项目：

```bash
# 修改 CLAUDE.md 添加项目特定规则
vim .claude/CLAUDE.md

# 添加新的规则
vim .claude/rules/backend.md

# 添加项目特定的技能
vim .claude/skills/generate-api.md
```

## 与其他工具对比

| 目录 | 作用 |
|------|------|
| `.vscode/` | 编辑器配置 |
| `.github/` | CI/CD 和 PR 模板 |
| `.cursor/` | Cursor IDE 配置 |
| **`.claude/`** | **Claude Code AI 行为中枢** |

## 许可证

MIT

```

### _meta.json

```json
{
  "owner": "eaveluo",
  "slug": "claude-code-setup",
  "displayName": "Claude Code Setup",
  "latest": {
    "version": "1.0.1",
    "publishedAt": 1772309296257,
    "commit": "https://github.com/openclaw/skills/commit/145dc9b5f82d20c65faf741940dee289acd2f6e9"
  },
  "history": []
}

```