用一个周末掌握 Claude Code

# Slash Commands
cp 01-slash-commands/*.md .claude/commands/

# Memory
cp 02-memory/project-CLAUDE.md ./CLAUDE.md

# Skills
cp -r 03-skills/code-review-specialist ~/.claude/skills/

# Subagents
cp 04-subagents/*.md .claude/agents/

# MCP
export GITHUB_TOKEN="token"
claude mcp add github -- npx -y @modelcontextprotocol/server-github

# Hooks
mkdir -p ~/.claude/hooks
cp 06-hooks/*.sh ~/.claude/hooks/
chmod +x ~/.claude/hooks/*.sh

# Plugins
/plugin install pr-review

# Checkpoints（默认自动开启，可在设置中配置）
# 参见 08-checkpoints/README.md

# Advanced Features（在设置中配置）
# 参见 09-advanced-features/config-examples.json

# CLI Reference（无需安装）
# 使用示例见 10-cli/README.md

cp 01-slash-commands/*.md /path/to/project/.claude/commands/

/optimize
/pr
/generate-api-docs

# 项目记忆
cp 02-memory/project-CLAUDE.md /path/to/project/CLAUDE.md

# 目录记忆
cp 02-memory/directory-api-CLAUDE.md /path/to/project/src/api/CLAUDE.md

# 个人记忆
cp 02-memory/personal-CLAUDE.md ~/.claude/CLAUDE.md

# 个人 skills
cp -r 03-skills/code-review-specialist ~/.claude/skills/

# 项目 skills
cp -r 03-skills/code-review-specialist /path/to/project/.claude/skills/

cp 04-subagents/*.md /path/to/project/.claude/agents/

# 设置环境变量
export GITHUB_TOKEN="your_token"
export DATABASE_URL="postgresql://..."

# 通过 CLI 添加 MCP server
claude mcp add github -- npx -y @modelcontextprotocol/server-github

# 或手动添加到项目 .mcp.json（参见 [05-mcp/README.md](05-mcp/README.md) 中的示例）

mkdir -p ~/.claude/hooks
cp 06-hooks/*.sh ~/.claude/hooks/
chmod +x ~/.claude/hooks/*.sh

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "Write",
      "hooks": ["~/.claude/hooks/format-code.sh"]
    }],
    "PostToolUse": [{
      "matcher": "Write",
      "hooks": ["~/.claude/hooks/security-scan.sh"]
    }]
  }
}

/plugin install pr-review
/plugin install devops-automation
/plugin install documentation

# 每次用户提示后都会自动创建 checkpoint
# 如需回退，按两次 Esc，或者使用：
/rewind

# 然后从以下五个选项中选择：
# 1. 恢复代码和对话
# 2. 恢复对话
# 3. 恢复代码
# 4. 从这里开始总结
# 5. 算了

# 交互模式
claude "explain this project"

# 输出模式（非交互）
claude -p "review this code"

# 处理文件内容
cat error.log | claude -p "explain this error"

# 为脚本输出 JSON
claude -p --output-format json "list functions"

# 恢复会话
claude -r "feature-auth" "continue implementation"

# 使用：Slash Commands + Subagents + Memory + MCP

用户：/review-pr

Claude：
1. 加载项目 memory（编码规范）
2. 通过 GitHub MCP 获取 PR
3. 委派给 code-reviewer subagent
4. 委派给 test-engineer subagent
5. 汇总发现
6. 提供完整审查结果

# 使用：Skills + Subagents + Memory

用户："为 auth 模块生成 API 文档"

Claude：
1. 加载项目 memory（文档规范）
2. 识别出文档生成请求
3. 自动触发 doc-generator skill
4. 委派给 api-documenter subagent
5. 生成带示例的完整文档

# 使用：Plugins + MCP + Hooks

用户：/deploy production

Claude：
1. 运行部署前 hook（校验环境）
2. 委派给 deployment-specialist subagent
3. 通过 Kubernetes MCP 执行部署
4. 监控进度
5. 运行部署后 hook（健康检查）
6. 报告状态

├── 01-slash-commands/
│   ├── optimize.md
│   ├── pr.md
│   ├── generate-api-docs.md
│   └── README.md
├── 02-memory/
│   ├── project-CLAUDE.md
│   ├── directory-api-CLAUDE.md
│   ├── personal-CLAUDE.md
│   └── README.md
├── 03-skills/
│   ├── code-review/
│   │   ├── SKILL.md
│   │   ├── scripts/
│   │   └── templates/
│   ├── brand-voice/
│   │   ├── SKILL.md
│   │   └── templates/
│   ├── doc-generator/
│   │   ├── SKILL.md
│   │   └── generate-docs.py
│   └── README.md
├── 04-subagents/
│   ├── code-reviewer.md
│   ├── test-engineer.md
│   ├── documentation-writer.md
│   ├── secure-reviewer.md
│   ├── implementation-agent.md
│   └── README.md
├── 05-mcp/
│   ├── github-mcp.json
│   ├── database-mcp.json
│   ├── filesystem-mcp.json
│   ├── multi-mcp.json
│   └── README.md
├── 06-hooks/
│   ├── format-code.sh
│   ├── pre-commit.sh
│   ├── security-scan.sh
│   ├── log-bash.sh
│   ├── validate-prompt.sh
│   ├── notify-team.sh
│   └── README.md
├── 07-plugins/
│   ├── pr-review/
│   ├── devops-automation/
│   ├── documentation/
│   └── README.md
├── 08-checkpoints/
│   ├── checkpoint-examples.md
│   └── README.md
├── 09-advanced-features/
│   ├── config-examples.json
│   ├── planning-mode-examples.md
│   └── README.md
├── 10-cli/
│   └── README.md
└── README.md（本文件）

# 安装开发依赖
uv pip install -r requirements-dev.txt

# 运行全部单元测试
pytest scripts/tests/ -v

# 运行带覆盖率报告的测试
pytest scripts/tests/ -v --cov=scripts --cov-report=html

# 运行代码质量检查
ruff check scripts/
ruff format --check scripts/

# 运行安全扫描
bandit -c pyproject.toml -r scripts/ --exclude scripts/tests/

# 运行类型检查
mypy scripts/ --ignore-missing-imports

uv run scripts/build_epub.py