docs: 完成所有文档的中文翻译并应用到项目

This commit is contained in:
xuxiang
2026-01-28 00:12:54 +08:00
parent 0ced59a26b
commit e133f58e1c
76 changed files with 6808 additions and 6170 deletions

View File

@@ -1,49 +1,49 @@
# Agent Orchestration
# 智能体编排 (Agent Orchestration)
## Available Agents
## 可用智能体 (Available Agents)
Located in `~/.claude/agents/`:
位于 `~/.claude/agents/`
| Agent | Purpose | When to Use |
| 智能体 (Agent) | 用途 | 适用场景 |
|-------|---------|-------------|
| planner | Implementation planning | Complex features, refactoring |
| architect | System design | Architectural decisions |
| tdd-guide | Test-driven development | New features, bug fixes |
| code-reviewer | Code review | After writing code |
| security-reviewer | Security analysis | Before commits |
| build-error-resolver | Fix build errors | When build fails |
| e2e-runner | E2E testing | Critical user flows |
| refactor-cleaner | Dead code cleanup | Code maintenance |
| doc-updater | Documentation | Updating docs |
| planner | 实现规划 | 复杂特性、重构 |
| architect | 系统设计 | 架构决策 |
| tdd-guide | 测试驱动开发 (TDD) | 新特性、Bug 修复 |
| code-reviewer | 代码审查 | 代码编写/修改后 |
| security-reviewer | 安全分析 | 提交代码前 |
| build-error-resolver | 修复构建错误 | 构建失败时 |
| e2e-runner | 端到端 (E2E) 测试 | 关键用户流程 |
| refactor-cleaner | 冗余代码清理 | 代码维护 |
| doc-updater | 文档更新 | 更新文档 |
## Immediate Agent Usage
## 立即调用智能体 (Immediate Agent Usage)
No user prompt needed:
1. Complex feature requests - Use **planner** agent
2. Code just written/modified - Use **code-reviewer** agent
3. Bug fix or new feature - Use **tdd-guide** agent
4. Architectural decision - Use **architect** agent
以下情况无需用户提示即可直接调用:
1. 复杂特性请求 - 使用 **planner** 智能体
2. 刚刚编写/修改的代码 - 使用 **code-reviewer** 智能体
3. Bug 修复或新特性 - 使用 **tdd-guide** 智能体
4. 架构决策 - 使用 **architect** 智能体
## Parallel Task Execution
## 并行任务执行 (Parallel Task Execution)
ALWAYS use parallel Task execution for independent operations:
对于相互独立的操作,**务必**使用并行任务执行:
```markdown
# GOOD: Parallel execution
Launch 3 agents in parallel:
1. Agent 1: Security analysis of auth.ts
2. Agent 2: Performance review of cache system
3. Agent 3: Type checking of utils.ts
# 推荐:并行执行
并行启动 3 个智能体:
1. 智能体 1 auth.ts 进行安全分析
2. 智能体 2对缓存系统进行性能审查
3. 智能体 3 utils.ts 进行类型检查
# BAD: Sequential when unnecessary
First agent 1, then agent 2, then agent 3
# 避忌:在不必要时采用串行执行
先启动智能体 1然后智能体 2最后智能体 3
```
## Multi-Perspective Analysis
## 多维度分析 (Multi-Perspective Analysis)
For complex problems, use split role sub-agents:
- Factual reviewer
- Senior engineer
- Security expert
- Consistency reviewer
- Redundancy checker
针对复杂问题,使用分角色子智能体:
- 事实审查员 (Factual Reviewer)
- 资深工程师 (Senior Engineer)
- 安全专家 (Security Expert)
- 一致性审查员 (Consistency Reviewer)
- 冗余检查员 (Redundancy Checker)

View File

@@ -1,17 +1,17 @@
# Coding Style
# 代码风格 (Coding Style)
## Immutability (CRITICAL)
## 不可变性 (Immutability)(至关重要)
ALWAYS create new objects, NEVER mutate:
始终创建新对象,严禁修改原对象 (Mutation)
```javascript
// WRONG: Mutation
// 错误:修改原对象 (Mutation)
function updateUser(user, name) {
user.name = name // MUTATION!
user.name = name // 直接修改了原对象!
return user
}
// CORRECT: Immutability
// 正确:不可变性 (Immutability)
function updateUser(user, name) {
return {
...user,
@@ -20,17 +20,17 @@ function updateUser(user, name) {
}
```
## File Organization
## 文件组织
MANY SMALL FILES > FEW LARGE FILES:
- High cohesion, low coupling
- 200-400 lines typical, 800 max
- Extract utilities from large components
- Organize by feature/domain, not by type
提倡“多而小”的文件,而非“少而大”的文件:
- 高内聚,低耦合
- 建议每文件 200-400 行,最大不超过 800
- 从大型组件中提取工具函数 (Utilities)
- 按功能/领域 (Feature/Domain) 组织,而非按类型 (Type) 组织
## Error Handling
## 错误处理
ALWAYS handle errors comprehensively:
始终进行全面的错误处理:
```typescript
try {
@@ -42,9 +42,9 @@ try {
}
```
## Input Validation
## 输入校验
ALWAYS validate user input:
始终校验用户输入:
```typescript
import { z } from 'zod'
@@ -57,14 +57,14 @@ const schema = z.object({
const validated = schema.parse(input)
```
## Code Quality Checklist
## 代码质量自检清单
Before marking work complete:
- [ ] Code is readable and well-named
- [ ] Functions are small (<50 lines)
- [ ] Files are focused (<800 lines)
- [ ] No deep nesting (>4 levels)
- [ ] Proper error handling
- [ ] No console.log statements
- [ ] No hardcoded values
- [ ] No mutation (immutable patterns used)
在标记工作完成之前:
- [ ] 代码易读且命名良好
- [ ] 函数体量小(<50 行)
- [ ] 文件内容聚焦(<800 行)
- [ ] 无深度嵌套(>4 层)
- [ ] 具备完善的错误处理
- [ ] 不存在 console.log 语句
- [ ] 不存在硬编码 (Hardcoded) 数值
- [ ] 不存在修改原对象 (Mutation) 操作(已采用不可变模式)

View File

@@ -1,6 +1,6 @@
# Git Workflow
# Git 工作流 (Git Workflow)
## Commit Message Format
## 提交信息格式 (Commit Message Format)
```
<type>: <description>
@@ -8,38 +8,38 @@
<optional body>
```
Types: feat, fix, refactor, docs, test, chore, perf, ci
类型 (Types): feat, fix, refactor, docs, test, chore, perf, ci
Note: Attribution disabled globally via ~/.claude/settings.json.
注意:归属归因 (Attribution) 已通过 `~/.claude/settings.json` 全局禁用。
## Pull Request Workflow
## 拉取请求工作流 (Pull Request Workflow)
When creating PRs:
1. Analyze full commit history (not just latest commit)
2. Use `git diff [base-branch]...HEAD` to see all changes
3. Draft comprehensive PR summary
4. Include test plan with TODOs
5. Push with `-u` flag if new branch
创建 PR 时:
1. 分析完整的提交历史(不仅是最近一次提交)
2. 使用 `git diff [base-branch]...HEAD` 查看所有变更
3. 起草详尽的 PR 摘要
4. 包含带有 TODO 的测试计划
5. 如果是新分支,使用 `-u` 参数推送
## Feature Implementation Workflow
## 功能实现工作流 (Feature Implementation Workflow)
1. **Plan First**
- Use **planner** agent to create implementation plan
- Identify dependencies and risks
- Break down into phases
1. **规划先行 (Plan First)**
- 使用 **planner** 智能体 (Agent) 创建实现计划
- 识别依赖关系与风险
- 拆分为多个阶段
2. **TDD Approach**
- Use **tdd-guide** agent
- Write tests first (RED)
- Implement to pass tests (GREEN)
- Refactor (IMPROVE)
- Verify 80%+ coverage
2. **测试驱动开发 (TDD Approach)**
- 使用 **tdd-guide** 智能体 (Agent)
- 先编写测试 (RED)
- 实现功能以通过测试 (GREEN)
- 重构 (IMPROVE)
- 验证 80% 以上的覆盖率
3. **Code Review**
- Use **code-reviewer** agent immediately after writing code
- Address CRITICAL and HIGH issues
- Fix MEDIUM issues when possible
3. **代码评审 (Code Review)**
- 在编写代码后立即使用 **code-reviewer** 智能体 (Agent)
- 解决严重 (CRITICAL) 和高 (HIGH) 等级的问题
- 尽可能修复中 (MEDIUM) 等级的问题
4. **Commit & Push**
- Detailed commit messages
- Follow conventional commits format
4. **提交与推送 (Commit & Push)**
- 详细的提交信息
- 遵循约定式提交 (Conventional Commits) 格式

View File

@@ -1,46 +1,46 @@
# Hooks System
# 钩子系统(Hooks System
## Hook Types
## 钩子类型(Hook Types
- **PreToolUse**: Before tool execution (validation, parameter modification)
- **PostToolUse**: After tool execution (auto-format, checks)
- **Stop**: When session ends (final verification)
- **工具调用前(PreToolUse**:在工具执行之前(验证、参数修改)
- **工具调用后(PostToolUse**:在工具执行之后(自动格式化、检查)
- **会话终止(Stop**:当会话结束时(最终验证)
## Current Hooks (in ~/.claude/settings.json)
## 当前已配置的钩子(Current Hooks)(位于 ~/.claude/settings.json 中)
### PreToolUse
- **tmux reminder**: Suggests tmux for long-running commands (npm, pnpm, yarn, cargo, etc.)
- **git push review**: Opens Zed for review before push
- **doc blocker**: Blocks creation of unnecessary .md/.txt files
### 工具调用前(PreToolUse
- **tmux 提醒**:针对耗时较长的命令(npm, pnpm, yarn, cargo 等)建议使用 tmux
- **git push 审查**在推送push之前打开 Zed 进行代码审查
- **文档拦截器(doc blocker**:拦截不必要的 .md/.txt 文件创建
### PostToolUse
- **PR creation**: Logs PR URL and GitHub Actions status
- **Prettier**: Auto-formats JS/TS files after edit
- **TypeScript check**: Runs tsc after editing .ts/.tsx files
- **console.log warning**: Warns about console.log in edited files
### 工具调用后(PostToolUse
- **PR 创建**:记录 PR URL GitHub Actions 状态
- **Prettier**:编辑后自动格式化 JS/TS 文件
- **TypeScript 检查**:编辑 .ts/.tsx 文件后运行 tsc
- **console.log 警告**:对已编辑文件中的 console.log 发出警告
### Stop
- **console.log audit**: Checks all modified files for console.log before session ends
### 会话终止(Stop
- **console.log 审计**:在会话结束前检查所有已修改的文件中是否存在 console.log
## Auto-Accept Permissions
## 自动授权许可(Auto-Accept Permissions
Use with caution:
- Enable for trusted, well-defined plans
- Disable for exploratory work
- Never use dangerously-skip-permissions flag
- Configure `allowedTools` in `~/.claude.json` instead
请谨慎使用:
- 仅对受信任且定义明确的任务方案启用
- 在探索性工作中禁用
- 严禁使用 `dangerously-skip-permissions` 标志
- 改为在 `~/.claude.json` 中配置 `allowedTools`
## TodoWrite Best Practices
## TodoWrite 最佳实践
Use TodoWrite tool to:
- Track progress on multi-step tasks
- Verify understanding of instructions
- Enable real-time steering
- Show granular implementation steps
使用 TodoWrite 工具Tool
- 跟踪多步骤任务的进度
- 验证对指令的理解程度
- 实现实时引导(steering
- 展示细粒度的实现步骤
Todo list reveals:
- Out of order steps
- Missing items
- Extra unnecessary items
- Wrong granularity
- Misinterpreted requirements
待办事项列表(Todo list)能够揭示:
- 步骤顺序错乱
- 遗漏项
- 多余的不必要项
- 粒度错误
- 需求误读

View File

@@ -1,6 +1,6 @@
# Common Patterns
# 通用模式(Common Patterns
## API Response Format
## API 响应格式API Response Format
```typescript
interface ApiResponse<T> {
@@ -15,7 +15,7 @@ interface ApiResponse<T> {
}
```
## Custom Hooks Pattern
## 自定义 Hook 模式(Custom Hooks Pattern
```typescript
export function useDebounce<T>(value: T, delay: number): T {
@@ -30,7 +30,7 @@ export function useDebounce<T>(value: T, delay: number): T {
}
```
## Repository Pattern
## 仓储模式(Repository Pattern
```typescript
interface Repository<T> {
@@ -42,14 +42,14 @@ interface Repository<T> {
}
```
## Skeleton Projects
## 骨架项目(Skeleton Projects
When implementing new functionality:
1. Search for battle-tested skeleton projects
2. Use parallel agents to evaluate options:
- Security assessment
- Extensibility analysis
- Relevance scoring
- Implementation planning
3. Clone best match as foundation
4. Iterate within proven structure
在实现新功能时:
1. 搜索经过实战检验的骨架项目Skeleton Projects
2. 使用并行智能体Parallel Agents)评估备选项:
- 安全性评估(Security assessment
- 可扩展性分析(Extensibility analysis
- 相关性评分(Relevance scoring
- 实施计划(Implementation planning
3. 克隆最匹配的项目作为基础
4. 在已验证的结构内进行迭代

View File

@@ -1,47 +1,47 @@
# Performance Optimization
# 性能优化(Performance Optimization
## Model Selection Strategy
## 模型选择策略(Model Selection Strategy
**Haiku 4.5** (90% of Sonnet capability, 3x cost savings):
- Lightweight agents with frequent invocation
- Pair programming and code generation
- Worker agents in multi-agent systems
**Haiku 4.5**(具备 Sonnet 90% 的能力,节省 3 倍成本):
- 频繁调用的轻量级智能体Agents
- 结对编程与代码生成
- 多智能体系统中的执行者智能体Worker agents
**Sonnet 4.5** (Best coding model):
- Main development work
- Orchestrating multi-agent workflows
- Complex coding tasks
**Sonnet 4.5**(最佳编程模型):
- 主力开发工作
- 编排多智能体工作流Workflow
- 复杂的编程任务
**Opus 4.5** (Deepest reasoning):
- Complex architectural decisions
- Maximum reasoning requirements
- Research and analysis tasks
**Opus 4.5**(最深层的推理能力):
- 复杂的架构决策
- 极高的推理需求
- 研究与分析任务
## Context Window Management
## 上下文窗口管理(Context Window Management
Avoid last 20% of context window for:
- Large-scale refactoring
- Feature implementation spanning multiple files
- Debugging complex interactions
在以下场景中避免触及上下文窗口Context Window)最后 20% 的容量:
- 大规模重构
- 涉及多个文件的功能实现
- 调试复杂的交互逻辑
Lower context sensitivity tasks:
- Single-file edits
- Independent utility creation
- Documentation updates
- Simple bug fixes
对上下文敏感度较低的任务:
- 单文件编辑
- 独立工具函数创建
- 文档更新
- 简单的 Bug 修复
## Ultrathink + Plan Mode
## Ultrathink + 计划模式(Plan Mode
For complex tasks requiring deep reasoning:
1. Use `ultrathink` for enhanced thinking
2. Enable **Plan Mode** for structured approach
3. "Rev the engine" with multiple critique rounds
4. Use split role sub-agents for diverse analysis
对于需要深度推理的复杂任务:
1. 使用 `ultrathink` 以获得增强的思维过程
2. 启用 **计划模式(Plan Mode** 以采用结构化方法
3. 通过多轮评审Critique rounds)来“预热引擎”
4. 使用分角色的子智能体Sub-agents进行多样化分析
## Build Troubleshooting
## 构建故障排除(Build Troubleshooting
If build fails:
1. Use **build-error-resolver** agent
2. Analyze error messages
3. Fix incrementally
4. Verify after each fix
如果构建失败:
1. 使用 **build-error-resolver** 智能体
2. 分析错误消息
3. 采用增量方式修复
4. 每次修复后进行验证

View File

@@ -1,24 +1,24 @@
# Security Guidelines
# 安全指南 (Security Guidelines)
## Mandatory Security Checks
## 强制安全检查 (Mandatory Security Checks)
Before ANY commit:
- [ ] No hardcoded secrets (API keys, passwords, tokens)
- [ ] All user inputs validated
- [ ] SQL injection prevention (parameterized queries)
- [ ] XSS prevention (sanitized HTML)
- [ ] CSRF protection enabled
- [ ] Authentication/authorization verified
- [ ] Rate limiting on all endpoints
- [ ] Error messages don't leak sensitive data
在任何提交Commit)之前:
- [ ] 无硬编码凭据API 密钥、密码、令牌/Tokens
- [ ] 所有用户输入均已验证
- [ ] 预防 SQL 注入(使用参数化查询)
- [ ] 预防 XSS对 HTML 进行净化处理/Sanitized
- [ ] 已启用 CSRF 保护
- [ ] 身份验证/授权已验证
- [ ] 所有端点均已设置速率限制Rate limiting
- [ ] 错误消息不泄露敏感数据
## Secret Management
## 凭据管理 (Secret Management)
```typescript
// NEVER: Hardcoded secrets
// 严禁:硬编码凭据
const apiKey = "sk-proj-xxxxx"
// ALWAYS: Environment variables
// 推荐:环境变量
const apiKey = process.env.OPENAI_API_KEY
if (!apiKey) {
@@ -26,11 +26,11 @@ if (!apiKey) {
}
```
## Security Response Protocol
## 安全响应协议 (Security Response Protocol)
If security issue found:
1. STOP immediately
2. Use **security-reviewer** agent
3. Fix CRITICAL issues before continuing
4. Rotate any exposed secrets
5. Review entire codebase for similar issues
如果发现安全问题:
1. 立即停止STOP
2. 使用 **security-reviewer** 智能体Agent
3. 在继续之前修复严重CRITICAL问题
4. 轮换任何暴露的凭据
5. 审查整个代码库是否存在类似问题

View File

@@ -1,30 +1,30 @@
# Testing Requirements
# 测试要求
## Minimum Test Coverage: 80%
## 最低测试覆盖率:80%
Test Types (ALL required):
1. **Unit Tests** - Individual functions, utilities, components
2. **Integration Tests** - API endpoints, database operations
3. **E2E Tests** - Critical user flows (Playwright)
测试类型(全部必选):
1. **单元测试(Unit Tests** - 独立函数、工具类、组件
2. **集成测试(Integration Tests** - API 终端、数据库操作
3. **端到端测试(E2E Tests** - 关键用户流程 (Playwright)
## Test-Driven Development
## 测试驱动开发TDD
MANDATORY workflow:
1. Write test first (RED)
2. Run test - it should FAIL
3. Write minimal implementation (GREEN)
4. Run test - it should PASS
5. Refactor (IMPROVE)
6. Verify coverage (80%+)
强制工作流(MANDATORY workflow
1. 先写测试(红 / RED
2. 运行测试 - 应当失败(FAIL
3. 编写最简实现代码(绿 / GREEN
4. 运行测试 - 应当通过(PASS
5. 重构(优化 / IMPROVE
6. 验证覆盖率(80%+
## Troubleshooting Test Failures
## 测试失败排查
1. Use **tdd-guide** agent
2. Check test isolation
3. Verify mocks are correct
4. Fix implementation, not tests (unless tests are wrong)
1. 使用 **tdd-guide** 智能体Agent
2. 检查测试隔离性
3. 验证 Mock 是否正确
4. 修复实现逻辑,而非测试代码(除非测试代码本身有误)
## Agent Support
## 智能体支持(Agent Support
- **tdd-guide** - Use PROACTIVELY for new features, enforces write-tests-first
- **e2e-runner** - Playwright E2E testing specialist
- **tdd-guide** - 主动用于开发新特性,强制执行“先写测试”原则
- **e2e-runner** - Playwright E2E 测试专家