docs(zh-CN): translate code block(plain text) (#753)

Co-authored-by: neo <neo.dowithless@gmail.com>
2026-03-30 13:43:26 +08:00 · 2026-03-23 06:39:24 +08:00
parent fd2a8edb53
commit 4f6f587700
118 changed files with 1807 additions and 1835 deletions
--- a/docs/zh-CN/AGENTS.md
+++ b/docs/zh-CN/AGENTS.md
@@ -146,14 +146,14 @@
 ## 项目结构

 ```
-agents/          — 28 specialized subagents
-skills/          — 115 workflow skills and domain knowledge
-commands/        — 59 slash commands
-hooks/           — Trigger-based automations
-rules/           — Always-follow guidelines (common + per-language)
-scripts/         — Cross-platform Node.js utilities
-mcp-configs/     — 14 MCP server configurations
-tests/           — Test suite
+agents/          — 28 个专业子代理
+skills/          — 115 个工作流技能和领域知识
+commands/        — 59 个斜杠命令
+hooks/           — 基于触发的自动化
+rules/           — 始终遵循的指导方针（通用 + 每种语言）
+scripts/         — 跨平台 Node.js 实用工具
+mcp-configs/     — 14 个 MCP 服务器配置
+tests/           — 测试套件
 ```

 ## 成功指标
--- a/docs/zh-CN/CONTRIBUTING.md
+++ b/docs/zh-CN/CONTRIBUTING.md
@@ -390,11 +390,11 @@ ECC 为其他平台提供了技能子集：
 ### 1. PR 标题格式

 ```
-feat(skills): add rust-patterns skill
-feat(agents): add api-designer agent
-feat(hooks): add auto-format hook
-fix(skills): update React patterns
-docs: improve contributing guide
+feat(skills): 新增 Rust 模式技能
+feat(agents): 新增 API 设计器代理
+feat(hooks): 新增自动格式化钩子
+fix(skills): 更新 React 模式
+docs: 完善贡献指南
 ```

 ### 2. PR 描述
--- a/docs/zh-CN/README.md
+++ b/docs/zh-CN/README.md
@@ -567,7 +567,7 @@ claude --version
 Claude Code v2.1+ **会自动加载** 任何已安装插件中的 `hooks/hooks.json`（按约定）。在 `plugin.json` 中显式声明会导致重复检测错误：

 ```
-Duplicate hooks file detected: ./hooks/hooks.json resolves to already-loaded file
+重复的钩子文件检测到：./hooks/hooks.json 解析到已加载的文件
 ```

 **历史背景：** 这已导致此仓库中多次修复/还原循环（[#29](https://github.com/affaan-m/everything-claude-code/issues/29), [#52](https://github.com/affaan-m/everything-claude-code/issues/52), [#103](https://github.com/affaan-m/everything-claude-code/issues/103)）。Claude Code 版本之间的行为发生了变化，导致了混淆。我们现在有一个回归测试来防止这种情况再次发生。
@@ -726,12 +726,12 @@ model: opus

 ```
 rules/
-  common/          # Universal principles (always install)
-  typescript/      # TS/JS specific patterns and tools
-  python/          # Python specific patterns and tools
-  golang/          # Go specific patterns and tools
-  swift/           # Swift specific patterns and tools
-  php/             # PHP specific patterns and tools
+  common/          # 通用原则（始终安装）
+  typescript/      # TS/JS 特定模式与工具
+  python/          # Python 特定模式与工具
+  golang/          # Go 特定模式与工具
+  swift/           # Swift 特定模式与工具
+  php/             # PHP 特定模式与工具
 ```

 有关安装和结构详情，请参阅 [`rules/README.md`](rules/README.md)。
@@ -763,26 +763,26 @@ rules/
 **开始新功能：**

 ```
-/everything-claude-code:plan "Add user authentication with OAuth"
-                                              → planner creates implementation blueprint
-/tdd                                          → tdd-guide enforces write-tests-first
-/code-review                                  → code-reviewer checks your work
+/everything-claude-code:plan "使用 OAuth 添加用户身份验证"
+                                              → 规划器创建实现蓝图
+/tdd                                          → tdd-guide 强制执行先写测试
+/code-review                                  → 代码审查员检查你的工作
 ```

 **修复错误：**

 ```
-/tdd                                          → tdd-guide: write a failing test that reproduces it
-                                              → implement the fix, verify test passes
-/code-review                                  → code-reviewer: catch regressions
+/tdd                                          → tdd-guide：编写一个能复现问题的失败测试
+                                              → 实现修复，验证测试通过
+/code-review                                  → code-reviewer：捕捉回归问题
 ```

 **准备生产环境：**

 ```
-/security-scan                                → security-reviewer: OWASP Top 10 audit
-/e2e                                          → e2e-runner: critical user flow tests
-/test-coverage                                → verify 80%+ coverage
+/security-scan                                → security-reviewer: OWASP Top 10 审计
+/e2e                                          → e2e-runner: 关键用户流程测试
+/test-coverage                                → verify 80%+ 覆盖率
 ```

 ***
@@ -970,7 +970,7 @@ Cursor 的**钩子事件比 Claude Code 多**（20 对 8）。`.cursor/hooks/ada

 ```
 Cursor stdin JSON → adapter.js → transforms → scripts/hooks/*.js
-                                              (shared with Claude Code)
+                                              (与 Claude Code 共享)
 ```

 关键钩子：
--- a/docs/zh-CN/agents/chief-of-staff.md
+++ b/docs/zh-CN/agents/chief-of-staff.md
@@ -64,7 +64,7 @@ gog calendar events --today --all --max 30
 ```

 ```text
-# Slack (via MCP)
+# Slack（通过 MCP）
 conversations_search_messages(search_query: "YOUR_NAME", filter_date_during: "Today")
 channels_list(channel_types: "im,mpim") → conversations_history(limit: "4h")
 ```
@@ -109,26 +109,26 @@ channels_list(channel_types: "im,mpim") → conversations_history(limit: "4h")
 ## 简报输出格式

 ```
-# Today's Briefing — [Date]
+# 今日简报 — [日期]

-## Schedule (N)
-| Time | Event | Location | Prep? |
+## 日程安排 (N)
+| 时间 | 事项 | 地点 | 准备? |
 |------|-------|----------|-------|

-## Email — Skipped (N) → auto-archived
-## Email — Action Required (N)
-### 1. Sender <email>
-**Subject**: ...
-**Summary**: ...
-**Draft reply**: ...
-→ [Send] [Edit] [Skip]
+## 邮件 — 已跳过 (N) → 自动归档
+## 邮件 — 需处理 (N)
+### 1. 发件人 <邮箱>
+**主题**: ...
+**摘要**: ...
+**回复草稿**: ...
+→ [发送] [编辑] [跳过]

-## Slack — Action Required (N)
-## LINE — Action Required (N)
+## Slack — 需处理 (N)
+## LINE — 需处理 (N)

-## Triage Queue
- Stale pending responses: N
- Overdue tasks: N
+## 待处理队列
+- 待回复超时事项: N
+- 逾期任务: N
 ```

 ## 关键设计原则
--- a/docs/zh-CN/agents/code-reviewer.md
+++ b/docs/zh-CN/agents/code-reviewer.md
@@ -178,13 +178,13 @@ const usersWithPosts = await db.query(`
 按严重程度组织发现的问题。对于每个问题：

 ```
-[CRITICAL] Hardcoded API key in source
-File: src/api/client.ts:42
-Issue: API key "sk-abc..." exposed in source code. This will be committed to git history.
-Fix: Move to environment variable and add to .gitignore/.env.example
+[严重] 源代码中存在硬编码的API密钥
+文件: src/api/client.ts:42
+问题: API密钥 "sk-abc..." 在源代码中暴露。这将提交到git历史记录中。
+修复: 移至环境变量并添加到 .gitignore/.env.example

-  const apiKey = "sk-abc123";           // BAD
-  const apiKey = process.env.API_KEY;   // GOOD
+  const apiKey = "sk-abc123";           // 错误做法
+  const apiKey = process.env.API_KEY;   // 正确做法
 ```

 ### 摘要格式
@@ -192,16 +192,16 @@ Fix: Move to environment variable and add to .gitignore/.env.example
 每次审查结束时使用：

 ```
-## Review Summary
+## 审查摘要

-| Severity | Count | Status |
+| 严重程度 | 数量 | 状态 |
 |----------|-------|--------|
-| CRITICAL | 0     | pass   |
-| HIGH     | 2     | warn   |
-| MEDIUM   | 3     | info   |
-| LOW      | 1     | note   |
+| CRITICAL | 0     | 通过   |
+| HIGH     | 2     | 警告   |
+| MEDIUM   | 3     | 信息   |
+| LOW      | 1     | 备注   |

-Verdict: WARNING — 2 HIGH issues should be resolved before merge.
+裁决：警告 — 2 个 HIGH 级别问题应在合并前解决。
 ```

 ## 批准标准
--- a/docs/zh-CN/agents/cpp-build-resolver.md
+++ b/docs/zh-CN/agents/cpp-build-resolver.md
@@ -31,11 +31,11 @@ cppcheck --enable=all src/ 2>/dev/null || echo "cppcheck not available"
 ## 解决工作流程

 ```text
-1. cmake --build build    -> Parse error message
-2. Read affected file     -> Understand context
-3. Apply minimal fix      -> Only what's needed
-4. cmake --build build    -> Verify fix
-5. ctest --test-dir build -> Ensure nothing broke
+1. cmake --build build    -> 解析错误信息
+2. 读取受影响的文件     -> 理解上下文
+3. 应用最小修复        -> 仅修复必需部分
+4. cmake --build build    -> 验证修复
+5. ctest --test-dir build -> 确保未破坏其他功能
 ```

 ## 常见修复模式
@@ -80,10 +80,10 @@ cmake --build build --clean-first
 ## 输出格式

 ```text
-[FIXED] src/handler/user.cpp:42
-Error: undefined reference to `UserService::create`
-Fix: Added missing method implementation in user_service.cpp
-Remaining errors: 3
+[已修复] src/handler/user.cpp:42
+错误：未定义的引用 `UserService::create`
+修复：在 user_service.cpp 中添加了缺失的方法实现
+剩余错误：3
 ```

 最终：`Build Status: SUCCESS/FAILED | Errors Fixed: N | Files Modified: list`
--- a/docs/zh-CN/agents/doc-updater.md
+++ b/docs/zh-CN/agents/doc-updater.md
@@ -44,12 +44,12 @@ npx jsdoc2md src/**/*.ts                # Extract JSDoc

 ```
 docs/CODEMAPS/
-├── INDEX.md          # Overview of all areas
-├── frontend.md       # Frontend structure
-├── backend.md        # Backend/API structure
-├── database.md       # Database schema
-├── integrations.md   # External services
-└── workers.md        # Background jobs
+├── INDEX.md          # 所有区域概览
+├── frontend.md       # 前端结构
+├── backend.md        # 后端/API 结构
+├── database.md       # 数据库模式
+├── integrations.md   # 外部服务
+└── workers.md        # 后台任务
 ```

 ### 4. 代码映射格式
--- a/docs/zh-CN/agents/flutter-reviewer.md
+++ b/docs/zh-CN/agents/flutter-reviewer.md
@@ -214,15 +214,15 @@ model: sonnet
 ## 输出格式

 ```
-[CRITICAL] Domain layer imports Flutter framework
-File: packages/domain/lib/src/usecases/user_usecase.dart:3
-Issue: `import 'package:flutter/material.dart'` — domain must be pure Dart.
-Fix: Move widget-dependent logic to presentation layer.
+[CRITICAL] 领域层导入了 Flutter 框架
+文件: packages/domain/lib/src/usecases/user_usecase.dart:3
+问题: `import 'package:flutter/material.dart'` — 领域层必须是纯 Dart。
+修复: 将依赖于 widget 的逻辑移至表示层。

-[HIGH] State consumer wraps entire screen
-File: lib/features/cart/presentation/cart_page.dart:42
-Issue: Consumer rebuilds entire page on every state change.
-Fix: Narrow scope to the subtree that depends on changed state, or use a selector.
+[HIGH] 状态消费者包裹了整个屏幕
+文件: lib/features/cart/presentation/cart_page.dart:42
+问题: 每次状态变化时，Consumer 都会重建整个页面。
+修复: 将范围缩小到依赖于已更改状态的子树，或使用选择器。
 ```

 ## 总结格式
@@ -230,16 +230,16 @@ Fix: Narrow scope to the subtree that depends on changed state, or use a selecto
 每次评审结束时附上：

 ```
-## Review Summary
+## 审查摘要

-| Severity | Count | Status |
-|----------|-------|--------|
-| CRITICAL | 0     | pass   |
-| HIGH     | 1     | block  |
-| MEDIUM   | 2     | info   |
-| LOW      | 0     | note   |
+| 严重性 | 数量 | 状态     |
+|--------|------|----------|
+| 严重   | 0    | 通过     |
+| 高     | 1    | 阻塞     |
+| 中     | 2    | 信息提示 |
+| 低     | 0    | 备注     |

-Verdict: BLOCK — HIGH issues must be fixed before merge.
+裁决：阻塞 — 必须修复高严重性问题后方可合并。
 ```

 ## 批准标准
--- a/docs/zh-CN/agents/go-build-resolver.md
+++ b/docs/zh-CN/agents/go-build-resolver.md
@@ -33,12 +33,12 @@ go mod tidy -v
 ## 解决工作流

 ```text
-1. go build ./...     -> Parse error message
-2. Read affected file -> Understand context
-3. Apply minimal fix  -> Only what's needed
-4. go build ./...     -> Verify fix
-5. go vet ./...       -> Check for warnings
-6. go test ./...      -> Ensure nothing broke
+1. go build ./...     -> 解析错误信息
+2. 读取受影响文件 -> 理解上下文
+3. 应用最小化修复 -> 仅修复必要部分
+4. go build ./...     -> 验证修复
+5. go vet ./...       -> 检查警告
+6. go test ./...      -> 确保未破坏原有功能
 ```

 ## 常见修复模式
@@ -84,10 +84,10 @@ go clean -modcache && go mod download  # Fix checksum issues
 ## 输出格式

 ```text
-[FIXED] internal/handler/user.go:42
-Error: undefined: UserService
-Fix: Added import "project/internal/service"
-Remaining errors: 3
+[已修复] internal/handler/user.go:42
+错误：未定义：UserService
+修复：添加了导入 "project/internal/service"
+剩余错误：3
 ```

 最终：`Build Status: SUCCESS/FAILED | Errors Fixed: N | Files Modified: list`
--- a/docs/zh-CN/agents/java-build-resolver.md
+++ b/docs/zh-CN/agents/java-build-resolver.md
@@ -36,11 +36,11 @@ model: sonnet
 ## 解决工作流

 ```text
-1. ./mvnw compile OR ./gradlew build  -> Parse error message
-2. Read affected file                 -> Understand context
-3. Apply minimal fix                  -> Only what's needed
-4. ./mvnw compile OR ./gradlew build  -> Verify fix
-5. ./mvnw test OR ./gradlew test      -> Ensure nothing broke
+1. ./mvnw compile 或 ./gradlew build  -> 解析错误信息
+2. 读取受影响的文件                 -> 理解上下文
+3. 应用最小修复                  -> 仅处理必需项
+4. ./mvnw compile 或 ./gradlew build  -> 验证修复
+5. ./mvnw test 或 ./gradlew test      -> 确保未破坏其他功能
 ```

 ## 常见修复模式
@@ -143,10 +143,10 @@ grep -A5 "annotationProcessorPaths\|annotationProcessor" pom.xml build.gradle
 ## 输出格式

 ```text
-[FIXED] src/main/java/com/example/service/PaymentService.java:87
-Error: cannot find symbol — symbol: class IdempotencyKey
-Fix: Added import com.example.domain.IdempotencyKey
-Remaining errors: 1
+[已修复] src/main/java/com/example/service/PaymentService.java:87
+错误: 找不到符号 — 符号: 类 IdempotencyKey
+修复: 添加了 import com.example.domain.IdempotencyKey
+剩余错误: 1
 ```

 最终：`Build Status: SUCCESS/FAILED | Errors Fixed: N | Files Modified: list`
--- a/docs/zh-CN/agents/kotlin-build-resolver.md
+++ b/docs/zh-CN/agents/kotlin-build-resolver.md
@@ -31,11 +31,11 @@ model: sonnet
 ## 解决工作流

 ```text
-1. ./gradlew build        -> Parse error message
-2. Read affected file     -> Understand context
-3. Apply minimal fix      -> Only what's needed
-4. ./gradlew build        -> Verify fix
-5. ./gradlew test         -> Ensure nothing broke
+1. ./gradlew build        -> 解析错误信息
+2. 读取受影响的文件      -> 理解上下文
+3. 应用最小修复          -> 仅解决必要问题
+4. ./gradlew build        -> 验证修复
+5. ./gradlew test         -> 确保无新增问题
 ```

 ## 常见修复模式
@@ -108,10 +108,10 @@ kotlin {
 ## 输出格式

 ```text
-[FIXED] src/main/kotlin/com/example/service/UserService.kt:42
-Error: Unresolved reference: UserRepository
-Fix: Added import com.example.repository.UserRepository
-Remaining errors: 2
+[已修复] src/main/kotlin/com/example/service/UserService.kt:42
+错误：未解析的引用：UserRepository
+修复：已添加导入 com.example.repository.UserRepository
+剩余错误：2
 ```

 最终：`Build Status: SUCCESS/FAILED | Errors Fixed: N | Files Modified: list`
--- a/docs/zh-CN/agents/kotlin-reviewer.md
+++ b/docs/zh-CN/agents/kotlin-reviewer.md
@@ -127,15 +127,15 @@ Button(onClick = onClick)
 ## 输出格式

 ```
-[CRITICAL] Domain module imports Android framework
-File: domain/src/main/kotlin/com/app/domain/UserUseCase.kt:3
-Issue: `import android.content.Context` — domain must be pure Kotlin with no framework dependencies.
-Fix: Move Context-dependent logic to data or platforms layer. Pass data via repository interface.
+[CRITICAL] Domain 模块导入了 Android 框架
+文件: domain/src/main/kotlin/com/app/domain/UserUseCase.kt:3
+问题: `import android.content.Context` — domain 层必须是纯 Kotlin，不能有框架依赖。
+修复: 将依赖 Context 的逻辑移到 data 层或 platforms 层。通过 repository 接口传递数据。

-[HIGH] StateFlow holding mutable list
-File: presentation/src/main/kotlin/com/app/ui/ListViewModel.kt:25
-Issue: `_state.value.items.add(newItem)` mutates the list inside StateFlow — Compose won't detect the change.
-Fix: Use `_state.update { it.copy(items = it.items + newItem) }`
+[HIGH] StateFlow 持有可变列表
+文件: presentation/src/main/kotlin/com/app/ui/ListViewModel.kt:25
+问题: `_state.value.items.add(newItem)` 在 StateFlow 内部修改了列表 — Compose 将无法检测到此更改。
+修复: 使用 `_state.update { it.copy(items = it.items + newItem) }`
 ```

 ## 摘要格式
@@ -143,16 +143,16 @@ Fix: Use `_state.update { it.copy(items = it.items + newItem) }`
 每次审查结束时附上：

 ```
-## Review Summary
+## 审查摘要

-| Severity | Count | Status |
+| 严重程度 | 数量 | 状态 |
 |----------|-------|--------|
-| CRITICAL | 0     | pass   |
-| HIGH     | 1     | block  |
-| MEDIUM   | 2     | info   |
-| LOW      | 0     | note   |
+| CRITICAL | 0     | 通过   |
+| HIGH     | 1     | 阻止   |
+| MEDIUM   | 2     | 信息   |
+| LOW      | 0     | 备注   |

-Verdict: BLOCK — HIGH issues must be fixed before merge.
+裁决：阻止 — 必须修复 HIGH 级别问题后方可合并。
 ```

 ## 批准标准
--- a/docs/zh-CN/agents/python-reviewer.md
+++ b/docs/zh-CN/agents/python-reviewer.md
@@ -79,10 +79,10 @@ pytest --cov=app --cov-report=term-missing # Test coverage
 ## 审查输出格式

 ```text
-[SEVERITY] Issue title
-File: path/to/file.py:42
-Issue: Description
-Fix: What to change
+[严重性] 问题标题
+文件：path/to/file.py:42
+问题：描述
+修复：修改内容
 ```

 ## 批准标准
--- a/docs/zh-CN/agents/pytorch-build-resolver.md
+++ b/docs/zh-CN/agents/pytorch-build-resolver.md
@@ -33,12 +33,12 @@ python -c "import torch; x = torch.randn(2,3).cuda(); print('CUDA tensor test: O
 ## 解决工作流

 ```text
-1. Read error traceback     -> Identify failing line and error type
-2. Read affected file       -> Understand model/training context
-3. Trace tensor shapes      -> Print shapes at key points
-4. Apply minimal fix        -> Only what's needed
-5. Run failing script       -> Verify fix
-6. Check gradients flow     -> Ensure backward pass works
+1. 阅读错误回溯     -> 定位失败行和错误类型
+2. 阅读受影响文件     -> 理解模型/训练上下文
+3. 追踪张量形状      -> 在关键点打印形状
+4. 应用最小修复      -> 仅修改必要部分
+5. 运行失败脚本      -> 验证修复
+6. 检查梯度流动      -> 确保反向传播正常工作
 ```

 ## 常见修复模式
@@ -109,10 +109,10 @@ print(f'Max allocated: {torch.cuda.max_memory_allocated()/1e9:.2f} GB')
 ## 输出格式

 ```text
-[FIXED] train.py:42
-Error: RuntimeError: mat1 and mat2 shapes cannot be multiplied (32x512 and 256x10)
-Fix: Changed nn.Linear(256, 10) to nn.Linear(512, 10) to match encoder output
-Remaining errors: 0
+[已修复] train.py:42
+错误：RuntimeError：无法相乘 mat1 和 mat2 的形状（32x512 和 256x10）
+修复：将 nn.Linear(256, 10) 更改为 nn.Linear(512, 10) 以匹配编码器输出
+剩余错误：0
 ```

 最终：`Status: SUCCESS/FAILED | Errors Fixed: N | Files Modified: list`
--- a/docs/zh-CN/agents/rust-build-resolver.md
+++ b/docs/zh-CN/agents/rust-build-resolver.md
@@ -32,12 +32,12 @@ if command -v cargo-audit >/dev/null; then cargo audit; else echo "cargo-audit n
 ## 解决工作流

 ```text
-1. cargo check          -> Parse error message and error code
-2. Read affected file   -> Understand ownership and lifetime context
-3. Apply minimal fix    -> Only what's needed
-4. cargo check          -> Verify fix
-5. cargo clippy         -> Check for warnings
-6. cargo test           -> Ensure nothing broke
+1. cargo check          -> 解析错误信息和错误代码
+2. 读取受影响的文件   -> 理解所有权和生命周期的上下文
+3. 应用最小修复      -> 仅做必要的修改
+4. cargo check          -> 验证修复
+5. cargo clippy         -> 检查警告
+6. cargo test           -> 确保没有破坏原有功能
 ```

 ## 常见修复模式
@@ -138,10 +138,10 @@ grep "rust-version" Cargo.toml
 ## 输出格式

 ```text
-[FIXED] src/handler/user.rs:42
-Error: E0502 — cannot borrow `map` as mutable because it is also borrowed as immutable
-Fix: Cloned value from immutable borrow before mutable insert
-Remaining errors: 3
+[已修复] src/handler/user.rs:42
+错误: E0502 — 无法以可变方式借用 `map`，因为它同时也被不可变借用
+修复: 在可变插入前从不可变借用克隆值
+剩余错误: 3
 ```

 最终：`Build Status: SUCCESS/FAILED | Errors Fixed: N | Files Modified: list`
--- a/docs/zh-CN/commands/checkpoint.md
+++ b/docs/zh-CN/commands/checkpoint.md
@@ -35,12 +35,12 @@ echo "$(date +%Y-%m-%d-%H:%M) | $CHECKPOINT_NAME | $(git rev-parse --short HEAD)
 3. 报告：

 ```
-CHECKPOINT COMPARISON: $NAME
+检查点对比：$NAME
 ============================
-Files changed: X
-Tests: +Y passed / -Z failed
-Coverage: +X% / -Y%
-Build: [PASS/FAIL]
+文件更改数：X
+测试结果：通过数 +Y / 失败数 -Z
+覆盖率：+X% / -Y%
+构建状态：[通过/失败]
 ```

 ## 列出检查点
--- a/docs/zh-CN/commands/claw.md
+++ b/docs/zh-CN/commands/claw.md
@@ -29,18 +29,18 @@ npm run claw
 ## REPL 命令

 ```text
-/help                          Show help
-/clear                         Clear current session history
-/history                       Print full conversation history
-/sessions                      List saved sessions
-/model [name]                  Show/set model
-/load <skill-name>             Hot-load a skill into context
-/branch <session-name>         Branch current session
-/search <query>                Search query across sessions
-/compact                       Compact old turns, keep recent context
-/export <md|json|txt> [path]   Export session
-/metrics                       Show session metrics
-exit                           Quit
+/help                          显示帮助信息
+/clear                         清除当前会话历史
+/history                       打印完整对话历史
+/sessions                      列出已保存的会话
+/model [name]                  显示/设置模型
+/load <skill-name>             热加载技能到上下文
+/branch <session-name>         分支当前会话
+/search <query>                跨会话搜索查询
+/compact                       压缩旧轮次，保留近期上下文
+/export <md|json|txt> [path]   导出会话
+/metrics                       显示会话指标
+exit                           退出
 ```

 ## 说明
--- a/docs/zh-CN/commands/cpp-build.md
+++ b/docs/zh-CN/commands/cpp-build.md
@@ -41,18 +41,16 @@ cppcheck --enable=all src/
 ## 示例会话

 ````text
-User: /cpp-build
+# C++ 构建问题解决

-Agent:
-# C++ Build Resolution
-
-## Initial Diagnostics
+## 初始诊断

 ```bash
 $ cmake --build build
 src/service/user.cpp:25:15: error: use of undeclared identifier 'UserRepository'
 src/handler/api.cpp:42:9: error: no matching function for call to 'process'
 src/handler/api.cpp:58:1: error: non-void function does not return a value
+
 ````

 发现的错误：3
@@ -133,45 +131,43 @@ All tests passed.
 构建状态：✅ 成功

 ```
+## 常见错误修复

-## Common Errors Fixed
-
-| Error | Typical Fix |
+| 错误 | 典型修复方法 |
 |-------|-------------|
-| `undeclared identifier` | Add `#include` or fix typo |
-| `no matching function` | Fix argument types or add overload |
-| `undefined reference` | Link library or add implementation |
-| `multiple definition` | Use `inline` or move to .cpp |
-| `incomplete type` | Replace forward decl with `#include` |
-| `no member named X` | Fix member name or include |
-| `cannot convert X to Y` | Add appropriate cast |
-| `CMake Error` | Fix CMakeLists.txt configuration |
+| `undeclared identifier` | 添加 `#include` 或修正拼写错误 |
+| `no matching function` | 修正参数类型或添加重载函数 |
+| `undefined reference` | 链接库或添加实现 |
+| `multiple definition` | 使用 `inline` 或移至 .cpp 文件 |
+| `incomplete type` | 将前向声明替换为 `#include` |
+| `no member named X` | 修正成员名称或包含头文件 |
+| `cannot convert X to Y` | 添加适当的类型转换 |
+| `CMake Error` | 修正 CMakeLists.txt 配置 |

-## Fix Strategy
+## 修复策略

-1. **Compilation errors first** - Code must compile
-2. **Linker errors second** - Resolve undefined references
-3. **Warnings third** - Fix with `-Wall -Wextra`
-4. **One fix at a time** - Verify each change
-5. **Minimal changes** - Don't refactor, just fix
+1. **优先处理编译错误** - 代码必须能够编译
+2. **其次处理链接器错误** - 解决未定义引用
+3. **第三处理警告** - 使用 `-Wall -Wextra` 进行修复
+4. **一次只修复一个问题** - 验证每个更改
+5. **最小化改动** - 仅修复问题，不重构代码

-## Stop Conditions
+## 停止条件

-The agent will stop and report if:
- Same error persists after 3 attempts
- Fix introduces more errors
- Requires architectural changes
- Missing external dependencies
+在以下情况下，代理将停止并报告：
+- 同一错误经过 3 次尝试后仍然存在
+- 修复引入了更多错误
+- 需要架构性更改
+- 缺少外部依赖项

-## Related Commands
+## 相关命令

- `/cpp-test` - Run tests after build succeeds
- `/cpp-review` - Review code quality
- `/verify` - Full verification loop
+- `/cpp-test` - 构建成功后运行测试
+- `/cpp-review` - 审查代码质量
+- `/verify` - 完整验证循环

-## Related
-
- Agent: `agents/cpp-build-resolver.md`
- Skill: `skills/cpp-coding-standards/`
+## 相关

+- 代理: `agents/cpp-build-resolver.md`
+- 技能: `skills/cpp-coding-standards/`
 ```
--- a/docs/zh-CN/commands/cpp-review.md
+++ b/docs/zh-CN/commands/cpp-review.md
@@ -68,26 +68,23 @@ cmake --build build -- -Wall -Wextra -Wpedantic
 ## 使用示例

 ````text
-User: /cpp-review
+# C++ 代码审查报告

-Agent:
-# C++ Code Review Report
+## 已审查文件
+- src/handler/user.cpp (已修改)
+- src/service/auth.cpp (已修改)

-## Files Reviewed
- src/handler/user.cpp (modified)
- src/service/auth.cpp (modified)
+## 静态分析结果
+✓ clang-tidy: 2 个警告
+✓ cppcheck: 无问题

-## Static Analysis Results
-✓ clang-tidy: 2 warnings
-✓ cppcheck: No issues
+## 发现的问题

-## Issues Found
-
-[CRITICAL] Memory Leak
-File: src/service/auth.cpp:45
-Issue: Raw `new` without matching `delete`
+[严重] 内存泄漏
+文件: src/service/auth.cpp:45
+问题: 使用了原始的 `new` 而没有匹配的 `delete`
 ```cpp
-auto* session = new Session(userId);  // Memory leak!
+auto* session = new Session(userId);  // 内存泄漏！
 cache[userId] = session;
 ````

@@ -121,25 +118,23 @@ void processUser(const User& user) {
 建议：❌ 在严重问题修复前阻止合并

 ```
+## 批准标准

-## Approval Criteria
-
-| Status | Condition |
+| 状态 | 条件 |
 |--------|-----------|
-| ✅ Approve | No CRITICAL or HIGH issues |
-| ⚠️ Warning | Only MEDIUM issues (merge with caution) |
-| ❌ Block | CRITICAL or HIGH issues found |
+| ✅ 批准 | 没有 CRITICAL 或 HIGH 级别的问题 |
+| ⚠️ 警告 | 仅有 MEDIUM 级别的问题（谨慎合并） |
+| ❌ 阻止 | 发现 CRITICAL 或 HIGH 级别的问题 |

-## Integration with Other Commands
+## 与其他命令的集成

- Use `/cpp-test` first to ensure tests pass
- Use `/cpp-build` if build errors occur
- Use `/cpp-review` before committing
- Use `/code-review` for non-C++ specific concerns
+- 首先使用 `/cpp-test` 确保测试通过
+- 如果出现构建错误，请使用 `/cpp-build`
+- 在提交前使用 `/cpp-review`
+- 对于非 C++ 特定的问题，请使用 `/code-review`

-## Related
-
- Agent: `agents/cpp-reviewer.md`
- Skills: `skills/cpp-coding-standards/`, `skills/cpp-testing/`
+## 相关

+- 代理：`agents/cpp-reviewer.md`
+- 技能：`skills/cpp-coding-standards/`, `skills/cpp-testing/`
 ```
--- a/docs/zh-CN/commands/cpp-test.md
+++ b/docs/zh-CN/commands/cpp-test.md
@@ -28,10 +28,10 @@ description: 为 C++ 强制执行 TDD 工作流程。先编写 GoogleTest 测试
 ## TDD 循环

 ```
-RED     → Write failing GoogleTest test
-GREEN   → Implement minimal code to pass
-REFACTOR → Improve code, tests stay green
-REPEAT  → Next test case
+RED     → 编写失败的 GoogleTest 测试
+GREEN   → 实现最小化代码以通过测试
+REFACTOR → 改进代码，测试保持通过
+REPEAT  → 下一个测试用例
 ```

 ## 示例会话
--- a/docs/zh-CN/commands/devfleet.md
+++ b/docs/zh-CN/commands/devfleet.md
@@ -11,14 +11,14 @@ description: 通过Claude DevFleet协调并行Claude Code代理——从自然
 ## 流程

 ```
-User describes project
-  → plan_project(prompt) → mission DAG with dependencies
-  → Show plan, get approval
-  → dispatch_mission(M1) → Agent spawns in worktree
-  → M1 completes → auto-merge → M2 auto-dispatches (depends_on M1)
-  → M2 completes → auto-merge
-  → get_report(M2) → files_changed, what_done, errors, next_steps
-  → Report summary to user
+用户描述项目
+  → plan_project(prompt) → 任务DAG与依赖关系
+  → 展示计划，获取批准
+  → dispatch_mission(M1) → 代理在工作区中生成
+  → M1完成 → 自动合并 → M2自动调度（依赖于M1）
+  → M2完成 → 自动合并
+  → get_report(M2) → 文件变更、完成内容、错误、后续步骤
+  → 向用户报告总结
 ```

 ## 工作流
@@ -26,7 +26,7 @@ User describes project
 1. **根据用户描述规划项目**：

 ```
-mcp__devfleet__plan_project(prompt="<user's description>")
+mcp__devfleet__plan_project(prompt="<用户描述>")
 ```

 这将返回一个包含链式任务的项目。向用户展示：
--- a/docs/zh-CN/commands/e2e.md
+++ b/docs/zh-CN/commands/e2e.md
@@ -38,24 +38,24 @@ e2e-runner 代理将：
 ## 使用示例

 ````
-User: /e2e Test the market search and view flow
+用户：/e2e 测试市场搜索和查看流程

-Agent (e2e-runner):
-# E2E Test Generation: Market Search and View Flow
+代理（e2e-runner）：
+# E2E 测试生成：市场搜索和查看流程

-## Test Scenario Identified
+## 已识别测试场景

-**User Journey:** Market Search → View Results → Click Market → View Details
+**用户旅程：** 市场搜索 → 查看结果 → 点击市场 → 查看详情

-**Test Coverage:**
-1. Navigate to markets page
-2. Perform semantic search
-3. Verify search results
-4. Click on first result
-5. Verify market details page loads
-6. Verify chart renders
+**测试覆盖范围：**
+1. 导航至市场页面
+2. 执行语义搜索
+3. 验证搜索结果
+4. 点击第一个结果
+5. 验证市场详情页面加载
+6. 验证图表渲染

-## Generated Test Code
+## 生成的测试代码

 ```typescript
 // tests/e2e/markets/search-and-view.spec.ts
@@ -155,6 +155,7 @@ test.describe('Market Search and View Flow', () => {
    expect(finalCount).toBe(initialCount)
  })
 })
+
 ````

 ## 运行测试
@@ -181,55 +182,55 @@ Artifacts generated:

 ```
 ╔══════════════════════════════════════════════════════════════╗
-║                    E2E Test Results                          ║
+║                    E2E 测试结果                          ║
 ╠══════════════════════════════════════════════════════════════╣
-║ Status:     ✅ ALL TESTS PASSED                              ║
-║ Total:      3 tests                                          ║
-║ Passed:     3 (100%)                                         ║
-║ Failed:     0                                                ║
-║ Flaky:      0                                                ║
-║ Duration:   9.1s                                             ║
+║ 状态：     ✅ 所有测试通过                              ║
+║ 总计：      3 项测试                                          ║
+║ 通过：     3 (100%)                                         ║
+║ 失败：     0                                                ║
+║ 不稳定：    0                                                ║
+║ 耗时：   9.1s                                             ║
 ╚══════════════════════════════════════════════════════════════╝

-Artifacts:
-📸 Screenshots: 2 files
-📹 Videos: 0 files (only on failure)
-🔍 Traces: 0 files (only on failure)
-📊 HTML Report: playwright-report/index.html
+产物：
+📸 截图： 2 个文件
+📹 视频： 0 个文件（仅在失败时生成）
+🔍 追踪文件： 0 个文件（仅在失败时生成）
+📊 HTML 报告： playwright-report/index.html

-View report: npx playwright show-report
+查看报告： npx playwright show-report
 ```

 ✅ E2E 测试套件已准备好进行 CI/CD 集成！

 ````
+## 测试产物

-## Test Artifacts
+当测试运行时，会捕获以下产物：

-When tests run, the following artifacts are captured:
+**所有测试：**
+- 包含时间线和结果的 HTML 报告
+- 用于 CI 集成的 JUnit XML 文件

-**On All Tests:**
- HTML Report with timeline and results
- JUnit XML for CI integration
+**仅在失败时：**
+- 失败状态的截图
+- 测试的视频录制
+- 用于调试的追踪文件（逐步重放）
+- 网络日志
+- 控制台日志

-**On Failure Only:**
- Screenshot of the failing state
- Video recording of the test
- Trace file for debugging (step-by-step replay)
- Network logs
- Console logs
-
-## Viewing Artifacts
+## 查看产物

 ```bash
-# View HTML report in browser
+# 在浏览器中查看 HTML 报告
 npx playwright show-report

-# View specific trace file
+# 查看特定的追踪文件
 npx playwright show-trace artifacts/trace-abc123.zip

-# Screenshots are saved in artifacts/ directory
+# 截图保存在 artifacts/ 目录中
 open artifacts/search-results.png
+
 ````

 ## 不稳定测试检测
@@ -239,18 +240,18 @@ open artifacts/search-results.png
 ```
 ⚠️  FLAKY TEST DETECTED: tests/e2e/markets/trade.spec.ts

-Test passed 7/10 runs (70% pass rate)
+测试通过了 7/10 次运行 (70% 通过率)

-Common failure:
-"Timeout waiting for element '[data-testid="confirm-btn"]'"
+常见失败原因:
+"等待元素 '[data-testid="confirm-btn"]' 超时"

-Recommended fixes:
-1. Add explicit wait: await page.waitForSelector('[data-testid="confirm-btn"]')
-2. Increase timeout: { timeout: 10000 }
-3. Check for race conditions in component
-4. Verify element is not hidden by animation
+推荐修复方法:
+1. 添加显式等待: await page.waitForSelector('[data-testid="confirm-btn"]')
+2. 增加超时时间: { timeout: 10000 }
+3. 检查组件中的竞争条件
+4. 确认元素未被动画遮挡

-Quarantine recommendation: Mark as test.fixme() until fixed
+隔离建议: 在修复前标记为 test.fixme()
 ```

 ## 浏览器配置
--- a/docs/zh-CN/commands/eval.md
+++ b/docs/zh-CN/commands/eval.md
@@ -54,9 +54,9 @@
 ```
 EVAL CHECK: feature-name
 ========================
-Capability: X/Y passing
-Regression: X/Y passing
-Status: IN PROGRESS / READY
+功能：X/Y 通过
+回归测试：X/Y 通过
+状态：进行中 / 就绪
 ```

 ## 报告评估
@@ -68,31 +68,31 @@ Status: IN PROGRESS / READY
 ```
 EVAL REPORT: feature-name
 =========================
-Generated: $(date)
+生成时间: $(date)

-CAPABILITY EVALS
+能力评估
 ----------------
-[eval-1]: PASS (pass@1)
-[eval-2]: PASS (pass@2) - required retry
-[eval-3]: FAIL - see notes
+[eval-1]: 通过 (pass@1)
+[eval-2]: 通过 (pass@2) - 需要重试
+[eval-3]: 失败 - 参见备注

-REGRESSION EVALS
+回归测试
 ----------------
-[test-1]: PASS
-[test-2]: PASS
-[test-3]: PASS
+[test-1]: 通过
+[test-2]: 通过
+[test-3]: 通过

-METRICS
+指标
 -------
-Capability pass@1: 67%
-Capability pass@3: 100%
-Regression pass^3: 100%
+能力 pass@1: 67%
+能力 pass@3: 100%
+回归 pass^3: 100%

-NOTES
+备注
 -----
-[Any issues, edge cases, or observations]
+[任何问题、边界情况或观察结果]

-RECOMMENDATION
+建议
 --------------
 [SHIP / NEEDS WORK / BLOCKED]
 ```
@@ -104,11 +104,11 @@ RECOMMENDATION
 显示所有评估定义：

 ```
-EVAL DEFINITIONS
+功能模块定义
 ================
-feature-auth      [3/5 passing] IN PROGRESS
-feature-search    [5/5 passing] READY
-feature-export    [0/4 passing] NOT STARTED
+feature-auth      [3/5 通过] 进行中
+feature-search    [5/5 通过] 就绪
+feature-export    [0/4 通过] 未开始
 ```

 ## 参数
--- a/docs/zh-CN/commands/evolve.md
+++ b/docs/zh-CN/commands/evolve.md
@@ -29,8 +29,8 @@ python3 ~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py evolve [
 ## 使用方法

 ```
-/evolve                    # Analyze all instincts and suggest evolutions
-/evolve --generate         # Also generate files under evolved/{skills,commands,agents}
+/evolve                    # 分析所有本能并建议进化方向
+/evolve --generate         # 同时在 evolved/{skills,commands,agents} 目录下生成文件
 ```

 ## 演化规则
@@ -102,29 +102,29 @@ python3 ~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py evolve [

 ```
 ============================================================
-  EVOLVE ANALYSIS - 12 instincts
-  Project: my-app (a1b2c3d4e5f6)
-  Project-scoped: 8 | Global: 4
+  演进分析 - 12 种直觉
+  项目：my-app (a1b2c3d4e5f6)
+  项目范围：8 | 全局：4
 ============================================================

-High confidence instincts (>=80%): 5
+高置信度直觉 (>=80%)：5

-## SKILL CANDIDATES
-1. Cluster: "adding tests"
-   Instincts: 3
-   Avg confidence: 82%
-   Domains: testing
-   Scopes: project
+## 技能候选
+1. 聚类："adding tests"
+   直觉：3
+   平均置信度：82%
+   领域：testing
+   范围：project

-## COMMAND CANDIDATES (2)
+## 命令候选 (2)
  /adding-tests
-    From: test-first-workflow [project]
-    Confidence: 84%
+    来源：test-first-workflow [project]
+    置信度：84%

-## AGENT CANDIDATES (1)
+## 代理候选 (1)
  adding-tests-agent
-    Covers 3 instincts
-    Avg confidence: 82%
+    涵盖 3 种直觉
+    平均置信度：82%
 ```

 ## 标志
--- a/docs/zh-CN/commands/go-build.md
+++ b/docs/zh-CN/commands/go-build.md
@@ -45,18 +45,16 @@ go mod tidy -v
 ## 示例会话

 ````text
-User: /go-build
+# Go Build 解析

-Agent:
-# Go Build Resolution
-
-## Initial Diagnostics
+## 初始诊断

 ```bash
 $ go build ./...
 internal/service/user.go:25:15: undefined: UserRepository
 internal/handler/api.go:42:9: cannot use x (type string) as type int
 internal/handler/api.go:58:2: missing return at end of function
+
 ````

 发现错误：3
@@ -144,44 +142,42 @@ ok      project/internal/handler   0.023s
 构建状态：✅ 成功

 ```
+## 常见错误修复

-## Common Errors Fixed
-
-| Error | Typical Fix |
+| 错误 | 典型修复 |
 |-------|-------------|
-| `undefined: X` | Add import or fix typo |
-| `cannot use X as Y` | Type conversion or fix assignment |
-| `missing return` | Add return statement |
-| `X does not implement Y` | Add missing method |
-| `import cycle` | Restructure packages |
-| `declared but not used` | Remove or use variable |
-| `cannot find package` | `go get` or `go mod tidy` |
+| `undefined: X` | 添加导入或修正拼写错误 |
+| `cannot use X as Y` | 类型转换或修正赋值 |
+| `missing return` | 添加返回语句 |
+| `X does not implement Y` | 添加缺失的方法 |
+| `import cycle` | 重构包结构 |
+| `declared but not used` | 移除或使用变量 |
+| `cannot find package` | `go get` 或 `go mod tidy` |

-## Fix Strategy
+## 修复策略

-1. **Build errors first** - Code must compile
-2. **Vet warnings second** - Fix suspicious constructs
-3. **Lint warnings third** - Style and best practices
-4. **One fix at a time** - Verify each change
-5. **Minimal changes** - Don't refactor, just fix
+1. **优先处理构建错误** - 代码必须能够编译
+2. **其次处理 vet 警告** - 修复可疑结构
+3. **再次处理 lint 警告** - 风格和最佳实践
+4. **一次修复一个问题** - 验证每个更改
+5. **最小化更改** - 不要重构，只修复

-## Stop Conditions
+## 停止条件

-The agent will stop and report if:
- Same error persists after 3 attempts
- Fix introduces more errors
- Requires architectural changes
- Missing external dependencies
+在以下情况下，代理将停止并报告：
+- 相同错误经过 3 次尝试后仍然存在
+- 修复引入了更多错误
+- 需要架构性更改
+- 缺少外部依赖

-## Related Commands
+## 相关命令

- `/go-test` - Run tests after build succeeds
- `/go-review` - Review code quality
- `/verify` - Full verification loop
+- `/go-test` - 构建成功后运行测试
+- `/go-review` - 审查代码质量
+- `/verify` - 完整验证循环

-## Related
-
- Agent: `agents/go-build-resolver.md`
- Skill: `skills/golang-patterns/`
+## 相关

+- 代理: `agents/go-build-resolver.md`
+- 技能: `skills/golang-patterns/`
 ```
--- a/docs/zh-CN/commands/go-review.md
+++ b/docs/zh-CN/commands/go-review.md
@@ -73,29 +73,26 @@ govulncheck ./...
 ## 使用示例

 ````text
-User: /go-review
+# Go 代码审查报告

-Agent:
-# Go Code Review Report
+## 已审查文件
+- internal/handler/user.go（已修改）
+- internal/service/auth.go（已修改）

-## Files Reviewed
- internal/handler/user.go (modified)
- internal/service/auth.go (modified)
+## 静态分析结果
+✓ go vet: 无问题
+✓ staticcheck: 无问题

-## Static Analysis Results
-✓ go vet: No issues
-✓ staticcheck: No issues
+## 发现的问题

-## Issues Found
-
-[CRITICAL] Race Condition
-File: internal/service/auth.go:45
-Issue: Shared map accessed without synchronization
+[严重] 竞态条件
+文件: internal/service/auth.go:45
+问题: 共享映射访问未同步
 ```go
-var cache = map[string]*Session{}  // Concurrent access!
+var cache = map[string]*Session{}  // 并发访问！

 func GetSession(id string) *Session {
-    return cache[id]  // Race condition
+    return cache[id]  // 竞态条件
 }
 ````

@@ -137,25 +134,23 @@ return fmt.Errorf("get user %s: %w", userID, err)
 建议：❌ 在严重问题修复前阻止合并

 ```
+## 批准标准

-## Approval Criteria
-
-| Status | Condition |
+| 状态 | 条件 |
 |--------|-----------|
-| ✅ Approve | No CRITICAL or HIGH issues |
-| ⚠️ Warning | Only MEDIUM issues (merge with caution) |
-| ❌ Block | CRITICAL or HIGH issues found |
+| ✅ 批准 | 无 CRITICAL 或 HIGH 级别问题 |
+| ⚠️ 警告 | 仅有 MEDIUM 级别问题 (谨慎合并) |
+| ❌ 阻止 | 发现 CRITICAL 或 HIGH 级别问题 |

-## Integration with Other Commands
+## 与其他命令的集成

- Use `/go-test` first to ensure tests pass
- Use `/go-build` if build errors occur
- Use `/go-review` before committing
- Use `/code-review` for non-Go specific concerns
+- 首先使用 `/go-test` 确保测试通过
+- 如果出现构建错误，请使用 `/go-build`
+- 提交前使用 `/go-review`
+- 对于非 Go 语言特定问题，请使用 `/code-review`

-## Related
+## 相关

 - Agent: `agents/go-reviewer.md`
 - Skills: `skills/golang-patterns/`, `skills/golang-testing/`
-
 ```
--- a/docs/zh-CN/commands/go-test.md
+++ b/docs/zh-CN/commands/go-test.md
@@ -28,34 +28,34 @@ description: 为Go强制执行TDD工作流程。首先编写表驱动测试，
 ## TDD 循环

 ```
-RED     → Write failing table-driven test
-GREEN   → Implement minimal code to pass
-REFACTOR → Improve code, tests stay green
-REPEAT  → Next test case
+RED     → 编写失败的表格驱动测试
+GREEN   → 实现最小化代码以通过测试
+REFACTOR → 改进代码，保持测试通过
+REPEAT  → 下一个测试用例
 ```

 ## 示例会话

 ````
-User: /go-test I need a function to validate email addresses
+用户: /go-test 我需要一个验证电子邮箱地址的函数

-Agent:
-# TDD Session: Email Validator
+代理:
+# TDD 会话: 电子邮件验证器

-## Step 1: Define Interface
+## 步骤 1: 定义接口

 ```go
 // validator/email.go
 package validator

-// ValidateEmail checks if the given string is a valid email address.
-// Returns nil if valid, error describing the issue otherwise.
+// ValidateEmail 检查给定的字符串是否为有效的电子邮件地址。
+// 如果有效则返回 nil，否则返回描述问题的错误。
 func ValidateEmail(email string) error {
    panic("not implemented")
 }
 ```

-## Step 2: Write Table-Driven Tests (RED)
+## 步骤 2: 编写表驱动测试 (RED)

 ```go
 // validator/email_test.go
@@ -71,13 +71,13 @@ func TestValidateEmail(t *testing.T) {
        email   string
        wantErr bool
    }{
-        // Valid emails
+        // 有效邮箱
        {"simple email", "user@example.com", false},
        {"with subdomain", "user@mail.example.com", false},
        {"with plus", "user+tag@example.com", false},
        {"with dots", "first.last@example.com", false},

-        // Invalid emails
+        // 无效邮箱
        {"empty string", "", true},
        {"no at sign", "userexample.com", true},
        {"no domain", "user@", true},
@@ -101,7 +101,7 @@ func TestValidateEmail(t *testing.T) {
 }
 ```

-## Step 3: Run Tests - Verify FAIL
+## 步骤 3: 运行测试 - 验证失败

 ```bash
 $ go test ./validator/...
@@ -113,9 +113,9 @@ $ go test ./validator/...
 FAIL
 ```

-✓ Tests fail as expected (panic).
+✓ 测试按预期失败 (panic)。

-## Step 4: Implement Minimal Code (GREEN)
+## 步骤 4: 实现最小化代码 (GREEN)

 ```go
 // validator/email.go
@@ -144,7 +144,7 @@ func ValidateEmail(email string) error {
 }
 ```

-## Step 5: Run Tests - Verify PASS
+## 步骤 5: 运行测试 - 验证通过

 ```bash
 $ go test ./validator/...
@@ -153,9 +153,9 @@ PASS
 ok      project/validator    0.003s
 ```

-✓ All tests passing!
+✓ 所有测试通过！

-## Step 6: Check Coverage
+## 步骤 6: 检查覆盖率

 ```bash
 $ go test -cover ./validator/...
@@ -165,9 +165,9 @@ coverage: 100.0% of statements
 ok      project/validator    0.003s
 ```

-✓ Coverage: 100%
+✓ 覆盖率: 100%

-## TDD Complete!
+## TDD 完成！
 ````

 ## 测试模式
--- a/docs/zh-CN/commands/harness-audit.md
+++ b/docs/zh-CN/commands/harness-audit.md
@@ -53,15 +53,15 @@ node scripts/harness-audit.js <scope> --format <text|json>
 ## 结果示例

 ```text
-Harness Audit (repo): 66/70
- Tool Coverage: 10/10 (10/10 pts)
- Context Efficiency: 9/10 (9/10 pts)
- Quality Gates: 10/10 (10/10 pts)
+Harness 审计 (代码库): 66/70
+- 工具覆盖率: 10/10 (10/10 分)
+- 上下文效率: 9/10 (9/10 分)
+- 质量门禁: 10/10 (10/10 分)

-Top 3 Actions:
-1) [Security Guardrails] Add prompt/tool preflight security guards in hooks/hooks.json. (hooks/hooks.json)
-2) [Tool Coverage] Sync commands/harness-audit.md and .opencode/commands/harness-audit.md. (.opencode/commands/harness-audit.md)
-3) [Eval Coverage] Increase automated test coverage across scripts/hooks/lib. (tests/)
+首要三项行动:
+1) [安全防护] 在 hooks/hooks.json 中添加提示/工具预检安全防护。 (hooks/hooks.json)
+2) [工具覆盖率] 同步 commands/harness-audit.md 和 .opencode/commands/harness-audit.md。 (.opencode/commands/harness-audit.md)
+3) [评估覆盖率] 提升 scripts/hooks/lib 目录下的自动化测试覆盖率。 (tests/)
 ```

 ## 参数
--- a/docs/zh-CN/commands/instinct-export.md
+++ b/docs/zh-CN/commands/instinct-export.md
@@ -15,9 +15,9 @@ command: /instinct-export
 ## 用法

 ```
-/instinct-export                           # Export all personal instincts
-/instinct-export --domain testing          # Export only testing instincts
-/instinct-export --min-confidence 0.7      # Only export high-confidence instincts
+/instinct-export                           # 导出所有个人本能
+/instinct-export --domain testing          # 仅导出测试相关本能
+/instinct-export --min-confidence 0.7      # 仅导出高置信度本能
 /instinct-export --output team-instincts.yaml
 /instinct-export --scope project --output project-instincts.yaml
 ```
--- a/docs/zh-CN/commands/instinct-import.md
+++ b/docs/zh-CN/commands/instinct-import.md
@@ -44,33 +44,33 @@ python3 ~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py import <
 ## 导入过程

 ```
-📥 Importing instincts from: team-instincts.yaml
+📥 从 team-instincts.yaml 导入本能
 ================================================

-Found 12 instincts to import.
+发现 12 个待导入的本能。

-Analyzing conflicts...
+正在分析冲突...

-## New Instincts (8)
-These will be added:
-  ✓ use-zod-validation (confidence: 0.7)
-  ✓ prefer-named-exports (confidence: 0.65)
-  ✓ test-async-functions (confidence: 0.8)
+## 新本能 (8)
+这些将被添加：
+  ✓ use-zod-validation (置信度: 0.7)
+  ✓ prefer-named-exports (置信度: 0.65)
+  ✓ test-async-functions (置信度: 0.8)
  ...

-## Duplicate Instincts (3)
-Already have similar instincts:
+## 重复本能 (3)
+已存在类似本能：
  ⚠️ prefer-functional-style
-     Local: 0.8 confidence, 12 observations
-     Import: 0.7 confidence
-     → Keep local (higher confidence)
+     本地: 0.8 置信度, 12 次观察
+     导入: 0.7 置信度
+     → 保留本地 (置信度更高)

  ⚠️ test-first-workflow
-     Local: 0.75 confidence
-     Import: 0.9 confidence
-     → Update to import (higher confidence)
+     本地: 0.75 置信度
+     导入: 0.9 置信度
+     → 更新为导入 (置信度更高)

-Import 8 new, update 1?
+导入 8 个新的，更新 1 个？
 ```

 ## 合并行为
@@ -105,13 +105,13 @@ project_name: "my-project"
 导入后：

 ```
-✅ Import complete!
+✅ 导入完成！

-Added: 8 instincts
-Updated: 1 instinct
-Skipped: 3 instincts (equal/higher confidence already exists)
+新增：8 项本能  
+更新：1 项本能  
+跳过：3 项本能（已存在同等或更高置信度的版本）

-New instincts saved to: ~/.claude/homunculus/instincts/inherited/
+新本能已保存至：~/.claude/homunculus/instincts/inherited/

-Run /instinct-status to see all instincts.
+运行 /instinct-status 以查看所有本能。
 ```
--- a/docs/zh-CN/commands/instinct-status.md
+++ b/docs/zh-CN/commands/instinct-status.md
@@ -40,20 +40,20 @@ python3 ~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py status

 ```
 ============================================================
-  INSTINCT STATUS - 12 total
+  INSTINCT 状态 - 总计 12
 ============================================================

-  Project: my-app (a1b2c3d4e5f6)
-  Project instincts: 8
-  Global instincts:  4
+  项目: my-app (a1b2c3d4e5f6)
+  项目 instincts: 8
+  全局 instincts:  4

-## PROJECT-SCOPED (my-app)
-  ### WORKFLOW (3)
+## 项目范围内 (my-app)
+  ### 工作流 (3)
    ███████░░░  70%  grep-before-edit [project]
-              trigger: when modifying code
+              触发条件: 当修改代码时

-## GLOBAL (apply to all projects)
-  ### SECURITY (2)
+## 全局 (适用于所有项目)
+  ### 安全 (2)
    █████████░  85%  validate-user-input [global]
-              trigger: when handling user input
+              触发条件: 当处理用户输入时
 ```
--- a/docs/zh-CN/commands/kotlin-test.md
+++ b/docs/zh-CN/commands/kotlin-test.md
@@ -28,21 +28,21 @@ description: 为Kotlin强制执行TDD工作流程。首先编写Kotest测试，
 ## TDD 循环

 ```
-RED     -> Write failing Kotest test
-GREEN   -> Implement minimal code to pass
-REFACTOR -> Improve code, tests stay green
-REPEAT  -> Next test case
+RED     -> 编写失败的 Kotest 测试
+GREEN   -> 实现最小化代码以通过测试
+REFACTOR -> 改进代码，测试保持通过状态
+REPEAT  -> 进入下一个测试用例
 ```

 ## 示例会话

 ````text
-User: /kotlin-test I need a function to validate user registration requests
+用户：/kotlin-test 我需要一个验证用户注册请求的函数

-Agent:
-# TDD Session: Registration Validator
+代理：
+# TDD 会话：注册验证器

-## Step 1: Define Interface
+## 第一步：定义接口

 ```kotlin
 // validator/RegistrationValidator.kt
@@ -64,7 +64,7 @@ fun validateRegistration(request: RegistrationRequest): ValidationResult {
 }
 ```

-## Step 2: Write Kotest Tests (RED)
+## 第二步：编写 Kotest 测试（RED）

 ```kotlin
 // validator/RegistrationValidatorTest.kt
@@ -141,7 +141,7 @@ class RegistrationValidatorTest : FunSpec({
 })
 ```

-## Step 3: Run Tests - Verify FAIL
+## 第三步：运行测试 - 验证失败

 ```bash
 $ ./gradlew test
@@ -152,9 +152,9 @@ RegistrationValidatorTest > valid registration returns Valid FAILED
 FAILED (5 tests, 0 passed, 5 failed)
 ```

-✓ Tests fail as expected (NotImplementedError).
+✓ 测试按预期失败（NotImplementedError）。

-## Step 4: Implement Minimal Code (GREEN)
+## 第四步：实现最小代码（GREEN）

 ```kotlin
 // validator/RegistrationValidator.kt
@@ -175,7 +175,7 @@ fun validateRegistration(request: RegistrationRequest): ValidationResult {
 }
 ```

-## Step 5: Run Tests - Verify PASS
+## 第五步：运行测试 - 验证通过

 ```bash
 $ ./gradlew test
@@ -189,9 +189,9 @@ RegistrationValidatorTest > multiple errors returns all errors PASSED
 PASSED (5 tests, 5 passed, 0 failed)
 ```

-✓ All tests passing!
+✓ 所有测试通过！

-## Step 6: Check Coverage
+## 第六步：检查覆盖率

 ```bash
 $ ./gradlew koverHtmlReport
@@ -199,9 +199,9 @@ $ ./gradlew koverHtmlReport
 Coverage: 100.0% of statements
 ```

-✓ Coverage: 100%
+✓ 覆盖率：100%

-## TDD Complete!
+## TDD 完成！
 ````

 ## 测试模式
--- a/docs/zh-CN/commands/learn-eval.md
+++ b/docs/zh-CN/commands/learn-eval.md
@@ -93,15 +93,15 @@ origin: auto-extracted
 ## 步骤 5 的输出格式

 ```
-### Checklist
- [x] skills/ grep: no overlap (or: overlap found → details)
- [x] MEMORY.md: no overlap (or: overlap found → details)
- [x] Existing skill append: new file appropriate (or: should append to [X])
- [x] Reusability: confirmed (or: one-off → Drop)
+### 检查清单
+- [x] skills/ grep: 无重叠 (或: 发现重叠 → 详情)
+- [x] MEMORY.md: 无重叠 (或: 发现重叠 → 详情)
+- [x] 现有技能追加: 新文件合适 (或: 应追加到 [X])
+- [x] 可复用性: 已确认 (或: 一次性 → 丢弃)

-### Verdict: Save / Improve then Save / Absorb into [X] / Drop
+### 裁决: 保存 / 改进后保存 / 吸收到 [X] / 丢弃

-**Rationale:** (1-2 sentences explaining the verdict)
+**理由:** (用 1-2 句话解释裁决)
 ```

 ## 设计原理
--- a/docs/zh-CN/commands/multi-backend.md
+++ b/docs/zh-CN/commands/multi-backend.md
@@ -31,34 +31,34 @@
 **调用语法**：

 ```
-# New session call
+# 新会话调用
 Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend codex - \"$PWD\" <<'EOF'
-ROLE_FILE: <role prompt path>
+ROLE_FILE: <角色提示路径>
 <TASK>
-Requirement: <enhanced requirement (or $ARGUMENTS if not enhanced)>
-Context: <project context and analysis from previous phases>
+需求: <增强后的需求（若未增强则为 $ARGUMENTS）>
+上下文: <来自先前阶段的项目上下文与分析>
 </TASK>
-OUTPUT: Expected output format
+OUTPUT: 期望的输出格式
 EOF",
  run_in_background: false,
  timeout: 3600000,
-  description: "Brief description"
+  description: "简要描述"
 })

-# Resume session call
+# 恢复会话调用
 Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend codex resume <SESSION_ID> - \"$PWD\" <<'EOF'
-ROLE_FILE: <role prompt path>
+ROLE_FILE: <角色提示路径>
 <TASK>
-Requirement: <enhanced requirement (or $ARGUMENTS if not enhanced)>
-Context: <project context and analysis from previous phases>
+需求: <增强后的需求（若未增强则为 $ARGUMENTS）>
+上下文: <来自先前阶段的项目上下文与分析>
 </TASK>
-OUTPUT: Expected output format
+OUTPUT: 期望的输出格式
 EOF",
  run_in_background: false,
  timeout: 3600000,
-  description: "Brief description"
+  description: "简要描述"
 })
 ```

--- a/docs/zh-CN/commands/multi-execute.md
+++ b/docs/zh-CN/commands/multi-execute.md
@@ -21,7 +21,7 @@ $ARGUMENTS
 **调用语法**（并行：使用 `run_in_background: true`）：

 ```
-# Resume session call (recommended) - Implementation Prototype
+# 恢复会话调用（推荐）- 实现原型
 Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend <codex|gemini> {{GEMINI_MODEL_FLAG}}resume <SESSION_ID> - \"$PWD\" <<'EOF'
 ROLE_FILE: <role prompt path>
@@ -33,10 +33,10 @@ OUTPUT: Unified Diff Patch ONLY. Strictly prohibit any actual modifications.
 EOF",
  run_in_background: true,
  timeout: 3600000,
-  description: "Brief description"
+  description: "简要描述"
 })

-# New session call - Implementation Prototype
+# 新建会话调用 - 实现原型
 Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend <codex|gemini> {{GEMINI_MODEL_FLAG}}- \"$PWD\" <<'EOF'
 ROLE_FILE: <role prompt path>
@@ -48,7 +48,7 @@ OUTPUT: Unified Diff Patch ONLY. Strictly prohibit any actual modifications.
 EOF",
  run_in_background: true,
  timeout: 3600000,
-  description: "Brief description"
+  description: "简要描述"
 })
 ```

@@ -59,21 +59,21 @@ Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend <codex|gemini> {{GEMINI_MODEL_FLAG}}resume <SESSION_ID> - \"$PWD\" <<'EOF'
 ROLE_FILE: <role prompt path>
 <TASK>
-Scope: Audit the final code changes.
+Scope: 审计最终的代码变更。
 Inputs:
- The applied patch (git diff / final unified diff)
- The touched files (relevant excerpts if needed)
+- 已应用的补丁 (git diff / final unified diff)
+- 涉及的文件 (必要时提供相关摘录)
 Constraints:
- Do NOT modify any files.
- Do NOT output tool commands that assume filesystem access.
+- 请勿修改任何文件。
+- 请勿输出假设有文件系统访问权限的工具命令。
 </TASK>
 OUTPUT:
-1) A prioritized list of issues (severity, file, rationale)
-2) Concrete fixes; if code changes are needed, include a Unified Diff Patch in a fenced code block.
+1) 一个按优先级排序的问题列表 (严重程度, 文件, 理由)
+2) 具体的修复方案；如果需要更改代码，请包含在一个用围栏代码块包裹的 Unified Diff Patch 中。
 EOF",
  run_in_background: true,
  timeout: 3600000,
-  description: "Brief description"
+  description: "简要描述"
 })
 ```

@@ -144,7 +144,7 @@ TaskOutput({ task_id: "<task_id>", block: true, timeout: 600000 })

 ```
 mcp__ace-tool__search_context({
-  query: "<semantic query based on plan content, including key files, modules, function names>",
+  query: "<基于计划内容的语义查询，包括关键文件、模块、函数名>",
  project_root_path: "$PWD"
 })
 ```
--- a/docs/zh-CN/commands/multi-frontend.md
+++ b/docs/zh-CN/commands/multi-frontend.md
@@ -31,34 +31,34 @@
 **调用语法**:

 ```
-# New session call
+# 新会话调用
 Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend gemini --gemini-model gemini-3-pro-preview - \"$PWD\" <<'EOF'
-ROLE_FILE: <role prompt path>
+ROLE_FILE: <角色提示文件路径>
 <TASK>
-Requirement: <enhanced requirement (or $ARGUMENTS if not enhanced)>
-Context: <project context and analysis from previous phases>
+需求: <增强后的需求（若未增强则为$ARGUMENTS）>
+上下文: <来自先前阶段的项目上下文与分析>
 </TASK>
-OUTPUT: Expected output format
+OUTPUT: 期望的输出格式
 EOF",
  run_in_background: false,
  timeout: 3600000,
-  description: "Brief description"
+  description: "简要描述"
 })

-# Resume session call
+# 恢复会话调用
 Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend gemini --gemini-model gemini-3-pro-preview resume <SESSION_ID> - \"$PWD\" <<'EOF'
-ROLE_FILE: <role prompt path>
+ROLE_FILE: <角色提示文件路径>
 <TASK>
-Requirement: <enhanced requirement (or $ARGUMENTS if not enhanced)>
-Context: <project context and analysis from previous phases>
+需求: <增强后的需求（若未增强则为$ARGUMENTS）>
+上下文: <来自先前阶段的项目上下文与分析>
 </TASK>
-OUTPUT: Expected output format
+OUTPUT: 期望的输出格式
 EOF",
  run_in_background: false,
  timeout: 3600000,
-  description: "Brief description"
+  description: "简要描述"
 })
 ```

--- a/docs/zh-CN/commands/multi-plan.md
+++ b/docs/zh-CN/commands/multi-plan.md
@@ -93,7 +93,7 @@ mcp__ace-tool__enhance_prompt({

 ```
 mcp__ace-tool__search_context({
-  query: "<semantic query based on enhanced requirement>",
+  query: "<基于增强需求的语义查询>",
  project_root_path: "$PWD"
 })
 ```
--- a/docs/zh-CN/commands/multi-workflow.md
+++ b/docs/zh-CN/commands/multi-workflow.md
@@ -35,34 +35,34 @@
 **调用语法**（并行：`run_in_background: true`，串行：`false`）：

 ```
-# New session call
+# 新会话调用
 Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend <codex|gemini> {{GEMINI_MODEL_FLAG}}- \"$PWD\" <<'EOF'
-ROLE_FILE: <role prompt path>
+ROLE_FILE: <角色提示文件路径>
 <TASK>
-Requirement: <enhanced requirement (or $ARGUMENTS if not enhanced)>
-Context: <project context and analysis from previous phases>
+需求: <增强后的需求（如未增强则为$ARGUMENTS）>
+上下文: <来自先前阶段的项目上下文和分析>
 </TASK>
-OUTPUT: Expected output format
+OUTPUT: 期望的输出格式
 EOF",
  run_in_background: true,
  timeout: 3600000,
-  description: "Brief description"
+  description: "简要描述"
 })

-# Resume session call
+# 恢复会话调用
 Bash({
  command: "~/.claude/bin/codeagent-wrapper {{LITE_MODE_FLAG}}--backend <codex|gemini> {{GEMINI_MODEL_FLAG}}resume <SESSION_ID> - \"$PWD\" <<'EOF'
-ROLE_FILE: <role prompt path>
+ROLE_FILE: <角色提示文件路径>
 <TASK>
-Requirement: <enhanced requirement (or $ARGUMENTS if not enhanced)>
-Context: <project context and analysis from previous phases>
+需求: <增强后的需求（如未增强则为$ARGUMENTS）>
+上下文: <来自先前阶段的项目上下文和分析>
 </TASK>
-OUTPUT: Expected output format
+OUTPUT: 期望的输出格式
 EOF",
  run_in_background: true,
  timeout: 3600000,
-  description: "Brief description"
+  description: "简要描述"
 })
 ```

--- a/docs/zh-CN/commands/orchestrate.md
+++ b/docs/zh-CN/commands/orchestrate.md
@@ -17,7 +17,7 @@ description: 针对多智能体工作流程的顺序和tmux/worktree编排指南
 完整功能实现工作流：

 ```
-planner -> tdd-guide -> code-reviewer -> security-reviewer
+规划者 -> 测试驱动开发指南 -> 代码审查员 -> 安全审查员
 ```

 ### bugfix
@@ -33,7 +33,7 @@ planner -> tdd-guide -> code-reviewer
 安全重构工作流：

 ```
-architect -> code-reviewer -> tdd-guide
+架构师 -> 代码审查员 -> 测试驱动开发指南
 ```

 ### security
@@ -112,38 +112,38 @@ security-reviewer -> code-reviewer -> architect
 ## 最终报告格式

 ```
-ORCHESTRATION REPORT
+编排报告
 ====================
-Workflow: feature
-Task: Add user authentication
-Agents: planner -> tdd-guide -> code-reviewer -> security-reviewer
+工作流：功能
+任务：添加用户认证
+智能体：规划者 -> TDD指南 -> 代码审查员 -> 安全审查员

-SUMMARY
+概要
 -------
-[One paragraph summary]
+[一段总结]

-AGENT OUTPUTS
+智能体输出
 -------------
-Planner: [summary]
-TDD Guide: [summary]
-Code Reviewer: [summary]
-Security Reviewer: [summary]
+规划者：[总结]
+TDD指南：[总结]
+代码审查员：[总结]
+安全审查员：[总结]

-FILES CHANGED
+已更改文件
 -------------
-[List all files modified]
+[列出所有修改的文件]

-TEST RESULTS
+测试结果
 ------------
-[Test pass/fail summary]
+[测试通过/失败总结]

-SECURITY STATUS
+安全状态
 ---------------
-[Security findings]
+[安全发现]

-RECOMMENDATION
+建议
 --------------
-[SHIP / NEEDS WORK / BLOCKED]
+[可发布 / 需要改进 / 已阻止]
 ```

 ## 并行执行
@@ -230,7 +230,7 @@ $ARGUMENTS:
 ## 自定义工作流示例

 ```
-/orchestrate custom "architect,tdd-guide,code-reviewer" "Redesign caching layer"
+/orchestrate 自定义 "architect,tdd-guide,code-reviewer" "重新设计缓存层"
 ```

 ## 提示
--- a/docs/zh-CN/commands/plan.md
+++ b/docs/zh-CN/commands/plan.md
@@ -37,59 +37,59 @@ planner 代理将：
 ## 使用示例

 ```
-User: /plan I need to add real-time notifications when markets resolve
+User: /plan 我需要为市场结算时添加实时通知功能

 Agent (planner):
-# Implementation Plan: Real-Time Market Resolution Notifications
+# 实施计划：实时市场结算通知

-## Requirements Restatement
- Send notifications to users when markets they're watching resolve
- Support multiple notification channels (in-app, email, webhook)
- Ensure notifications are delivered reliably
- Include market outcome and user's position result
+## 需求重述
+- 当用户关注的市场结算时，向用户发送通知
+- 支持多种通知渠道（应用内、电子邮件、Webhook）
+- 确保通知可靠送达
+- 包含市场结果和用户持仓结果

-## Implementation Phases
+## 实施阶段

-### Phase 1: Database Schema
- Add notifications table with columns: id, user_id, market_id, type, status, created_at
- Add user_notification_preferences table for channel preferences
- Create indexes on user_id and market_id for performance
+### 第一阶段：数据库架构
+- 添加 notifications 表，包含列：id, user_id, market_id, type, status, created_at
+- 添加 user_notification_preferences 表用于存储渠道偏好设置
+- 在 user_id 和 market_id 上创建索引以提升性能

-### Phase 2: Notification Service
- Create notification service in lib/notifications.ts
- Implement notification queue using BullMQ/Redis
- Add retry logic for failed deliveries
- Create notification templates
+### 第二阶段：通知服务
+- 在 lib/notifications.ts 中创建通知服务
+- 使用 BullMQ/Redis 实现通知队列
+- 为发送失败的情况添加重试逻辑
+- 创建通知模板

-### Phase 3: Integration Points
- Hook into market resolution logic (when status changes to "resolved")
- Query all users with positions in market
- Enqueue notifications for each user
+### 第三阶段：集成点
+- 接入市场结算逻辑（当状态变为 "resolved" 时）
+- 查询在市场中有持仓的所有用户
+- 为每个用户将通知加入队列

-### Phase 4: Frontend Components
- Create NotificationBell component in header
- Add NotificationList modal
- Implement real-time updates via Supabase subscriptions
- Add notification preferences page
+### 第四阶段：前端组件
+- 在头部创建 NotificationBell 组件
+- 添加 NotificationList 模态框
+- 通过 Supabase 订阅实现实时更新
+- 添加通知偏好设置页面

-## Dependencies
- Redis (for queue)
- Email service (SendGrid/Resend)
- Supabase real-time subscriptions
+## 依赖项
+- Redis（用于队列）
+- 电子邮件服务（SendGrid/Resend）
+- Supabase 实时订阅

-## Risks
- HIGH: Email deliverability (SPF/DKIM required)
- MEDIUM: Performance with 1000+ users per market
- MEDIUM: Notification spam if markets resolve frequently
- LOW: Real-time subscription overhead
+## 风险
+- 高：电子邮件送达率（需要配置 SPF/DKIM）
+- 中：市场用户超过 1000+ 时的性能问题
+- 中：市场频繁结算可能导致通知泛滥
+- 低：实时订阅开销

-## Estimated Complexity: MEDIUM
- Backend: 4-6 hours
- Frontend: 3-4 hours
- Testing: 2-3 hours
- Total: 9-13 hours
+## 预估复杂度：中
+- 后端：4-6 小时
+- 前端：3-4 小时
+- 测试：2-3 小时
+- 总计：9-13 小时

-**WAITING FOR CONFIRMATION**: Proceed with this plan? (yes/no/modify)
+**等待确认**：是否按此计划进行？（是/否/修改）
 ```

 ## 重要说明
--- a/docs/zh-CN/commands/pm2.md
+++ b/docs/zh-CN/commands/pm2.md
@@ -34,21 +34,21 @@

 ```
 project/
-├── ecosystem.config.cjs              # PM2 config
-├── {backend}/start.cjs               # Python wrapper (if applicable)
+├── ecosystem.config.cjs              # PM2 配置文件
+├── {backend}/start.cjs               # Python 包装器（如适用）
 └── .claude/
    ├── commands/
-    │   ├── pm2-all.md                # Start all + monit
-    │   ├── pm2-all-stop.md           # Stop all
-    │   ├── pm2-all-restart.md        # Restart all
-    │   ├── pm2-{port}.md             # Start single + logs
-    │   ├── pm2-{port}-stop.md        # Stop single
-    │   ├── pm2-{port}-restart.md     # Restart single
-    │   ├── pm2-logs.md               # View all logs
-    │   └── pm2-status.md             # View status
+    │   ├── pm2-all.md                # 启动所有 + 监控
+    │   ├── pm2-all-stop.md           # 停止所有
+    │   ├── pm2-all-restart.md        # 重启所有
+    │   ├── pm2-{port}.md             # 启动单个 + 日志
+    │   ├── pm2-{port}-stop.md        # 停止单个
+    │   ├── pm2-{port}-restart.md     # 重启单个
+    │   ├── pm2-logs.md               # 查看所有日志
+    │   └── pm2-status.md             # 查看状态
    └── scripts/
-        ├── pm2-logs-{port}.ps1       # Single service logs
-        └── pm2-monit.ps1             # PM2 monitor
+        ├── pm2-logs-{port}.ps1       # 单个服务日志
+        └── pm2-monit.ps1             # PM2 监控器
 ```

 ***
@@ -255,29 +255,29 @@ pm2 resurrect                    # Restore saved list
 所有文件生成后，输出：

 ```
-## PM2 Init Complete
+## PM2 初始化完成

-**Services:**
+**服务列表：**

-| Port | Name | Type |
+| 端口 | 名称 | 类型 |
 |------|------|------|
 | {port} | {name} | {type} |

-**Claude Commands:** /pm2-all, /pm2-all-stop, /pm2-{port}, /pm2-{port}-stop, /pm2-logs, /pm2-status
+**Claude 指令：** /pm2-all, /pm2-all-stop, /pm2-{port}, /pm2-{port}-stop, /pm2-logs, /pm2-status

-**Terminal Commands:**
-## First time (with config file)
+**终端命令：**
+## 首次运行（使用配置文件）
 pm2 start ecosystem.config.cjs && pm2 save

-## After first time (simplified)
-pm2 start all          # Start all
-pm2 stop all           # Stop all
-pm2 restart all        # Restart all
-pm2 start {name}       # Start single
-pm2 stop {name}        # Stop single
-pm2 logs               # View logs
-pm2 monit              # Monitor panel
-pm2 resurrect          # Restore saved processes
+## 首次之后（简化命令）
+pm2 start all          # 启动全部
+pm2 stop all           # 停止全部
+pm2 restart all        # 重启全部
+pm2 start {name}       # 启动单个
+pm2 stop {name}        # 停止单个
+pm2 logs               # 查看日志
+pm2 monit              # 监控面板
+pm2 resurrect          # 恢复已保存进程

-**Tip:** Run `pm2 save` after first start to enable simplified commands.
+**提示：** 首次启动后运行 `pm2 save` 以启用简化命令。
 ```
--- a/docs/zh-CN/commands/python-review.md
+++ b/docs/zh-CN/commands/python-review.md
@@ -178,54 +178,53 @@ with open("config.json") as f:  # Good
 运行：`black app/routes/user.py app/services/auth.py`

 ````
+## 审批标准

-## Approval Criteria
-
-| Status | Condition |
+| 状态 | 条件 |
 |--------|-----------|
-| ✅ Approve | No CRITICAL or HIGH issues |
-| ⚠️ Warning | Only MEDIUM issues (merge with caution) |
-| ❌ Block | CRITICAL or HIGH issues found |
+| ✅ 批准 | 无 CRITICAL 或 HIGH 级别问题 |
+| ⚠️ 警告 | 仅存在 MEDIUM 级别问题（谨慎合并） |
+| ❌ 阻止 | 发现 CRITICAL 或 HIGH 级别问题 |

-## Integration with Other Commands
+## 与其他命令的集成

- Use `/tdd` first to ensure tests pass
- Use `/code-review` for non-Python specific concerns
- Use `/python-review` before committing
- Use `/build-fix` if static analysis tools fail
+- 首先使用 `/tdd` 确保测试通过
+- 使用 `/code-review` 处理非 Python 特定问题
+- 在提交前使用 `/python-review`
+- 如果静态分析工具失败，请使用 `/build-fix`

-## Framework-Specific Reviews
+## 框架特定审查

-### Django Projects
-The reviewer checks for:
- N+1 query issues (use `select_related` and `prefetch_related`)
- Missing migrations for model changes
- Raw SQL usage when ORM could work
- Missing `transaction.atomic()` for multi-step operations
+### Django 项目
+审查员检查：
+- N+1 查询问题（使用 `select_related` 和 `prefetch_related`）
+- 模型更改缺少迁移
+- 在 ORM 可用时使用原始 SQL
+- 多步骤操作缺少 `transaction.atomic()`

-### FastAPI Projects
-The reviewer checks for:
- CORS misconfiguration
- Pydantic models for request validation
- Response models correctness
- Proper async/await usage
- Dependency injection patterns
+### FastAPI 项目
+审查员检查：
+- CORS 配置错误
+- 用于请求验证的 Pydantic 模型
+- 响应模型的正确性
+- 正确的 async/await 使用
+- 依赖注入模式

-### Flask Projects
-The reviewer checks for:
- Context management (app context, request context)
- Proper error handling
- Blueprint organization
- Configuration management
+### Flask 项目
+审查员检查：
+- 上下文管理（应用上下文、请求上下文）
+- 正确的错误处理
+- Blueprint 组织
+- 配置管理

-## Related
+## 相关

 - Agent: `agents/python-reviewer.md`
 - Skills: `skills/python-patterns/`, `skills/python-testing/`

-## Common Fixes
+## 常见修复

-### Add Type Hints
+### 添加类型提示
 ```python
 # Before
 def calculate(x, y):
--- a/docs/zh-CN/commands/refactor-clean.md
+++ b/docs/zh-CN/commands/refactor-clean.md
@@ -18,7 +18,7 @@
 如果没有可用工具，使用 Grep 查找零次导入的导出：

 ```
-# Find exports, then check if they're imported anywhere
+# 查找导出项，然后检查是否有任何地方导入了它们
 ```

 ## 步骤 2：分类发现结果
@@ -64,15 +64,15 @@
 报告结果：

 ```
-Dead Code Cleanup
+无用代码清理
 ──────────────────────────────
-Deleted:   12 unused functions
-           3 unused files
-           5 unused dependencies
-Skipped:   2 items (tests failed)
-Saved:     ~450 lines removed
+已删除：   12 个未使用函数
+           3 个未使用文件
+           5 个未使用依赖项
+已跳过：   2 个项目（测试失败）
+已节省：   ~450 行代码被移除
 ──────────────────────────────
-All tests passing ✅
+所有测试通过 ✅
 ```

 ## 规则
--- a/docs/zh-CN/commands/resume-session.md
+++ b/docs/zh-CN/commands/resume-session.md
@@ -17,10 +17,10 @@ description: 从 ~/.claude/sessions/ 加载最新的会话文件，并从上次
 ## 用法

 ```
-/resume-session                                                      # loads most recent file in ~/.claude/sessions/
-/resume-session 2024-01-15                                           # loads most recent session for that date
-/resume-session ~/.claude/sessions/2024-01-15-session.tmp           # loads a specific legacy-format file
-/resume-session ~/.claude/sessions/2024-01-15-abc123de-session.tmp  # loads a current short-id session file
+/resume-session                                                      # 加载 ~/.claude/sessions/ 目录下最新的文件
+/resume-session 2024-01-15                                           # 加载该日期最新的会话
+/resume-session ~/.claude/sessions/2024-01-15-session.tmp           # 加载特定的旧格式文件
+/resume-session ~/.claude/sessions/2024-01-15-abc123de-session.tmp  # 加载当前短ID格式的会话文件
 ```

 ## 流程
@@ -55,31 +55,31 @@ description: 从 ~/.claude/sessions/ 加载最新的会话文件，并从上次
 使用以下确切格式回复一份结构化简报：

 ```
-SESSION LOADED: [actual resolved path to the file]
+会话已加载：[文件的实际解析路径]
 ════════════════════════════════════════════════

-PROJECT: [project name / topic from file]
+项目：[文件中的项目名称/主题]

-WHAT WE'RE BUILDING:
-[2-3 sentence summary in your own words]
+我们正在构建什么：
+[用你自己的话总结 2-3 句话]

-CURRENT STATE:
-✅ Working: [count] items confirmed
-🔄 In Progress: [list files that are in progress]
-🗒️ Not Started: [list planned but untouched]
+当前状态：
+✅ 已完成：[数量] 项已确认
+🔄 进行中：[列出进行中的文件]
+🗒️ 未开始：[列出计划但未开始的文件]

-WHAT NOT TO RETRY:
-[list every failed approach with its reason — this is critical]
+不应重试的内容：
+[列出每个失败的方法及其原因——此部分至关重要]

-OPEN QUESTIONS / BLOCKERS:
-[list any blockers or unanswered questions]
+待解决问题/阻碍：
+[列出任何阻碍或未解答的问题]

-NEXT STEP:
-[exact next step if defined in the file]
-[if not defined: "No next step defined — recommend reviewing 'What Has NOT Been Tried Yet' together before starting"]
+下一步：
+[如果文件中已定义，则列出确切下一步]
+[如果未定义："未定义下一步——建议在开始前共同回顾'尚未尝试的方法'"]

 ════════════════════════════════════════════════
-Ready to continue. What would you like to do?
+准备就绪。您希望做什么？
 ```

 ### 步骤 4：等待用户
@@ -117,32 +117,31 @@ Ready to continue. What would you like to do?
 SESSION LOADED: /Users/you/.claude/sessions/2024-01-15-abc123de-session.tmp
 ════════════════════════════════════════════════

-PROJECT: my-app — JWT Authentication
+项目：my-app — JWT 认证

-WHAT WE'RE BUILDING:
-User authentication with JWT tokens stored in httpOnly cookies.
-Register and login endpoints are partially done. Route protection
-via middleware hasn't been started yet.
+构建目标：
+使用存储在 httpOnly cookie 中的 JWT 令牌实现用户认证。
+注册和登录端点已部分完成。通过中间件进行路由保护尚未开始。

-CURRENT STATE:
-✅ Working: 3 items (register endpoint, JWT generation, password hashing)
-🔄 In Progress: app/api/auth/login/route.ts (token works, cookie not set yet)
-🗒️ Not Started: middleware.ts, app/login/page.tsx
+当前状态：
+✅ 已完成：3 项（注册端点、JWT 生成、密码哈希）
+🔄 进行中：app/api/auth/login/route.ts（令牌有效，但 cookie 尚未设置）
+🗒️ 未开始：middleware.ts、app/login/page.tsx

-WHAT NOT TO RETRY:
-❌ Next-Auth — conflicts with custom Prisma adapter, threw adapter error on every request
-❌ localStorage for JWT — causes SSR hydration mismatch, incompatible with Next.js
+需避免的事项：
+❌ Next-Auth — 与自定义 Prisma 适配器冲突，每次请求均抛出适配器错误
+❌ localStorage 存储 JWT — 导致 SSR 水合不匹配，与 Next.js 不兼容

-OPEN QUESTIONS / BLOCKERS:
- Does cookies().set() work inside a Route Handler or only Server Actions?
+待解决问题 / 阻碍：
+- cookies().set() 在路由处理器中是否有效，还是仅适用于服务器操作？

-NEXT STEP:
-In app/api/auth/login/route.ts — set the JWT as an httpOnly cookie using
+下一步：
+在 app/api/auth/login/route.ts 中 — 使用以下方式将 JWT 设置为 httpOnly cookie：
 cookies().set('token', jwt, { httpOnly: true, secure: true, sameSite: 'strict' })
-then test with Postman for a Set-Cookie header in the response.
+随后使用 Postman 测试响应中是否包含 Set-Cookie 标头。

 ════════════════════════════════════════════════
-Ready to continue. What would you like to do?
+准备继续。您希望做什么？
 ```

 ***
--- a/docs/zh-CN/commands/rust-test.md
+++ b/docs/zh-CN/commands/rust-test.md
@@ -28,10 +28,10 @@ description: 为Rust强制执行TDD工作流。先写测试，然后实现。使
 ## TDD 循环

 ```
-RED     -> Write failing test first
-GREEN   -> Implement minimal code to pass
-REFACTOR -> Improve code, tests stay green
-REPEAT  -> Next test case
+RED     -> 先编写失败的测试
+GREEN   -> 实现最小化代码以通过测试
+REFACTOR -> 改进代码，保持测试通过
+REPEAT  -> 下一个测试用例
 ```

 ## 示例会话
--- a/docs/zh-CN/commands/save-session.md
+++ b/docs/zh-CN/commands/save-session.md
@@ -56,9 +56,9 @@ mkdir -p ~/.claude/sessions
 写入后，显示完整内容并询问：

 ```
-Session saved to [actual resolved path to the session file]
+会话已保存至 [实际解析的会话文件路径]

-Does this look accurate? Anything to correct or add before we close?
+这看起来准确吗？在关闭之前，还有什么需要纠正或补充的吗？
 ```

 等待确认。如果用户要求，进行编辑。
--- a/docs/zh-CN/commands/skill-create.md
+++ b/docs/zh-CN/commands/skill-create.md
@@ -138,24 +138,23 @@ src/
 └── services/       # API 和外部服务

 ```
+## 工作流

-## Workflows
+### 添加新组件
+1. 创建 `src/components/ComponentName.tsx`
+2. 在 `src/components/__tests__/ComponentName.test.tsx` 中添加测试
+3. 从 `src/components/index.ts` 导出

-### Adding a New Component
-1. Create `src/components/ComponentName.tsx`
-2. Add tests in `src/components/__tests__/ComponentName.test.tsx`
-3. Export from `src/components/index.ts`
+### 数据库迁移
+1. 修改 `src/db/schema.ts`
+2. 运行 `pnpm db:generate`
+3. 运行 `pnpm db:migrate`

-### Database Migration
-1. Modify `src/db/schema.ts`
-2. Run `pnpm db:generate`
-3. Run `pnpm db:migrate`
+## 测试模式

-## Testing Patterns
-
- Test files: `__tests__/` directories or `.test.ts` suffix
- Coverage target: 80%+
- Framework: Vitest
+- 测试文件：`__tests__/` 目录或 `.test.ts` 后缀
+- 覆盖率目标：80%+
+- 框架：Vitest
 ```

 ## GitHub 应用集成
--- a/docs/zh-CN/commands/skill-health.md
+++ b/docs/zh-CN/commands/skill-health.md
@@ -34,9 +34,9 @@ node "$ECC_ROOT/scripts/skills-health.js" --dashboard --json
 ## 使用方法

 ```
-/skill-health                    # Full dashboard view
-/skill-health --panel failures   # Only failure clustering panel
-/skill-health --json             # Machine-readable JSON output
+/skill-health                    # 完整仪表盘视图
+/skill-health --panel failures   # 仅故障聚类面板
+/skill-health --json             # 机器可读的 JSON 输出
 ```

 ## 操作步骤
--- a/docs/zh-CN/commands/tdd.md
+++ b/docs/zh-CN/commands/tdd.md
@@ -41,10 +41,10 @@ tdd-guide 代理将：
 ```
 RED → GREEN → REFACTOR → REPEAT

-RED:      Write a failing test
-GREEN:    Write minimal code to pass
-REFACTOR: Improve code, keep tests passing
-REPEAT:   Next feature/scenario
+RED:      编写一个失败测试
+GREEN:    编写通过测试的最简代码
+REFACTOR: 改进代码，保持测试通过
+REPEAT:   开始下一个功能/场景
 ```

 ## 使用示例
@@ -254,79 +254,77 @@ Coverage: 100% ✅ (Target: 80%)
 ✅ TDD 会话完成！

 ```
+## TDD 最佳实践

-## TDD Best Practices
+**应做：**
+- ✅ 先写测试，再写实现
+- ✅ 运行测试并确认失败，再实现功能
+- ✅ 编写最少代码使测试通过
+- ✅ 仅在测试通过后进行重构
+- ✅ 添加边界情况和错误场景
+- ✅ 目标覆盖率 80% 以上（关键代码 100%）

-**DO:**
- ✅ Write the test FIRST, before any implementation
- ✅ Run tests and verify they FAIL before implementing
- ✅ Write minimal code to make tests pass
- ✅ Refactor only after tests are green
- ✅ Add edge cases and error scenarios
- ✅ Aim for 80%+ coverage (100% for critical code)
+**不应做：**
+- ❌ 先写实现再写测试
+- ❌ 每次更改后跳过运行测试
+- ❌ 一次性编写过多代码
+- ❌ 忽略失败的测试
+- ❌ 测试实现细节（应测试行为）
+- ❌ 过度模拟（优先使用集成测试）

-**DON'T:**
- ❌ Write implementation before tests
- ❌ Skip running tests after each change
- ❌ Write too much code at once
- ❌ Ignore failing tests
- ❌ Test implementation details (test behavior)
- ❌ Mock everything (prefer integration tests)
+## 应包含的测试类型

-## Test Types to Include
+**单元测试**（函数级别）：
+- 正常路径场景
+- 边界情况（空值、null、最大值）
+- 错误条件
+- 边界值

-**Unit Tests** (Function-level):
- Happy path scenarios
- Edge cases (empty, null, max values)
- Error conditions
- Boundary values
+**集成测试**（组件级别）：
+- API 端点
+- 数据库操作
+- 外部服务调用
+- 包含钩子的 React 组件

-**Integration Tests** (Component-level):
- API endpoints
- Database operations
- External service calls
- React components with hooks
+**端到端测试**（使用 `/e2e` 命令）：
+- 关键用户流程
+- 多步骤流程
+- 全栈集成

-**E2E Tests** (use `/e2e` command):
- Critical user flows
- Multi-step processes
- Full stack integration
+## 覆盖率要求

-## Coverage Requirements
+- 所有代码**最低 80%**
+- **必须达到 100%** 的代码：
+  - 财务计算
+  - 认证逻辑
+  - 安全关键代码
+  - 核心业务逻辑

- **80% minimum** for all code
- **100% required** for:
-  - Financial calculations
-  - Authentication logic
-  - Security-critical code
-  - Core business logic
+## 重要说明

-## Important Notes
+**强制要求**：测试必须在实现之前编写。TDD 循环是：

-**MANDATORY**: Tests must be written BEFORE implementation. The TDD cycle is:
+1. **红** - 编写失败的测试
+2. **绿** - 实现功能使测试通过
+3. **重构** - 改进代码

-1. **RED** - Write failing test
-2. **GREEN** - Implement to pass
-3. **REFACTOR** - Improve code
+切勿跳过红阶段。切勿在测试之前编写代码。

-Never skip the RED phase. Never write code before tests.
+## 与其他命令的集成

-## Integration with Other Commands
+- 首先使用 `/plan` 来了解要构建什么
+- 使用 `/tdd` 进行带测试的实现
+- 如果出现构建错误，请使用 `/build-fix`
+- 使用 `/code-review` 审查实现
+- 使用 `/test-coverage` 验证覆盖率

- Use `/plan` first to understand what to build
- Use `/tdd` to implement with tests
- Use `/build-fix` if build errors occur
- Use `/code-review` to review implementation
- Use `/test-coverage` to verify coverage
+## 相关代理

-## Related Agents
+此命令调用由 ECC 提供的 `tdd-guide` 代理。

-This command invokes the `tdd-guide` agent provided by ECC.
+相关的 `tdd-workflow` 技能也随 ECC 捆绑提供。

-The related `tdd-workflow` skill is also bundled with ECC.
-
-For manual installs, the source files live at:
+对于手动安装，源文件位于：
 - `agents/tdd-guide.md`
 - `skills/tdd-workflow/SKILL.md`
-
 ```
--- a/docs/zh-CN/commands/test-coverage.md
+++ b/docs/zh-CN/commands/test-coverage.md
@@ -51,13 +51,13 @@
 显示前后对比：

 ```
-Coverage Report
+覆盖率报告
 ──────────────────────────────
-File                   Before  After
+文件                   变更前  变更后
 src/services/auth.ts   45%     88%
 src/utils/validation.ts 32%    82%
 ──────────────────────────────
-Overall:               67%     84%  ✅
+总计：               67%     84%  ✅
 ```

 ## 重点关注领域
--- a/docs/zh-CN/commands/update-docs.md
+++ b/docs/zh-CN/commands/update-docs.md
@@ -69,12 +69,12 @@
 ## 步骤 7：显示摘要

 ```
-Documentation Update
+文档更新
 ──────────────────────────────
-Updated:  docs/CONTRIBUTING.md (scripts table)
-Updated:  docs/ENV.md (3 new variables)
-Flagged:  docs/DEPLOY.md (142 days stale)
-Skipped:  docs/API.md (no changes detected)
+已更新：docs/CONTRIBUTING.md（脚本表格）
+已更新：docs/ENV.md（新增3个变量）
+已标记：docs/DEPLOY.md（142天未更新）
+已跳过：docs/API.md（未检测到变更）
 ──────────────────────────────
 ```

--- a/docs/zh-CN/commands/verify.md
+++ b/docs/zh-CN/commands/verify.md
@@ -36,16 +36,16 @@
 生成一份简洁的验证报告：

 ```
-VERIFICATION: [PASS/FAIL]
+验证： [通过/失败]

-Build:    [OK/FAIL]
-Types:    [OK/X errors]
-Lint:     [OK/X issues]
-Tests:    [X/Y passed, Z% coverage]
-Secrets:  [OK/X found]
-Logs:     [OK/X console.logs]
+构建：    [成功/失败]
+类型：    [成功/X 错误]
+代码检查： [成功/X 问题]
+测试：    [X/Y 通过，Z% 覆盖率]
+密钥检查： [成功/X 发现]
+日志：     [成功/X console.logs]

-Ready for PR: [YES/NO]
+准备提交 PR： [是/否]
 ```

 如果存在任何关键问题，列出它们并提供修复建议。
--- a/docs/zh-CN/examples/CLAUDE.md
+++ b/docs/zh-CN/examples/CLAUDE.md
@@ -43,11 +43,11 @@

 ```
 src/
-|-- app/              # Next.js app router
-|-- components/       # Reusable UI components
-|-- hooks/            # Custom React hooks
-|-- lib/              # Utility libraries
-|-- types/            # TypeScript definitions
+|-- app/              # Next.js 应用路由
+|-- components/       # 可复用的 UI 组件
+|-- hooks/            # 自定义 React 钩子
+|-- lib/              # 工具库
+|-- types/            # TypeScript 定义
 ```

 ## 关键模式
--- a/docs/zh-CN/examples/django-api-CLAUDE.md
+++ b/docs/zh-CN/examples/django-api-CLAUDE.md
@@ -97,38 +97,38 @@ class InsufficientStockError(APIException):
 ```
 config/
  settings/
-    base.py              # Shared settings
-    local.py             # Dev overrides (DEBUG=True)
-    production.py        # Production settings
-  urls.py                # Root URL config
-  celery.py              # Celery app configuration
+    base.py              # 共享设置
+    local.py             # 开发环境覆盖设置 (DEBUG=True)
+    production.py        # 生产环境设置
+  urls.py                # 根 URL 配置
+  celery.py              # Celery 应用配置
 apps/
-  accounts/              # User auth, registration, profile
+  accounts/              # 用户认证、注册、个人资料
    models.py
    serializers.py
    views.py
-    services.py          # Business logic
+    services.py          # 业务逻辑
    tests/
      test_views.py
      test_services.py
-      factories.py       # Factory Boy factories
-  orders/                # Order management
+      factories.py       # Factory Boy 工厂
+  orders/                # 订单管理
    models.py
    serializers.py
    views.py
    services.py
-    tasks.py             # Celery tasks
+    tasks.py             # Celery 任务
    tests/
-  products/              # Product catalog
+  products/              # 产品目录
    models.py
    serializers.py
    views.py
    tests/
 core/
-  exceptions.py          # Custom API exceptions
-  permissions.py         # Shared permission classes
-  pagination.py          # Custom pagination
-  middleware.py          # Request logging, timing
+  exceptions.py          # 自定义 API 异常
+  permissions.py         # 共享权限类
+  pagination.py          # 自定义分页
+  middleware.py          # 请求日志记录、计时
  tests/
 ```

--- a/docs/zh-CN/examples/go-microservice-CLAUDE.md
+++ b/docs/zh-CN/examples/go-microservice-CLAUDE.md
@@ -66,31 +66,31 @@ func toGRPCError(err error) error {
 ```
 cmd/
  server/
-    main.go              # Entrypoint, Wire injection, graceful shutdown
+    main.go              # 入口点，Wire注入，优雅关闭
 internal/
-  domain/                # Business types and interfaces
-    user.go              # User entity and repository interface
-    errors.go            # Sentinel errors
-  service/               # Business logic
+  domain/                # 业务类型和接口
+    user.go              # 用户实体和仓库接口
+    errors.go            # 哨兵错误
+  service/               # 业务逻辑
    user_service.go
    user_service_test.go
-  repository/            # Data access (sqlc-generated + custom)
+  repository/            # 数据访问（sqlc生成 + 自定义）
    postgres/
      user_repo.go
-      user_repo_test.go  # Integration tests with testcontainers
-  handler/               # gRPC + REST handlers
+      user_repo_test.go  # 使用testcontainers的集成测试
+  handler/               # gRPC + REST处理程序
    grpc/
      user_handler.go
    rest/
      user_handler.go
-  config/                # Configuration loading
+  config/                # 配置加载
    config.go
-proto/                   # Protobuf definitions
+proto/                   # Protobuf定义
  user/v1/
    user.proto
-queries/                 # SQL queries for sqlc
+queries/                 # sqlc的SQL查询
  user.sql
-migrations/              # Database migrations
+migrations/              # 数据库迁移
  001_create_users.up.sql
  001_create_users.down.sql
 ```
--- a/docs/zh-CN/examples/rust-api-CLAUDE.md
+++ b/docs/zh-CN/examples/rust-api-CLAUDE.md
@@ -92,36 +92,36 @@ impl IntoResponse for AppError {

 ```
 src/
-  main.rs              # Entrypoint, server setup, graceful shutdown
-  lib.rs               # Re-exports for integration tests
-  config.rs            # Environment config with envy or figment
-  router.rs            # Axum router with all routes
+  main.rs              # 入口点、服务器设置、优雅关闭
+  lib.rs               # 用于集成测试的重新导出
+  config.rs            # 使用 envy 或 figment 的环境配置
+  router.rs            # 包含所有路由的 Axum 路由器
  middleware/
-    auth.rs            # JWT extraction and validation
-    logging.rs         # Request/response tracing
+    auth.rs            # JWT 提取与验证
+    logging.rs         # 请求/响应追踪
  handlers/
-    mod.rs             # Route handlers (thin — delegate to services)
+    mod.rs             # 路由处理器（精简版——委托给服务层）
    users.rs
    orders.rs
  services/
-    mod.rs             # Business logic
+    mod.rs             # 业务逻辑
    users.rs
    orders.rs
  repositories/
-    mod.rs             # Database access (SQLx queries)
+    mod.rs             # 数据库访问（SQLx 查询）
    users.rs
    orders.rs
  domain/
-    mod.rs             # Domain types, error enums
+    mod.rs             # 领域类型、错误枚举
    user.rs
    order.rs
 migrations/
  001_create_users.sql
  002_create_orders.sql
 tests/
-  common/mod.rs        # Shared test helpers, test server setup
-  api_users.rs         # Integration tests for user endpoints
-  api_orders.rs        # Integration tests for order endpoints
+  common/mod.rs        # 共享测试辅助工具、测试服务器设置
+  api_users.rs         # 用户端点的集成测试
+  api_orders.rs        # 订单端点的集成测试
 ```

 ## 关键模式
--- a/docs/zh-CN/examples/saas-nextjs-CLAUDE.md
+++ b/docs/zh-CN/examples/saas-nextjs-CLAUDE.md
@@ -45,24 +45,24 @@
 ```
 src/
  app/
-    (auth)/          # Auth pages (login, signup, forgot-password)
-    (dashboard)/     # Protected dashboard pages
+    (auth)/          # 认证页面（登录、注册、忘记密码）
+    (dashboard)/     # 受保护的仪表板页面
    api/
-      webhooks/      # Stripe, Supabase webhooks
-    layout.tsx       # Root layout with providers
+      webhooks/      # Stripe、Supabase webhooks
+    layout.tsx       # 根布局（包含 providers）
  components/
-    ui/              # Shadcn/ui components
-    forms/           # Form components with validation
-    dashboard/       # Dashboard-specific components
-  hooks/             # Custom React hooks
+    ui/              # Shadcn/ui 组件
+    forms/           # 带验证的表单组件
+    dashboard/       # 仪表板专用组件
+  hooks/             # 自定义 React hooks
  lib/
-    supabase/        # Supabase client factories
-    stripe/          # Stripe client and helpers
-    utils.ts         # General utilities
-  types/             # Shared TypeScript types
+    supabase/        # Supabase 客户端工厂
+    stripe/          # Stripe 客户端与辅助工具
+    utils.ts         # 通用工具函数
+  types/             # 共享 TypeScript 类型
 supabase/
-  migrations/        # Database migrations
-  seed.sql           # Development seed data
+  migrations/        # 数据库迁移
+  seed.sql           # 开发用种子数据
 ```

 ## 关键模式
--- a/docs/zh-CN/hooks/README.md
+++ b/docs/zh-CN/hooks/README.md
@@ -5,7 +5,7 @@
 ## 钩子如何工作

 ```
-User request → Claude picks a tool → PreToolUse hook runs → Tool executes → PostToolUse hook runs
+用户请求 → Claude 选择工具 → PreToolUse 钩子运行 → 工具执行 → PostToolUse 钩子运行
 ```

 * **PreToolUse** 钩子在工具执行前运行。它们可以**阻止**（退出码 2）或**警告**（stderr 输出但不阻止）。
--- a/docs/zh-CN/plugins/README.md
+++ b/docs/zh-CN/plugins/README.md
@@ -82,8 +82,8 @@ claude plugin marketplace add https://github.com/mixedbread-ai/mgrep

 ```
 ~/.claude/plugins/
-|-- cache/                    # Downloaded plugins
-|-- installed_plugins.json    # Installed list
-|-- known_marketplaces.json   # Added marketplaces
-|-- marketplaces/             # Marketplace data
+|-- cache/                    # 已下载的插件
+|-- installed_plugins.json    # 已安装列表
+|-- known_marketplaces.json   # 已添加的市场
+|-- marketplaces/             # 市场数据
 ```
--- a/docs/zh-CN/rules/README.md
+++ b/docs/zh-CN/rules/README.md
@@ -6,7 +6,7 @@

 ```
 rules/
-├── common/          # Language-agnostic principles (always install)
+├── common/          # 语言无关原则（始终安装）
 │   ├── coding-style.md
 │   ├── git-workflow.md
 │   ├── testing.md
@@ -15,11 +15,11 @@ rules/
 │   ├── hooks.md
 │   ├── agents.md
 │   └── security.md
-├── typescript/      # TypeScript/JavaScript specific
-├── python/          # Python specific
-├── golang/          # Go specific
-├── swift/           # Swift specific
-└── php/             # PHP specific
+├── typescript/      # TypeScript/JavaScript 特定
+├── python/          # Python 特定
+├── golang/          # Go 特定
+├── swift/           # Swift 特定
+└── php/             # PHP 特定
 ```

 * **common/** 包含通用原则 —— 没有语言特定的代码示例。
--- a/docs/zh-CN/rules/common/coding-style.md
+++ b/docs/zh-CN/rules/common/coding-style.md
@@ -5,9 +5,9 @@
 始终创建新对象，绝不改变现有对象：

 ```
-// Pseudocode
-WRONG:  modify(original, field, value) → changes original in-place
-CORRECT: update(original, field, value) → returns new copy with change
+// 伪代码
+WRONG:  modify(original, field, value) → 原地修改 original
+CORRECT: update(original, field, value) → 返回包含更改的新副本
 ```

 理由：不可变数据可以防止隐藏的副作用，使调试更容易，并支持安全的并发。
--- a/docs/zh-CN/rules/java/testing.md
+++ b/docs/zh-CN/rules/java/testing.md
@@ -18,10 +18,10 @@ paths:

 ```
 src/test/java/com/example/app/
-  service/           # Unit tests for service layer
-  controller/        # Web layer / API tests
-  repository/        # Data access tests
-  integration/       # Cross-layer integration tests
+  service/           # 服务层单元测试
+  controller/        # Web 层/API 测试
+  repository/        # 数据访问测试
+  integration/       # 跨层集成测试
 ```

 在 `src/test/java` 中镜像 `src/main/java` 的包结构。
--- a/docs/zh-CN/rules/kotlin/testing.md
+++ b/docs/zh-CN/rules/kotlin/testing.md
@@ -120,10 +120,10 @@ fun `delete item emits updated list without deleted item`() = runTest { }

 ```
 src/
-├── commonTest/kotlin/     # Shared tests (ViewModel, UseCase, Repository)
-├── androidUnitTest/kotlin/ # Android unit tests (JUnit)
-├── androidInstrumentedTest/kotlin/  # Instrumented tests (Room, UI)
-└── iosTest/kotlin/        # iOS-specific tests
+├── commonTest/kotlin/     # 共享测试（ViewModel、UseCase、Repository）
+├── androidUnitTest/kotlin/ # Android 单元测试（JUnit）
+├── androidInstrumentedTest/kotlin/  # 仪器化测试（Room、UI）
+└── iosTest/kotlin/        # iOS 专用测试
 ```

 最低测试覆盖率：每个功能都需要覆盖 ViewModel + UseCase。
--- a/docs/zh-CN/rules/perl/coding-style.md
+++ b/docs/zh-CN/rules/perl/coding-style.md
@@ -28,10 +28,10 @@ paths:
 使用 **perltidy** 并采用以下设置：

 ```
-i=4    # 4-space indent
-l=100  # 100 char line length
-ce     # cuddled else
-bar    # opening brace always right
+-i=4    # 4 空格缩进
+-l=100  # 100 字符行宽
+-ce     # else 紧贴前括号
+-bar    # 左花括号始终在右侧
 ```

 ## 代码检查
--- a/docs/zh-CN/rules/rust/coding-style.md
+++ b/docs/zh-CN/rules/rust/coding-style.md
@@ -129,15 +129,15 @@ for user in &users {
 src/
 ├── main.rs
 ├── lib.rs
-├── auth/           # Domain module
+├── auth/           # 领域模块
 │   ├── mod.rs
 │   ├── token.rs
 │   └── middleware.rs
-├── orders/         # Domain module
+├── orders/         # 领域模块
 │   ├── mod.rs
 │   ├── model.rs
 │   └── service.rs
-└── db/             # Infrastructure
+└── db/             # 基础设施
    ├── mod.rs
    └── pool.rs
 ```
--- a/docs/zh-CN/rules/rust/testing.md
+++ b/docs/zh-CN/rules/rust/testing.md
@@ -20,17 +20,17 @@ paths:
 ```text
 my_crate/
 ├── src/
-│   ├── lib.rs           # Unit tests in #[cfg(test)] modules
+│   ├── lib.rs           # 位于 #[cfg(test)] 模块中的单元测试
 │   ├── auth/
 │   │   └── mod.rs       # #[cfg(test)] mod tests { ... }
 │   └── orders/
 │       └── service.rs   # #[cfg(test)] mod tests { ... }
-├── tests/               # Integration tests (each file = separate binary)
+├── tests/               # 集成测试（每个文件 = 独立的二进制文件）
 │   ├── api_test.rs
 │   ├── db_test.rs
-│   └── common/          # Shared test utilities
+│   └── common/          # 共享的测试工具
 │       └── mod.rs
-└── benches/             # Criterion benchmarks
+└── benches/             # Criterion 基准测试
    └── benchmark.rs
 ```

--- a/docs/zh-CN/skills/ai-regression-testing/SKILL.md
+++ b/docs/zh-CN/skills/ai-regression-testing/SKILL.md
@@ -21,25 +21,25 @@ origin: ECC
 当 AI 编写代码然后审查其自身工作时，它会将相同的假设带入这两个步骤。这会形成一个可预测的失败模式：

 ```
-AI writes fix → AI reviews fix → AI says "looks correct" → Bug still exists
+AI 编写修复 → AI 审查修复 → AI 表示“看起来正确” → 漏洞依然存在
 ```

 **实际示例**（在生产环境中观察到）：

 ```
-Fix 1: Added notification_settings to API response
-  → Forgot to add it to the SELECT query
-  → AI reviewed and missed it (same blind spot)
+修复 1：向 API 响应添加了 notification_settings
+  → 忘记将其添加到 SELECT 查询中
+  → AI 审核时遗漏了（相同的盲点）

-Fix 2: Added it to SELECT query
-  → TypeScript build error (column not in generated types)
-  → AI reviewed Fix 1 but didn't catch the SELECT issue
+修复 2：将其添加到 SELECT 查询中
+  → TypeScript 构建错误（列不在生成的类型中）
+  → AI 审核了修复 1，但未发现 SELECT 问题

-Fix 3: Changed to SELECT *
-  → Fixed production path, forgot sandbox path
-  → AI reviewed and missed it AGAIN (4th occurrence)
+修复 3：改为 SELECT *
+  → 修复了生产路径，忘记了沙箱路径
+  → AI 审核时再次遗漏（第 4 次出现）

-Fix 4: Test caught it instantly on first run ✅
+修复 4：测试在首次运行时立即捕获了问题 ✅
 ```

 模式：**沙盒/生产环境路径不一致**是 AI 引入的 #1 回归问题。
@@ -228,18 +228,18 @@ describe("GET /api/user/messages (conversation list)", () => {
 User: "バグチェックして" (or "/bug-check")
  │
  ├─ Step 1: npm run test
-  │   ├─ FAIL → Bug found mechanically (no AI judgment needed)
-  │   └─ PASS → Continue
+  │   ├─ FAIL → 发现机械性错误（无需AI判断）
+  │   └─ PASS → 继续
  │
  ├─ Step 2: npm run build
-  │   ├─ FAIL → Type error found mechanically
-  │   └─ PASS → Continue
+  │   ├─ FAIL → 发现类型错误
+  │   └─ PASS → 继续
  │
-  ├─ Step 3: AI code review (with known blind spots in mind)
-  │   └─ Findings reported
+  ├─ Step 3: AI代码审查（考虑已知盲点）
+  │   └─ 报告发现的问题
  │
-  └─ Step 4: For each fix, write a regression test
-      └─ Next bug-check catches if fix breaks
+  └─ Step 4: 对每个修复编写回归测试
+      └─ 下次bug-check时捕获修复是否破坏功能
 ```

 ## 常见的 AI 回归模式
@@ -345,10 +345,10 @@ const handleRemove = async (id: string) => {
 不要追求 100% 的覆盖率。相反：

 ```
-Bug found in /api/user/profile     → Write test for profile API
-Bug found in /api/user/messages    → Write test for messages API
-Bug found in /api/user/favorites   → Write test for favorites API
-No bug in /api/user/notifications  → Don't write test (yet)
+在 /api/user/profile 发现 bug → 为 profile API 编写测试
+在 /api/user/messages 发现 bug → 为 messages API 编写测试
+在 /api/user/favorites 发现 bug → 为 favorites API 编写测试
+在 /api/user/notifications 没有发现 bug → 暂时不编写测试
 ```

 **为什么这在 AI 开发中有效：**
--- a/docs/zh-CN/skills/android-clean-architecture/SKILL.md
+++ b/docs/zh-CN/skills/android-clean-architecture/SKILL.md
@@ -22,13 +22,13 @@ origin: ECC

 ```
 project/
-├── app/                  # Android entry point, DI wiring, Application class
-├── core/                 # Shared utilities, base classes, error types
-├── domain/               # UseCases, domain models, repository interfaces (pure Kotlin)
-├── data/                 # Repository implementations, DataSources, DB, network
-├── presentation/         # Screens, ViewModels, UI models, navigation
-├── design-system/        # Reusable Compose components, theme, typography
-└── feature/              # Feature modules (optional, for larger projects)
+├── app/                  # Android 入口点，DI 装配，Application 类
+├── core/                 # 共享工具类，基类，错误类型
+├── domain/               # 用例，领域模型，仓库接口（纯 Kotlin）
+├── data/                 # 仓库实现，数据源，数据库，网络
+├── presentation/         # 界面，ViewModel，UI 模型，导航
+├── design-system/        # 可复用的 Compose 组件，主题，排版
+└── feature/              # 功能模块（可选，用于大型项目）
    ├── auth/
    ├── settings/
    └── profile/
@@ -37,11 +37,11 @@ project/
 ### 依赖规则

 ```
-app → presentation, domain, data, core
-presentation → domain, design-system, core
-data → domain, core
-domain → core (or no dependencies)
-core → (nothing)
+app → presentation, domain, data, core  
+presentation → domain, design-system, core  
+data → domain, core  
+domain → core (或无依赖)  
+core → (无依赖)
 ```

 **关键**：`domain` 绝不能依赖 `data`、`presentation` 或任何框架。它仅包含纯 Kotlin 代码。
--- a/docs/zh-CN/skills/api-design/SKILL.md
+++ b/docs/zh-CN/skills/api-design/SKILL.md
@@ -22,7 +22,7 @@ origin: ECC
 ### URL 结构

 ```
-# Resources are nouns, plural, lowercase, kebab-case
+# 资源使用名词、复数、小写、短横线连接
 GET    /api/v1/users
 GET    /api/v1/users/:id
 POST   /api/v1/users
@@ -30,11 +30,11 @@ PUT    /api/v1/users/:id
 PATCH  /api/v1/users/:id
 DELETE /api/v1/users/:id

-# Sub-resources for relationships
+# 用于关系的子资源
 GET    /api/v1/users/:id/orders
 POST   /api/v1/users/:id/orders

-# Actions that don't map to CRUD (use verbs sparingly)
+# 非 CRUD 映射的操作（谨慎使用动词）
 POST   /api/v1/orders/:id/cancel
 POST   /api/v1/auth/login
 POST   /api/v1/auth/refresh
@@ -43,16 +43,16 @@ POST   /api/v1/auth/refresh
 ### 命名规则

 ```
-# GOOD
-/api/v1/team-members          # kebab-case for multi-word resources
-/api/v1/orders?status=active  # query params for filtering
-/api/v1/users/123/orders      # nested resources for ownership
+# 良好
+/api/v1/team-members          # 多单词资源使用 kebab-case
+/api/v1/orders?status=active  # 查询参数用于过滤
+/api/v1/users/123/orders      # 嵌套资源表示所有权关系

-# BAD
-/api/v1/getUsers              # verb in URL
-/api/v1/user                  # singular (use plural)
-/api/v1/team_members          # snake_case in URLs
-/api/v1/users/123/getOrders   # verb in nested resource
+# 不良
+/api/v1/getUsers              # URL 中包含动词
+/api/v1/user                  # 使用单数形式（应使用复数）
+/api/v1/team_members          # URL 中使用 snake_case
+/api/v1/users/123/getOrders   # 嵌套资源路径中包含动词
 ```

 ## HTTP 方法和状态码
@@ -72,41 +72,41 @@ POST   /api/v1/auth/refresh
 ### 状态码参考

 ```
-# Success
-200 OK                    — GET, PUT, PATCH (with response body)
-201 Created               — POST (include Location header)
-204 No Content            — DELETE, PUT (no response body)
+# 成功
+200 OK                    — GET、PUT、PATCH（包含响应体）
+201 Created               — POST（包含 Location 头部）
+204 No Content            — DELETE、PUT（无响应体）

-# Client Errors
-400 Bad Request           — Validation failure, malformed JSON
-401 Unauthorized          — Missing or invalid authentication
-403 Forbidden             — Authenticated but not authorized
-404 Not Found             — Resource doesn't exist
-409 Conflict              — Duplicate entry, state conflict
-422 Unprocessable Entity  — Semantically invalid (valid JSON, bad data)
-429 Too Many Requests     — Rate limit exceeded
+# 客户端错误
+400 Bad Request           — 验证失败、JSON 格式错误
+401 Unauthorized          — 缺少或无效的身份验证
+403 Forbidden             — 已认证但未授权
+404 Not Found             — 资源不存在
+409 Conflict              — 重复条目、状态冲突
+422 Unprocessable Entity  — 语义无效（JSON 格式正确但数据错误）
+429 Too Many Requests     — 超出速率限制

-# Server Errors
-500 Internal Server Error — Unexpected failure (never expose details)
-502 Bad Gateway           — Upstream service failed
-503 Service Unavailable   — Temporary overload, include Retry-After
+# 服务器错误
+500 Internal Server Error — 意外故障（切勿暴露细节）
+502 Bad Gateway           — 上游服务失败
+503 Service Unavailable   — 临时过载，需包含 Retry-After 头部
 ```

 ### 常见错误

 ```
-# BAD: 200 for everything
+# 错误：对所有请求都返回 200
 { "status": 200, "success": false, "error": "Not found" }

-# GOOD: Use HTTP status codes semantically
+# 正确：按语义使用 HTTP 状态码
 HTTP/1.1 404 Not Found
 { "error": { "code": "not_found", "message": "User not found" } }

-# BAD: 500 for validation errors
-# GOOD: 400 or 422 with field-level details
+# 错误：验证错误返回 500
+# 正确：返回 400 或 422 并包含字段级详情

-# BAD: 200 for created resources
-# GOOD: 201 with Location header
+# 错误：创建资源返回 200
+# 正确：返回 201 并包含 Location 标头
 HTTP/1.1 201 Created
 Location: /api/v1/users/abc-123
 ```
@@ -202,7 +202,7 @@ interface ApiError {
 ```
 GET /api/v1/users?page=2&per_page=20

-# Implementation
+# 实现
 SELECT * FROM users
 ORDER BY created_at DESC
 LIMIT 20 OFFSET 20;
@@ -216,11 +216,11 @@ LIMIT 20 OFFSET 20;
 ```
 GET /api/v1/users?cursor=eyJpZCI6MTIzfQ&limit=20

-# Implementation
+# 实现
 SELECT * FROM users
 WHERE id > :cursor_id
 ORDER BY id ASC
-LIMIT 21;  -- fetch one extra to determine has_next
+LIMIT 21;  -- 多取一条以判断是否有下一页
 ```

 ```json
@@ -250,44 +250,44 @@ LIMIT 21;  -- fetch one extra to determine has_next
 ### 过滤

 ```
-# Simple equality
+# 简单相等
 GET /api/v1/orders?status=active&customer_id=abc-123

-# Comparison operators (use bracket notation)
+# 比较运算符（使用括号表示法）
 GET /api/v1/products?price[gte]=10&price[lte]=100
 GET /api/v1/orders?created_at[after]=2025-01-01

-# Multiple values (comma-separated)
+# 多个值（逗号分隔）
 GET /api/v1/products?category=electronics,clothing

-# Nested fields (dot notation)
+# 嵌套字段（点表示法）
 GET /api/v1/orders?customer.country=US
 ```

 ### 排序

 ```
-# Single field (prefix - for descending)
+# 单字段排序（前缀 - 表示降序）
 GET /api/v1/products?sort=-created_at

-# Multiple fields (comma-separated)
+# 多字段排序（逗号分隔）
 GET /api/v1/products?sort=-featured,price,-created_at
 ```

 ### 全文搜索

 ```
-# Search query parameter
+# 搜索查询参数
 GET /api/v1/products?q=wireless+headphones

-# Field-specific search
+# 字段特定搜索
 GET /api/v1/users?email=alice
 ```

 ### 稀疏字段集

 ```
-# Return only specified fields (reduces payload)
+# 仅返回指定字段（减少负载）
 GET /api/v1/users?fields=id,name,email
 GET /api/v1/orders?fields=id,total,status&include=customer.name
 ```
@@ -334,7 +334,7 @@ X-RateLimit-Limit: 100
 X-RateLimit-Remaining: 95
 X-RateLimit-Reset: 1640000000

-# When exceeded
+# 超出限制时
 HTTP/1.1 429 Too Many Requests
 Retry-After: 60
 {
@@ -379,21 +379,21 @@ Accept: application/vnd.myapp.v2+json
 ### 版本控制策略

 ```
-1. Start with /api/v1/ — don't version until you need to
-2. Maintain at most 2 active versions (current + previous)
-3. Deprecation timeline:
-   - Announce deprecation (6 months notice for public APIs)
-   - Add Sunset header: Sunset: Sat, 01 Jan 2026 00:00:00 GMT
-   - Return 410 Gone after sunset date
-4. Non-breaking changes don't need a new version:
-   - Adding new fields to responses
-   - Adding new optional query parameters
-   - Adding new endpoints
-5. Breaking changes require a new version:
-   - Removing or renaming fields
-   - Changing field types
-   - Changing URL structure
-   - Changing authentication method
+1. 从 /api/v1/ 开始 —— 除非必要，否则不要急于版本化
+2. 最多同时维护 2 个活跃版本（当前版本 + 前一个版本）
+3. 弃用时间线：
+   - 宣布弃用（公共 API 需提前 6 个月通知）
+   - 添加 Sunset 响应头：Sunset: Sat, 01 Jan 2026 00:00:00 GMT
+   - 在弃用日期后返回 410 Gone 状态
+4. 非破坏性变更无需创建新版本：
+   - 向响应中添加新字段
+   - 添加新的可选查询参数
+   - 添加新的端点
+5. 破坏性变更需要创建新版本：
+   - 移除或重命名字段
+   - 更改字段类型
+   - 更改 URL 结构
+   - 更改身份验证方法
 ```

 ## 实现模式
--- a/docs/zh-CN/skills/architecture-decision-records/SKILL.md
+++ b/docs/zh-CN/skills/architecture-decision-records/SKILL.md
@@ -96,11 +96,11 @@ origin: ECC
 ```
 docs/
 └── adr/
-    ├── README.md              ← index of all ADRs
+    ├── README.md              ← 所有 ADR 的索引
    ├── 0001-use-nextjs.md
    ├── 0002-postgres-over-mongo.md
    ├── 0003-rest-over-graphql.md
-    └── template.md            ← blank template for manual use
+    └── template.md            ← 供手动使用的空白模板
 ```

 ### ADR 索引格式
--- a/docs/zh-CN/skills/autonomous-loops/SKILL.md
+++ b/docs/zh-CN/skills/autonomous-loops/SKILL.md
@@ -147,13 +147,13 @@ CLAW_SESSION=my-project CLAW_SKILLS=tdd-workflow,security-review node scripts/cl
 ### 架构：双提示系统

 ```
-PROMPT 1 (Orchestrator)              PROMPT 2 (Sub-Agents)
+PROMPT 1（协调器）              PROMPT 2（子代理）
 ┌─────────────────────┐             ┌──────────────────────┐
-│ Parse spec file      │             │ Receive full context  │
-│ Scan output dir      │  deploys   │ Read assigned number  │
-│ Plan iteration       │────────────│ Follow spec exactly   │
-│ Assign creative dirs │  N agents  │ Generate unique output │
-│ Manage waves         │             │ Save to output dir    │
+│ 解析规范文件         │             │ 接收完整上下文        │
+│ 扫描输出目录         │  部署       │ 读取分配编号          │
+│ 规划迭代             │────────────│ 严格遵循规范          │
+│ 分配创作目录         │  N个代理    │ 生成唯一输出          │
+│ 管理批次             │             │ 保存至输出目录        │
 └─────────────────────┘             └──────────────────────┘
 ```

@@ -218,20 +218,20 @@ PROMPT 1 (Orchestrator)              PROMPT 2 (Sub-Agents)

 ```
 ┌─────────────────────────────────────────────────────┐
-│  CONTINUOUS CLAUDE ITERATION                        │
+│  持续 CLAUDE 迭代                                   │
 │                                                     │
-│  1. Create branch (continuous-claude/iteration-N)   │
-│  2. Run claude -p with enhanced prompt              │
-│  3. (Optional) Reviewer pass — separate claude -p   │
-│  4. Commit changes (claude generates message)       │
-│  5. Push + create PR (gh pr create)                 │
-│  6. Wait for CI checks (poll gh pr checks)          │
-│  7. CI failure? → Auto-fix pass (claude -p)         │
-│  8. Merge PR (squash/merge/rebase)                  │
-│  9. Return to main → repeat                         │
+│  1. 创建分支 (continuous-claude/iteration-N)       │
+│  2. 使用增强提示运行 claude -p                      │
+│  3. (可选) 审查者通过 — 单独的 claude -p            │
+│  4. 提交更改 (claude 生成提交信息)                  │
+│  5. 推送 + 创建 PR (gh pr create)                   │
+│  6. 等待 CI 检查 (轮询 gh pr checks)                │
+│  7. CI 失败？ → 自动修复通过 (claude -p)             │
+│  8. 合并 PR (squash/merge/rebase)                   │
+│  9. 返回 main → 重复                                │
 │                                                     │
-│  Limit by: --max-runs N | --max-cost $X             │
-│            --max-duration 2h | completion signal     │
+│  限制条件： --max-runs N | --max-cost $X            │
+│            --max-duration 2h | 完成信号             │
 └─────────────────────────────────────────────────────┘
 ```

@@ -390,27 +390,27 @@ done
 ### 架构概述

 ```
-RFC/PRD Document
+RFC/PRD 文档
       │
       ▼
-  DECOMPOSITION (AI)
-  Break RFC into work units with dependency DAG
+  分解（AI）
+  将 RFC 分解为具有依赖关系 DAG 的工作单元
       │
       ▼
 ┌──────────────────────────────────────────────────────┐
-│  RALPH LOOP (up to 3 passes)                         │
+│  RALPH 循环（最多 3 轮）                             │
 │                                                      │
-│  For each DAG layer (sequential, by dependency):     │
+│  针对每个 DAG 层级（按依赖关系顺序）：                 │
 │                                                      │
-│  ┌── Quality Pipelines (parallel per unit) ───────┐  │
-│  │  Each unit in its own worktree:                │  │
-│  │  Research → Plan → Implement → Test → Review   │  │
-│  │  (depth varies by complexity tier)             │  │
+│  ┌── 质量流水线（每个单元并行） ───────┐              │
+│  │  每个单元在其独立的工作树中：        │              │
+│  │  研究 → 规划 → 实现 → 测试 → 评审   │              │
+│  │  （深度根据复杂度层级变化）          │              │
 │  └────────────────────────────────────────────────┘  │
 │                                                      │
-│  ┌── Merge Queue ─────────────────────────────────┐  │
-│  │  Rebase onto main → Run tests → Land or evict │  │
-│  │  Evicted units re-enter with conflict context  │  │
+│  ┌── 合并队列 ─────────────────────────────────┐     │
+│  │  变基到主分支 → 运行测试 → 合并或移除       │     │
+│  │  被移除的单元携带冲突上下文重新进入         │     │
 │  └────────────────────────────────────────────────┘  │
 │                                                      │
 └──────────────────────────────────────────────────────┘
@@ -442,9 +442,9 @@ interface WorkUnit {
 依赖关系 DAG 决定了执行顺序：

 ```
-Layer 0: [unit-a, unit-b]     ← no deps, run in parallel
-Layer 1: [unit-c]             ← depends on unit-a
-Layer 2: [unit-d, unit-e]     ← depend on unit-c
+Layer 0: [unit-a, unit-b]     ← 无依赖，并行运行
+Layer 1: [unit-c]             ← 依赖于 unit-a
+Layer 2: [unit-d, unit-e]     ← 依赖于 unit-c
 ```

 ### 复杂度层级
@@ -484,13 +484,13 @@ Layer 2: [unit-d, unit-e]     ← depend on unit-c
 ```
 Unit branch
    │
-    ├─ Rebase onto main
-    │   └─ Conflict? → EVICT (capture conflict context)
+    ├─ 变基到 main 分支
+    │   └─ 冲突？→ 移除（捕获冲突上下文）
    │
-    ├─ Run build + tests
-    │   └─ Fail? → EVICT (capture test output)
+    ├─ 运行构建 + 测试
+    │   └─ 失败？→ 移除（捕获测试输出）
    │
-    └─ Pass → Fast-forward main, push, delete branch
+    └─ 通过 → 快进合并 main 分支，推送，删除分支
 ```

 **文件重叠智能：**
@@ -513,13 +513,13 @@ Unit branch
 ### 阶段间的数据流

 ```
-research.contextFilePath ──────────────────→ plan
-plan.implementationSteps ──────────────────→ implement
-implement.{filesCreated, whatWasDone} ─────→ test, reviews
-test.failingSummary ───────────────────────→ reviews, implement (next pass)
-reviews.{feedback, issues} ────────────────→ review-fix → implement (next pass)
-final-review.reasoning ────────────────────→ implement (next pass)
-evictionContext ───────────────────────────→ implement (after merge conflict)
+research.contextFilePath ──────────────────→ 方案
+plan.implementationSteps ──────────────────→ 实施
+implement.{filesCreated, whatWasDone} ─────→ 测试, 审查
+test.failingSummary ───────────────────────→ 审查, 实施（下一轮）
+reviews.{feedback, issues} ────────────────→ 审查修复 → 实施（下一轮）
+final-review.reasoning ────────────────────→ 实施（下一轮）
+evictionContext ───────────────────────────→ 实施（合并冲突后）
 ```

 ### 工作树隔离
@@ -560,15 +560,15 @@ evictionContext ─────────────────────
 ### 决策矩阵

 ```
-Is the task a single focused change?
-├─ Yes → Sequential Pipeline or NanoClaw
-└─ No → Is there a written spec/RFC?
-         ├─ Yes → Do you need parallel implementation?
-         │        ├─ Yes → Ralphinho (DAG orchestration)
-         │        └─ No → Continuous Claude (iterative PR loop)
-         └─ No → Do you need many variations of the same thing?
-                  ├─ Yes → Infinite Agentic Loop (spec-driven generation)
-                  └─ No → Sequential Pipeline with de-sloppify
+该任务是否是一个单一的、专注的变更？
+├─ 是 → 顺序管道或NanoClaw
+└─ 否 → 是否有书面的规范/RFC？
+         ├─ 有 → 是否需要并行实现？
+         │        ├─ 是 → Ralphinho（DAG编排）
+         │        └─ 否 → Continuous Claude（迭代式PR循环）
+         └─ 否 → 是否需要同一事物的多种变体？
+                  ├─ 是 → 无限代理循环（规范驱动生成）
+                  └─ 否 → 顺序管道与去杂乱化
 ```

 ### 模式组合
--- a/docs/zh-CN/skills/blueprint/SKILL.md
+++ b/docs/zh-CN/skills/blueprint/SKILL.md
@@ -33,7 +33,7 @@ Blueprint 自动检测 git/gh 可用性。如果具备 git + GitHub CLI，它会
 ### 基本用法

 ```
-/blueprint myapp "migrate database to PostgreSQL"
+/blueprint myapp "将数据库迁移到PostgreSQL"
 ```

 生成 `plans/myapp-migrate-database-to-postgresql.md`，包含类似以下的步骤：
@@ -47,7 +47,7 @@ Blueprint 自动检测 git/gh 可用性。如果具备 git + GitHub CLI，它会
 ### 多代理项目

 ```
-/blueprint chatbot "extract LLM providers into a plugin system"
+/blueprint chatbot "将LLM提供商提取到插件系统中"
 ```

 生成一个尽可能包含并行步骤的计划（例如，在插件接口步骤完成后，“实现 Anthropic 插件”和“实现 OpenAI 插件”可以并行运行），分配模型层级（接口设计步骤使用最强模型，实现步骤使用默认模型），并在每个步骤后验证不变量（例如“所有现有测试通过”、“核心模块无提供商导入”）。
--- a/docs/zh-CN/skills/claude-devfleet/SKILL.md
+++ b/docs/zh-CN/skills/claude-devfleet/SKILL.md
@@ -19,21 +19,21 @@ claude mcp add devfleet --transport http http://localhost:18801/mcp
 ## 工作原理

 ```
-User → "Build a REST API with auth and tests"
+用户 → "构建一个带有身份验证和测试的 REST API"
  ↓
-plan_project(prompt) → project_id + mission DAG
+plan_project(prompt) → 项目ID + 任务DAG
  ↓
-Show plan to user → get approval
+向用户展示计划 → 获取批准
  ↓
-dispatch_mission(M1) → Agent 1 spawns in worktree
+dispatch_mission(M1) → 代理1在工作树中生成
  ↓
-M1 completes → auto-merge → auto-dispatch M2 (depends_on M1)
+M1完成 → 自动合并 → 自动分发M2 (依赖于M1)
  ↓
-M2 completes → auto-merge
+M2完成 → 自动合并
  ↓
-get_report(M2) → files_changed, what_done, errors, next_steps
+get_report(M2) → 更改的文件、完成的工作、错误、后续步骤
  ↓
-Report back to user
+向用户报告
 ```

 ### 工具
--- a/docs/zh-CN/skills/codebase-onboarding/SKILL.md
+++ b/docs/zh-CN/skills/codebase-onboarding/SKILL.md
@@ -23,28 +23,28 @@ origin: ECC
 在不阅读每个文件的情况下，收集关于项目的原始信息。并行运行以下检查：

 ```
-1. Package manifest detection
-   → package.json, go.mod, Cargo.toml, pyproject.toml, pom.xml, build.gradle,
-     Gemfile, composer.json, mix.exs, pubspec.yaml
+1. 包清单检测
+   → package.json、go.mod、Cargo.toml、pyproject.toml、pom.xml、build.gradle、
+     Gemfile、composer.json、mix.exs、pubspec.yaml

-2. Framework fingerprinting
-   → next.config.*, nuxt.config.*, angular.json, vite.config.*,
-     django settings, flask app factory, fastapi main, rails config
+2. 框架指纹识别
+   → next.config.*、nuxt.config.*、angular.json、vite.config.*、
+     django 设置、flask 应用工厂、fastapi 主程序、rails 配置

-3. Entry point identification
-   → main.*, index.*, app.*, server.*, cmd/, src/main/
+3. 入口点识别
+   → main.*、index.*、app.*、server.*、cmd/、src/main/

-4. Directory structure snapshot
-   → Top 2 levels of the directory tree, ignoring node_modules, vendor,
-     .git, dist, build, __pycache__, .next
+4. 目录结构快照
+   → 目录树的前 2 层，忽略 node_modules、vendor、
+     .git、dist、build、__pycache__、.next

-5. Config and tooling detection
-   → .eslintrc*, .prettierrc*, tsconfig.json, Makefile, Dockerfile,
-     docker-compose*, .github/workflows/, .env.example, CI configs
+5. 配置与工具检测
+   → .eslintrc*、.prettierrc*、tsconfig.json、Makefile、Dockerfile、
+     docker-compose*、.github/workflows/、.env.example、CI 配置

-6. Test structure detection
-   → tests/, test/, __tests__/, *_test.go, *.spec.ts, *.test.js,
-     pytest.ini, jest.config.*, vitest.config.*
+6. 测试结构检测
+   → tests/、test/、__tests__/、*_test.go、*.spec.ts、*.test.js、
+     pytest.ini、jest.config.*、vitest.config.*
 ```

 ### 阶段 2：架构映射
@@ -71,12 +71,12 @@ origin: ECC
 <!-- Example for a React project — replace with detected directories -->

 ```
-src/components/  → React UI components
-src/api/         → API route handlers
-src/lib/         → Shared utilities
-src/db/          → Database models and migrations
-tests/           → Test suites
-scripts/         → Build and deployment scripts
+src/components/  → React UI 组件
+src/api/         → API 路由处理程序
+src/lib/         → 共享工具库
+src/db/          → 数据库模型和迁移文件
+tests/           → 测试套件
+scripts/         → 构建和部署脚本
 ```

 **数据流**
--- a/docs/zh-CN/skills/coding-standards/SKILL.md
+++ b/docs/zh-CN/skills/coding-standards/SKILL.md
@@ -244,14 +244,14 @@ setCount(count + 1)  // Can be stale in async scenarios
 ### REST API 约定

 ```
-GET    /api/markets              # List all markets
-GET    /api/markets/:id          # Get specific market
-POST   /api/markets              # Create new market
-PUT    /api/markets/:id          # Update market (full)
-PATCH  /api/markets/:id          # Update market (partial)
-DELETE /api/markets/:id          # Delete market
+GET    /api/markets              # 列出所有市场
+GET    /api/markets/:id          # 获取特定市场
+POST   /api/markets              # 创建新市场
+PUT    /api/markets/:id          # 更新市场（完整）
+PATCH  /api/markets/:id          # 更新市场（部分）
+DELETE /api/markets/:id          # 删除市场

-# Query parameters for filtering
+# 用于筛选的查询参数
 GET /api/markets?status=active&limit=10&offset=0
 ```

@@ -341,10 +341,10 @@ src/
 ### 文件命名

 ```
-components/Button.tsx          # PascalCase for components
-hooks/useAuth.ts              # camelCase with 'use' prefix
-lib/formatDate.ts             # camelCase for utilities
-types/market.types.ts         # camelCase with .types suffix
+components/Button.tsx          # 组件使用帕斯卡命名法
+hooks/useAuth.ts              # 使用 'use' 前缀的驼峰命名法
+lib/formatDate.ts             # 工具函数使用驼峰命名法
+types/market.types.ts         # 使用 .types 后缀的驼峰命名法
 ```

 ## 注释与文档
--- a/docs/zh-CN/skills/configure-ecc/SKILL.md
+++ b/docs/zh-CN/skills/configure-ecc/SKILL.md
@@ -44,11 +44,11 @@ git clone https://github.com/affaan-m/everything-claude-code.git /tmp/everything
 使用 `AskUserQuestion` 询问用户安装位置：

 ```
-Question: "Where should ECC components be installed?"
-Options:
-  - "User-level (~/.claude/)" — "Applies to all your Claude Code projects"
-  - "Project-level (.claude/)" — "Applies only to the current project"
-  - "Both" — "Common/shared items user-level, project-specific items project-level"
+问题："ECC组件应安装在哪里？"
+选项：
+  - "用户级别 (~/.claude/)" — "适用于您所有的Claude Code项目"
+  - "项目级别 (.claude/)" — "仅适用于当前项目"
+  - "两者" — "通用/共享项在用户级别，项目特定项在项目级别"
 ```

 将选择存储为 `INSTALL_LEVEL`。设置目标目录：
@@ -74,12 +74,12 @@ mkdir -p $TARGET/skills $TARGET/rules
 使用 `AskUserQuestion`（单选）：

 ```
-Question: "Install core skills only, or include niche/framework packs?"
-Options:
-  - "Core only (recommended)" — "tdd, e2e, evals, verification, research-first, security, frontend patterns, compacting, cross-functional Anthropic skills"
-  - "Core + selected niche" — "Add framework/domain-specific skills after core"
-  - "Niche only" — "Skip core, install specific framework/domain skills"
-Default: Core only
+问题："只安装核心技能，还是包含小众/框架包？"
+选项：
+  - "仅核心（推荐）" — "tdd, e2e, evals, verification, research-first, security, frontend patterns, compacting, cross-functional Anthropic skills"
+  - "核心 + 精选小众" — "在核心基础上添加框架/领域特定技能"
+  - "仅小众" — "跳过核心，安装特定框架/领域技能"
+默认：仅核心
 ```

 如果用户选择细分领域或核心 + 细分领域，则继续下面的类别选择，并且仅包含他们选择的那些细分领域技能。
@@ -89,16 +89,16 @@ Default: Core only
 下方有7个可选的类别组。后续的详细确认列表涵盖了8个类别中的45项技能，外加1个独立模板。使用 `AskUserQuestion` 与 `multiSelect: true`：

 ```
-Question: "Which skill categories do you want to install?"
-Options:
-  - "Framework & Language" — "Django, Laravel, Spring Boot, Go, Python, Java, Frontend, Backend patterns"
-  - "Database" — "PostgreSQL, ClickHouse, JPA/Hibernate patterns"
-  - "Workflow & Quality" — "TDD, verification, learning, security review, compaction"
-  - "Research & APIs" — "Deep research, Exa search, Claude API patterns"
-  - "Social & Content Distribution" — "X/Twitter API, crossposting alongside content-engine"
-  - "Media Generation" — "fal.ai image/video/audio alongside VideoDB"
-  - "Orchestration" — "dmux multi-agent workflows"
-  - "All skills" — "Install every available skill"
+问题：“您希望安装哪些技能类别？”
+选项：
+  - “框架与语言” — “Django, Laravel, Spring Boot, Go, Python, Java, 前端, 后端模式”
+  - “数据库” — “PostgreSQL, ClickHouse, JPA/Hibernate 模式”
+  - “工作流与质量” — “TDD, 验证, 学习, 安全审查, 压缩”
+  - “研究与 API” — “深度研究, Exa 搜索, Claude API 模式”
+  - “社交与内容分发” — “X/Twitter API, 内容引擎并行交叉发布”
+  - “媒体生成” — “fal.ai 图像/视频/音频与 VideoDB 并行”
+  - “编排” — “dmux 多智能体工作流”
+  - “所有技能” — “安装所有可用技能”
 ```

 ### 2c: 确认个人技能
@@ -213,12 +213,12 @@ cp -r $ECC_ROOT/skills/<skill-name> $TARGET/skills/
 使用 `AskUserQuestion` 和 `multiSelect: true`：

 ```
-Question: "Which rule sets do you want to install?"
-Options:
-  - "Common rules (Recommended)" — "Language-agnostic principles: coding style, git workflow, testing, security, etc. (8 files)"
-  - "TypeScript/JavaScript" — "TS/JS patterns, hooks, testing with Playwright (5 files)"
-  - "Python" — "Python patterns, pytest, black/ruff formatting (5 files)"
-  - "Go" — "Go patterns, table-driven tests, gofmt/staticcheck (5 files)"
+问题："您希望安装哪些规则集？"
+选项：
+  - "通用规则（推荐）" — "语言无关原则：编码风格、Git工作流、测试、安全等（8个文件）"
+  - "TypeScript/JavaScript" — "TS/JS模式、钩子、Playwright测试（5个文件）"
+  - "Python" — "Python模式、pytest、black/ruff格式化（5个文件）"
+  - "Go" — "Go模式、表驱动测试、gofmt/staticcheck（5个文件）"
 ```

 执行安装：
@@ -300,12 +300,12 @@ grep -rn "skills/" $TARGET/skills/
 使用 `AskUserQuestion`：

 ```
-Question: "Would you like to optimize the installed files for your project?"
-Options:
-  - "Optimize skills" — "Remove irrelevant sections, adjust paths, tailor to your tech stack"
-  - "Optimize rules" — "Adjust coverage targets, add project-specific patterns, customize tool configs"
-  - "Optimize both" — "Full optimization of all installed files"
-  - "Skip" — "Keep everything as-is"
+问题："您想要优化项目中的已安装文件吗？"
+选项：
+  - "优化技能" — "移除无关部分，调整路径，适配您的技术栈"
+  - "优化规则" — "调整覆盖目标，添加项目特定模式，自定义工具配置"
+  - "两者都优化" — "对所有已安装文件进行全面优化"
+  - "跳过" — "保持原样不变"
 ```

 ### 如果优化技能：
@@ -341,26 +341,26 @@ rm -rf /tmp/everything-claude-code
 然后打印摘要报告：

 ```
-## ECC Installation Complete
+## ECC 安装完成

-### Installation Target
- Level: [user-level / project-level / both]
- Path: [target path]
+### 安装目标
+- 级别：[用户级别 / 项目级别 / 两者]
+- 路径：[目标路径]

-### Skills Installed ([count])
- skill-1, skill-2, skill-3, ...
+### 已安装技能 ([数量])
+- 技能-1, 技能-2, 技能-3, ...

-### Rules Installed ([count])
- common (8 files)
- typescript (5 files)
+### 已安装规则 ([数量])
+- 通用规则 (8 个文件)
+- TypeScript 规则 (5 个文件)
 - ...

-### Verification Results
- [count] issues found, [count] fixed
- [list any remaining issues]
+### 验证结果
+- 发现 [数量] 个问题，已修复 [数量] 个
+- [列出任何剩余问题]

-### Optimizations Applied
- [list changes made, or "None"]
+### 已应用的优化
+- [列出所做的更改，或 "无"]
 ```

 ***
--- a/docs/zh-CN/skills/context-budget/SKILL.md
+++ b/docs/zh-CN/skills/context-budget/SKILL.md
@@ -76,16 +76,16 @@ origin: ECC
 生成上下文预算报告：

 ```
-Context Budget Report
+上下文预算报告
 ═══════════════════════════════════════

-Total estimated overhead: ~XX,XXX tokens
-Context model: Claude Sonnet (200K window)
-Effective available context: ~XXX,XXX tokens (XX%)
+总预估开销：约 XX,XXX 个词元
+上下文模型：Claude Sonnet (200K 窗口)
+有效可用上下文：约 XXX,XXX 个词元 (XX%)

-Component Breakdown:
+组件细分：
 ┌─────────────────┬────────┬───────────┐
-│ Component       │ Count  │ Tokens    │
+│ 组件            │ 数量   │ 词元数    │
 ├─────────────────┼────────┼───────────┤
 │ Agents          │ N      │ ~X,XXX    │
 │ Skills          │ N      │ ~X,XXX    │
@@ -94,15 +94,15 @@ Component Breakdown:
 │ CLAUDE.md       │ N      │ ~X,XXX    │
 └─────────────────┴────────┴───────────┘

-⚠ Issues Found (N):
-[ranked by token savings]
+⚠ 发现的问题 (N)：
+[按可节省词元数排序]

-Top 3 Optimizations:
-1. [action] → save ~X,XXX tokens
-2. [action] → save ~X,XXX tokens
-3. [action] → save ~X,XXX tokens
+前 3 项优化建议：
+1. [action] → 节省约 X,XXX 个词元
+2. [action] → 节省约 X,XXX 个词元
+3. [action] → 节省约 X,XXX 个词元

-Potential savings: ~XX,XXX tokens (XX% of current overhead)
+潜在节省空间：约 XX,XXX 个词元 (占当前开销的 XX%)
 ```

 在详细模式下，额外输出每个文件的令牌计数、最繁重文件的行级细分、重叠组件之间的具体冗余行，以及 MCP 工具列表和每个工具模式大小的估算。
@@ -112,26 +112,26 @@ Potential savings: ~XX,XXX tokens (XX% of current overhead)
 **基本审计**

 ```
-User: /context-budget
-Skill: Scans setup → 16 agents (12,400 tokens), 28 skills (6,200), 87 MCP tools (43,500), 2 CLAUDE.md (1,200)
-       Flags: 3 heavy agents, 14 MCP servers (3 CLI-replaceable)
-       Top saving: remove 3 MCP servers → -27,500 tokens (47% overhead reduction)
+/context-budget
+技能：扫描设置 → 16个代理（12,400个令牌），28个技能（6,200），87个MCP工具（43,500），2个CLAUDE.md（1,200）
+       标记：3个重型代理，14个MCP服务器（3个可替换为CLI）
+       最高节省：移除3个MCP服务器 → -27,500个令牌（减少47%开销）
 ```

 **详细模式**

 ```
-User: /context-budget --verbose
-Skill: Full report + per-file breakdown showing planner.md (213 lines, 1,840 tokens),
-       MCP tool list with per-tool sizes, duplicated rule lines side by side
+/context-budget --verbose
+技能：完整报告 + 按文件细目显示 planner.md（213 行，1,840 个令牌），
+       MCP 工具列表及每个工具的大小，重复规则行并排显示
 ```

 **扩容前检查**

 ```
-User: I want to add 5 more MCP servers, do I have room?
-Skill: Current overhead 33% → adding 5 servers (~50 tools) would add ~25,000 tokens → pushes to 45% overhead
-       Recommendation: remove 2 CLI-replaceable servers first to stay under 40%
+User: 我想再添加5个MCP服务器，有空间吗？
+Skill: 当前开销33% → 添加5个服务器（约50个工具）会增加约25,000个tokens → 开销将升至45%
+       建议：先移除2个可用CLI替代的服务器以保持在40%以下
 ```

 ## 最佳实践
--- a/docs/zh-CN/skills/continuous-agent-loop/SKILL.md
+++ b/docs/zh-CN/skills/continuous-agent-loop/SKILL.md
@@ -13,11 +13,11 @@ origin: ECC
 ```text
 Start
  |
-  +-- Need strict CI/PR control? -- yes --> continuous-pr
+  +-- 需要严格的 CI/PR 控制？ -- yes --> continuous-pr
  |                                    
-  +-- Need RFC decomposition? -- yes --> rfc-dag
+  +-- 需要 RFC 分解？ -- yes --> rfc-dag
  |
-  +-- Need exploratory parallel generation? -- yes --> infinite
+  +-- 需要探索性并行生成？ -- yes --> infinite
  |
  +-- default --> sequential
 ```
--- a/docs/zh-CN/skills/continuous-learning-v2/SKILL.md
+++ b/docs/zh-CN/skills/continuous-learning-v2/SKILL.md
@@ -82,43 +82,43 @@ Use functional patterns over classes when appropriate.
 ## 工作原理

 ```
-Session Activity (in a git repo)
+会话活动（在 git 仓库中）
      |
-      | Hooks capture prompts + tool use (100% reliable)
-      | + detect project context (git remote / repo path)
+      | 钩子捕获提示 + 工具使用（100% 可靠）
+      | + 检测项目上下文（git remote / 仓库路径）
      v
 +---------------------------------------------+
 |  projects/<project-hash>/observations.jsonl  |
-|   (prompts, tool calls, outcomes, project)   |
+|   （提示、工具调用、结果、项目）               |
 +---------------------------------------------+
      |
-      | Observer agent reads (background, Haiku)
+      | 观察者代理读取（后台，Haiku）
      v
 +---------------------------------------------+
-|          PATTERN DETECTION                   |
-|   * User corrections -> instinct             |
-|   * Error resolutions -> instinct            |
-|   * Repeated workflows -> instinct           |
-|   * Scope decision: project or global?       |
+|          模式检测                            |
+|   * 用户修正 -> 直觉                          |
+|   * 错误解决 -> 直觉                          |
+|   * 重复工作流 -> 直觉                        |
+|   * 范围决策：项目级或全局？                   |
 +---------------------------------------------+
      |
-      | Creates/updates
+      | 创建/更新
      v
 +---------------------------------------------+
 |  projects/<project-hash>/instincts/personal/ |
-|   * prefer-functional.yaml (0.7) [project]   |
-|   * use-react-hooks.yaml (0.9) [project]     |
+|   * prefer-functional.yaml (0.7) [项目]      |
+|   * use-react-hooks.yaml (0.9) [项目]        |
 +---------------------------------------------+
-|  instincts/personal/  (GLOBAL)               |
-|   * always-validate-input.yaml (0.85) [global]|
-|   * grep-before-edit.yaml (0.6) [global]     |
+|  instincts/personal/  （全局）                |
+|   * always-validate-input.yaml (0.85) [全局] |
+|   * grep-before-edit.yaml (0.6) [全局]       |
 +---------------------------------------------+
      |
-      | /evolve clusters + /promote
+      | /evolve 聚类 + /promote
      v
 +---------------------------------------------+
-|  projects/<hash>/evolved/ (project-scoped)   |
-|  evolved/ (global)                           |
+|  projects/<hash>/evolved/ （项目范围）        |
+|  evolved/ （全局）                            |
 |   * commands/new-feature.md                  |
 |   * skills/testing-workflow.md               |
 |   * agents/refactor-specialist.md            |
@@ -248,29 +248,29 @@ mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,sk

 ```
 ~/.claude/homunculus/
-+-- identity.json           # Your profile, technical level
-+-- projects.json           # Registry: project hash -> name/path/remote
-+-- observations.jsonl      # Global observations (fallback)
+-- identity.json           # 你的个人资料，技术水平
+-- projects.json           # 注册表：项目哈希 -> 名称/路径/远程地址
+-- observations.jsonl      # 全局观察记录（备用）
 +-- instincts/
-|   +-- personal/           # Global auto-learned instincts
-|   +-- inherited/          # Global imported instincts
+|   +-- personal/           # 全局自动学习的本能
+|   +-- inherited/          # 全局导入的本能
 +-- evolved/
-|   +-- agents/             # Global generated agents
-|   +-- skills/             # Global generated skills
-|   +-- commands/           # Global generated commands
+|   +-- agents/             # 全局生成的代理
+|   +-- skills/             # 全局生成的技能
+|   +-- commands/           # 全局生成的命令
 +-- projects/
-    +-- a1b2c3d4e5f6/       # Project hash (from git remote URL)
-    |   +-- project.json    # Per-project metadata mirror (id/name/root/remote)
+    +-- a1b2c3d4e5f6/       # 项目哈希（来自 git 远程 URL）
+    |   +-- project.json    # 项目级元数据镜像（ID/名称/根目录/远程地址）
    |   +-- observations.jsonl
    |   +-- observations.archive/
    |   +-- instincts/
-    |   |   +-- personal/   # Project-specific auto-learned
-    |   |   +-- inherited/  # Project-specific imported
+    |   |   +-- personal/   # 项目特定自动学习的
+    |   |   +-- inherited/  # 项目特定导入的
    |   +-- evolved/
    |       +-- skills/
    |       +-- commands/
    |       +-- agents/
-    +-- f6e5d4c3b2a1/       # Another project
+    +-- f6e5d4c3b2a1/       # 另一个项目
        +-- ...
 ```

--- a/docs/zh-CN/skills/crosspost/SKILL.md
+++ b/docs/zh-CN/skills/crosspost/SKILL.md
@@ -102,35 +102,35 @@ origin: ECC
 **X 版本：**

 ```
-We just shipped [feature].
+我们刚刚发布了 [feature]。

-[One specific thing it does that's impressive]
+[它所实现的某个具体且令人印象深刻的功能]

-[Link]
+[链接]
 ```

 **LinkedIn 版本：**

 ```
-Excited to share: we just launched [feature] at [Company].
+激动地宣布：我们刚刚在[Company]推出了[feature]。

-Here's why it matters:
+以下是其重要意义：

-[2-3 short paragraphs with context]
+[2-3段简短背景说明]

-[Takeaway for the audience]
+[对受众的核心启示]

-[Link]
+[链接]
 ```

 **Threads 版本：**

 ```
-just shipped something cool — [feature]
+刚发布了一个很酷的东西 —— [feature]

-[casual explanation of what it does]
+[对这个功能是什么的随意解释]

-link in bio
+链接在简介里
 ```

 ### 源内容：技术见解
@@ -138,21 +138,21 @@ link in bio
 **X 版本：**

 ```
-TIL: [specific technical insight]
+今天学到：[具体技术见解]

-[Why it matters in one sentence]
+[一句话说明其重要性]
 ```

 **LinkedIn 版本：**

 ```
-A pattern I've been using that's made a real difference:
+我一直在使用的一种模式，它带来了真正的改变：

-[Technical insight with professional framing]
+[技术见解与专业框架]

-[How it applies to teams/orgs]
+[它如何适用于团队/组织]

-#relevantHashtag
+#相关标签
 ```

 ## API 集成
--- a/docs/zh-CN/skills/data-scraper-agent/SKILL.md
+++ b/docs/zh-CN/skills/data-scraper-agent/SKILL.md
@@ -101,34 +101,34 @@ for batch in chunks(items, size=5):

 ```
 my-agent/
-├── config.yaml              # User customises this (keywords, filters, preferences)
+├── config.yaml              # 用户自定义此文件（关键词、过滤器、偏好设置）
 ├── profile/
-│   └── context.md           # User context the AI uses (resume, interests, criteria)
+│   └── context.md           # AI 使用的用户上下文（简历、兴趣、标准）
 ├── scraper/
 │   ├── __init__.py
-│   ├── main.py              # Orchestrator: scrape → enrich → store
-│   ├── filters.py           # Rule-based pre-filter (fast, before AI)
+│   ├── main.py              # 协调器：抓取 → 丰富 → 存储
+│   ├── filters.py           # 基于规则的预过滤器（快速，在 AI 处理之前）
 │   └── sources/
 │       ├── __init__.py
-│       └── source_name.py   # One file per data source
+│       └── source_name.py   # 每个数据源一个文件
 ├── ai/
 │   ├── __init__.py
-│   ├── client.py            # Gemini REST client with model fallback
-│   ├── pipeline.py          # Batch AI analysis
-│   ├── jd_fetcher.py        # Fetch full content from URLs (optional)
-│   └── memory.py            # Learn from user feedback
+│   ├── client.py            # Gemini REST 客户端，带模型回退
+│   ├── pipeline.py          # 批量 AI 分析
+│   ├── jd_fetcher.py        # 从 URL 获取完整内容（可选）
+│   └── memory.py            # 从用户反馈中学习
 ├── storage/
 │   ├── __init__.py
-│   └── notion_sync.py       # Or sheets_sync.py / supabase_sync.py
+│   └── notion_sync.py       # 或 sheets_sync.py / supabase_sync.py
 ├── data/
-│   └── feedback.json        # User decision history (auto-updated)
+│   └── feedback.json        # 用户决策历史（自动更新）
 ├── .env.example
-├── setup.py                 # One-time DB/schema creation
-├── enrich_existing.py       # Backfill AI scores on old rows
+├── setup.py                 # 一次性数据库/模式创建
+├── enrich_existing.py       # 对旧行进行 AI 分数回填
 ├── requirements.txt
 └── .github/
    └── workflows/
-        └── scraper.yml      # GitHub Actions schedule
+        └── scraper.yml      # GitHub Actions 计划任务
 ```

 ***
@@ -725,8 +725,8 @@ beautifulsoup4==4.12.3
 lxml==5.1.0
 python-dotenv==1.0.1
 pyyaml==6.0.2
-notion-client==2.2.1   # if using Notion
-# playwright==1.40.0   # uncomment for JS-rendered sites
+notion-client==2.2.1   # 如需使用 Notion
+# playwright==1.40.0   # 针对 JS 渲染的站点，请取消注释
 ```

 ***
@@ -753,14 +753,14 @@ notion-client==2.2.1   # if using Notion
 ## 真实世界示例

 ```
-"Build me an agent that monitors Hacker News for AI startup funding news"
-"Scrape product prices from 3 e-commerce sites and alert when they drop"
-"Track new GitHub repos tagged with 'llm' or 'agents' — summarise each one"
-"Collect Chief of Staff job listings from LinkedIn and Cutshort into Notion"
-"Monitor a subreddit for posts mentioning my company — classify sentiment"
-"Scrape new academic papers from arXiv on a topic I care about daily"
-"Track sports fixture results and keep a running table in Google Sheets"
-"Build a real estate listing watcher — alert on new properties under ₹1 Cr"
+"为我构建一个监控 Hacker News 上 AI 初创公司融资新闻的智能体"
+"从 3 家电商网站抓取产品价格并在降价时发出提醒"
+"追踪标记有 'llm' 或 'agents' 的新 GitHub 仓库——并为每个仓库生成摘要"
+"将 LinkedIn 和 Cutshort 上的首席运营官职位列表收集到 Notion 中"
+"监控一个提到我公司的 subreddit 帖子——并进行情感分类"
+"每日从 arXiv 抓取我关注主题的新学术论文"
+"追踪体育赛事结果并在 Google Sheets 中维护动态更新的表格"
+"构建一个房地产房源监控器——在新房源价格低于 1 千万卢比时发出提醒"
 ```

 ***
--- a/docs/zh-CN/skills/database-migrations/SKILL.md
+++ b/docs/zh-CN/skills/database-migrations/SKILL.md
@@ -300,27 +300,27 @@ ALTER TABLE users DROP COLUMN IF EXISTS avatar_url;

 ```
 Phase 1: EXPAND
-  - Add new column/table (nullable or with default)
-  - Deploy: app writes to BOTH old and new
-  - Backfill existing data
+  - 添加新列/表（可为空或带有默认值）
+  - 部署：应用同时写入旧数据和新数据
+  - 回填现有数据

 Phase 2: MIGRATE
-  - Deploy: app reads from NEW, writes to BOTH
-  - Verify data consistency
+  - 部署：应用读取新数据，同时写入新旧数据
+  - 验证数据一致性

 Phase 3: CONTRACT
-  - Deploy: app only uses NEW
-  - Drop old column/table in separate migration
+  - 部署：应用仅使用新数据
+  - 在单独迁移中删除旧列/表
 ```

 ### 时间线示例

 ```
-Day 1: Migration adds new_status column (nullable)
-Day 1: Deploy app v2 — writes to both status and new_status
-Day 2: Run backfill migration for existing rows
-Day 3: Deploy app v3 — reads from new_status only
-Day 7: Migration drops old status column
+Day 1：迁移添加新的 `new_status` 列（可空）
+Day 1：部署应用 v2 —— 同时写入 `status` 和 `new_status`
+Day 2：运行针对现有行的回填迁移
+Day 3：部署应用 v3 —— 仅从 `new_status` 读取
+Day 7：迁移删除旧的 `status` 列
 ```

 ## 反模式
--- a/docs/zh-CN/skills/deep-research/SKILL.md
+++ b/docs/zh-CN/skills/deep-research/SKILL.md
@@ -60,8 +60,8 @@ firecrawl_search(query: "<sub-question keywords>", limit: 8)
 **使用 exa：**

 ```
-web_search_exa(query: "<sub-question keywords>", numResults: 8)
-web_search_advanced_exa(query: "<keywords>", numResults: 5, startPublishedDate: "2025-01-01")
+web_search_exa(query: "<子问题关键词>", numResults: 8)
+web_search_advanced_exa(query: "<关键词>", numResults: 5, startPublishedDate: "2025-01-01")
 ```

 **搜索策略：**
@@ -135,10 +135,10 @@ crawling_exa(url: "<url>", tokensNum: 5000)
 对于广泛的主题，使用 Claude Code 的 Task 工具进行并行处理：

 ```
-Launch 3 research agents in parallel:
-1. Agent 1: Research sub-questions 1-2
-2. Agent 2: Research sub-questions 3-4
-3. Agent 3: Research sub-question 5 + cross-cutting themes
+并行启动3个研究代理：
+1. 代理1：研究子问题1-2
+2. 代理2：研究子问题3-4
+3. 代理3：研究子问题5 + 交叉主题
 ```

 每个代理负责搜索、阅读来源并返回发现结果。主会话将其综合成最终报告。
@@ -155,9 +155,9 @@ Launch 3 research agents in parallel:
 ## 示例

 ```
-"Research the current state of nuclear fusion energy"
-"Deep dive into Rust vs Go for backend services in 2026"
-"Research the best strategies for bootstrapping a SaaS business"
-"What's happening with the US housing market right now?"
-"Investigate the competitive landscape for AI code editors"
+"研究核聚变能源的当前现状"
+"深入探讨 2026 年 Rust 与 Go 在后端服务中的对比"
+"研究自举 SaaS 业务的最佳策略"
+"美国房地产市场目前情况如何？"
+"调查 AI 代码编辑器的竞争格局"
 ```
--- a/docs/zh-CN/skills/deployment-patterns/SKILL.md
+++ b/docs/zh-CN/skills/deployment-patterns/SKILL.md
@@ -24,17 +24,17 @@ origin: ECC
 逐步替换实例——在发布过程中，新旧版本同时运行。

 ```
-Instance 1: v1 → v2  (update first)
-Instance 2: v1        (still running v1)
-Instance 3: v1        (still running v1)
+实例 1: v1 → v2  (首次更新)
+实例 2: v1        (仍在运行 v1)
+实例 3: v1        (仍在运行 v1)

-Instance 1: v2
-Instance 2: v1 → v2  (update second)
-Instance 3: v1
+实例 1: v2
+实例 2: v1 → v2  (第二次更新)
+实例 3: v1

-Instance 1: v2
-Instance 2: v2
-Instance 3: v1 → v2  (update last)
+实例 1: v2
+实例 2: v2
+实例 3: v1 → v2  (最后更新)
 ```

 **优点：** 零停机时间，渐进式发布
@@ -46,12 +46,12 @@ Instance 3: v1 → v2  (update last)
 运行两个相同的环境。原子化地切换流量。

 ```
-Blue  (v1) ← traffic
-Green (v2)   idle, running new version
+Blue  (v1) ← 流量
+Green (v2)   空闲，运行新版本

-# After verification:
-Blue  (v1)   idle (becomes standby)
-Green (v2) ← traffic
+# 验证后：
+Blue  (v1)   空闲（转为备用状态）
+Green (v2) ← 流量
 ```

 **优点：** 即时回滚（切换回蓝色环境），切换干净利落
@@ -63,15 +63,15 @@ Green (v2) ← traffic
 首先将一小部分流量路由到新版本。

 ```
-v1: 95% of traffic
-v2:  5% of traffic  (canary)
+v1：95% 的流量
+v2：5% 的流量（金丝雀）

-# If metrics look good:
-v1: 50% of traffic
-v2: 50% of traffic
+# 如果指标表现良好：
+v1：50% 的流量
+v2：50% 的流量

-# Final:
-v2: 100% of traffic
+# 最终：
+v2：100% 的流量
 ```

 **优点：** 在全量发布前，通过真实流量发现问题
@@ -168,21 +168,21 @@ CMD ["gunicorn", "config.wsgi:application", "--bind", "0.0.0.0:8000", "--workers
 ### Docker 最佳实践

 ```
-# GOOD practices
- Use specific version tags (node:22-alpine, not node:latest)
- Multi-stage builds to minimize image size
- Run as non-root user
- Copy dependency files first (layer caching)
- Use .dockerignore to exclude node_modules, .git, tests
- Add HEALTHCHECK instruction
- Set resource limits in docker-compose or k8s
+# 良好实践
+- 使用特定版本标签（node:22-alpine，而非 node:latest）
+- 采用多阶段构建以最小化镜像体积
+- 以非 root 用户身份运行
+- 优先复制依赖文件（利用分层缓存）
+- 使用 .dockerignore 排除 node_modules、.git、tests 等文件
+- 添加 HEALTHCHECK 指令
+- 在 docker-compose 或 k8s 中设置资源限制

-# BAD practices
- Running as root
- Using :latest tags
- Copying entire repo in one COPY layer
- Installing dev dependencies in production image
- Storing secrets in image (use env vars or secrets manager)
+# 不良实践
+- 以 root 身份运行
+- 使用 :latest 标签
+- 在单个 COPY 层中复制整个仓库
+- 在生产镜像中安装开发依赖
+- 在镜像中存储密钥（应使用环境变量或密钥管理器）
 ```

 ## CI/CD 流水线
@@ -254,11 +254,11 @@ jobs:
 ### 流水线阶段

 ```
-PR opened:
-  lint → typecheck → unit tests → integration tests → preview deploy
+PR 已开启：
+  lint → typecheck → 单元测试 → 集成测试 → 预览部署

-Merged to main:
-  lint → typecheck → unit tests → integration tests → build image → deploy staging → smoke tests → deploy production
+合并到 main：
+  lint → typecheck → 单元测试 → 集成测试 → 构建镜像 → 部署到 staging → 冒烟测试 → 部署到 production
 ```

 ## 健康检查
--- a/docs/zh-CN/skills/django-patterns/SKILL.md
+++ b/docs/zh-CN/skills/django-patterns/SKILL.md
@@ -26,10 +26,10 @@ myproject/
 │   ├── __init__.py
 │   ├── settings/
 │   │   ├── __init__.py
-│   │   ├── base.py          # Base settings
-│   │   ├── development.py   # Dev settings
-│   │   ├── production.py    # Production settings
-│   │   └── test.py          # Test settings
+│   │   ├── base.py          # 基础设置
+│   │   ├── development.py   # 开发环境设置
+│   │   ├── production.py    # 生产环境设置
+│   │   └── test.py          # 测试环境设置
 │   ├── urls.py
 │   ├── wsgi.py
 │   └── asgi.py
--- a/docs/zh-CN/skills/django-verification/SKILL.md
+++ b/docs/zh-CN/skills/django-verification/SKILL.md
@@ -289,86 +289,86 @@ git diff | grep "import pdb"  # Debugger
 ## 输出模板

 ```
-DJANGO VERIFICATION REPORT
+DJANGO 验证报告
 ==========================

-Phase 1: Environment Check
+阶段 1：环境检查
  ✓ Python 3.11.5
-  ✓ Virtual environment active
-  ✓ All environment variables set
+  ✓ 虚拟环境已激活
+  ✓ 所有环境变量已设置

-Phase 2: Code Quality
-  ✓ mypy: No type errors
-  ✗ ruff: 3 issues found (auto-fixed)
-  ✓ black: No formatting issues
-  ✓ isort: Imports properly sorted
-  ✓ manage.py check: No issues
+阶段 2：代码质量
+  ✓ mypy: 无类型错误
+  ✗ ruff: 发现 3 个问题（已自动修复）
+  ✓ black: 无格式问题
+  ✓ isort: 导入已正确排序
+  ✓ manage.py check: 无问题

-Phase 3: Migrations
-  ✓ No unapplied migrations
-  ✓ No migration conflicts
-  ✓ All models have migrations
+阶段 3：数据库迁移
+  ✓ 无未应用的迁移
+  ✓ 无迁移冲突
+  ✓ 所有模型均有对应的迁移文件

-Phase 4: Tests + Coverage
-  Tests: 247 passed, 0 failed, 5 skipped
-  Coverage:
-    Overall: 87%
+阶段 4：测试与覆盖率
+  测试：247 通过，0 失败，5 跳过
+  覆盖率：
+    总计：87%
    users: 92%
    products: 89%
    orders: 85%
    payments: 91%

-Phase 5: Security Scan
-  ✗ pip-audit: 2 vulnerabilities found (fix required)
-  ✓ safety check: No issues
-  ✓ bandit: No security issues
-  ✓ No secrets detected
+阶段 5：安全扫描
+  ✗ pip-audit: 发现 2 个漏洞（需要修复）
+  ✓ safety check: 无问题
+  ✓ bandit: 无安全问题
+  ✓ 未检测到密钥泄露
  ✓ DEBUG = False

-Phase 6: Django Commands
-  ✓ collectstatic completed
-  ✓ Database integrity OK
-  ✓ Cache backend reachable
+阶段 6：Django 命令
+  ✓ collectstatic 完成
+  ✓ 数据库完整性正常
+  ✓ 缓存后端可访问

-Phase 7: Performance
-  ✓ No N+1 queries detected
-  ✓ Database indexes configured
-  ✓ Query count acceptable
+阶段 7：性能
+  ✓ 未检测到 N+1 查询
+  ✓ 数据库索引已配置
+  ✓ 查询数量可接受

-Phase 8: Static Assets
-  ✓ npm audit: No vulnerabilities
-  ✓ Assets built successfully
-  ✓ Static files collected
+阶段 8：静态资源
+  ✓ npm audit: 无漏洞
+  ✓ 资源构建成功
+  ✓ 静态文件已收集

-Phase 9: Configuration
+阶段 9：配置
  ✓ DEBUG = False
-  ✓ SECRET_KEY configured
-  ✓ ALLOWED_HOSTS set
-  ✓ HTTPS enabled
-  ✓ HSTS enabled
-  ✓ Database configured
+  ✓ SECRET_KEY 已配置
+  ✓ ALLOWED_HOSTS 已设置
+  ✓ HTTPS 已启用
+  ✓ HSTS 已启用
+  ✓ 数据库已配置

-Phase 10: Logging
-  ✓ Logging configured
-  ✓ Log files writable
+阶段 10：日志
+  ✓ 日志配置完成
+  ✓ 日志文件可写入

-Phase 11: API Documentation
-  ✓ Schema generated
-  ✓ Swagger UI accessible
+阶段 11：API 文档
+  ✓ 架构已生成
+  ✓ Swagger UI 可访问

-Phase 12: Diff Review
-  Files changed: 12
-  +450, -120 lines
-  ✓ No debug statements
-  ✓ No hardcoded secrets
-  ✓ Migrations included
+阶段 12：差异审查
+  文件变更：12
+  行数变化：+450, -120
+  ✓ 无调试语句
+  ✓ 无硬编码密钥
+  ✓ 包含迁移文件

-RECOMMENDATION: ⚠️ Fix pip-audit vulnerabilities before deploying
+建议：⚠️ 部署前修复 pip-audit 发现的漏洞

-NEXT STEPS:
-1. Update vulnerable dependencies
-2. Re-run security scan
-3. Deploy to staging for final testing
+后续步骤：
+1. 更新存在漏洞的依赖项
+2. 重新运行安全扫描
+3. 部署到预发布环境进行最终测试
 ```

 ## 预部署检查清单
--- a/docs/zh-CN/skills/dmux-workflows/SKILL.md
+++ b/docs/zh-CN/skills/dmux-workflows/SKILL.md
@@ -47,14 +47,14 @@ dmux
 将研究和实现拆分为并行轨道：

 ```
-Pane 1 (Research): "Research best practices for rate limiting in Node.js.
-  Check current libraries, compare approaches, and write findings to
+Pane 1 (Research): "研究 Node.js 中速率限制的最佳实践。
+  检查当前可用的库，比较不同方法，并将研究结果写入
  /tmp/rate-limit-research.md"

-Pane 2 (Implement): "Implement rate limiting middleware for our Express API.
-  Start with a basic token bucket, we'll refine after research completes."
+Pane 2 (Implement): "为我们的 Express API 实现速率限制中间件。
+  先从基本的令牌桶算法开始，研究完成后我们将进一步优化。"

-# After Pane 1 completes, merge findings into Pane 2's context
+# Pane 1 完成后，将研究结果合并到 Pane 2 的上下文中
 ```

 ### 模式 2：多文件功能
@@ -62,11 +62,11 @@ Pane 2 (Implement): "Implement rate limiting middleware for our Express API.
 在独立文件间并行工作：

 ```
-Pane 1: "Create the database schema and migrations for the billing feature"
-Pane 2: "Build the billing API endpoints in src/api/billing/"
-Pane 3: "Create the billing dashboard UI components"
+Pane 1: "创建计费功能的数据库模式和迁移"
+Pane 2: "在 src/api/billing/ 中构建计费 API 端点"
+Pane 3: "创建计费仪表板 UI 组件"

-# Merge all, then do integration in main pane
+# 合并所有内容，然后在主面板中进行集成
 ```

 ### 模式 3：测试 + 修复循环
@@ -74,10 +74,10 @@ Pane 3: "Create the billing dashboard UI components"
 在一个窗格中运行测试，在另一个窗格中修复：

 ```
-Pane 1 (Watcher): "Run the test suite in watch mode. When tests fail,
-  summarize the failures."
+窗格 1（观察者）：“在监视模式下运行测试套件。当测试失败时，
+  总结失败原因。”

-Pane 2 (Fixer): "Fix failing tests based on the error output from pane 1"
+窗格 2（修复者）：“根据窗格 1 的错误输出修复失败的测试”
 ```

 ### 模式 4：跨套件
@@ -95,11 +95,11 @@ Pane 3 (Claude Code): "Write E2E tests for the checkout flow"
 并行审查视角：

 ```
-Pane 1: "Review src/api/ for security vulnerabilities"
-Pane 2: "Review src/api/ for performance issues"
-Pane 3: "Review src/api/ for test coverage gaps"
+Pane 1: "审查 src/api/ 中的安全漏洞"
+Pane 2: "审查 src/api/ 中的性能问题"
+Pane 3: "审查 src/api/ 中的测试覆盖缺口"

-# Merge all reviews into a single report
+# 将所有审查合并为一份报告
 ```

 ## 最佳实践
--- a/docs/zh-CN/skills/docker-patterns/SKILL.md
+++ b/docs/zh-CN/skills/docker-patterns/SKILL.md
@@ -156,9 +156,9 @@ docker compose -f docker-compose.yml -f docker-compose.prod.yml up -d
 同一 Compose 网络中的服务可通过服务名解析：

 ```
-# From "app" container:
-postgres://postgres:postgres@db:5432/app_dev    # "db" resolves to the db container
-redis://redis:6379/0                             # "redis" resolves to the redis container
+# 从 "app" 容器：
+postgres://postgres:postgres@db:5432/app_dev    # "db" 解析到 db 容器
+redis://redis:6379/0                             # "redis" 解析到 redis 容器
 ```

 ### 自定义网络
@@ -345,21 +345,21 @@ docker network inspect <project>_default
 ## 反模式

 ```
-# BAD: Using docker compose in production without orchestration
-# Use Kubernetes, ECS, or Docker Swarm for production multi-container workloads
+# 错误做法：在生产环境中使用 docker compose 而不进行编排
+# 生产环境多容器工作负载应使用 Kubernetes、ECS 或 Docker Swarm

-# BAD: Storing data in containers without volumes
-# Containers are ephemeral -- all data lost on restart without volumes
+# 错误做法：在容器内存储数据而不使用卷
+# 容器是临时性的——不使用卷时，重启会导致所有数据丢失

-# BAD: Running as root
-# Always create and use a non-root user
+# 错误做法：以 root 用户身份运行
+# 始终创建并使用非 root 用户

-# BAD: Using :latest tag
-# Pin to specific versions for reproducible builds
+# 错误做法：使用 :latest 标签
+# 固定到特定版本以实现可复现的构建

-# BAD: One giant container with all services
-# Separate concerns: one process per container
+# 错误做法：将所有服务放入一个巨型容器
+# 关注点分离：每个容器运行一个进程

-# BAD: Putting secrets in docker-compose.yml
-# Use .env files (gitignored) or Docker secrets
+# 错误做法：将密钥放入 docker-compose.yml
+# 使用 .env 文件（在 git 中忽略）或 Docker secrets
 ```
--- a/docs/zh-CN/skills/eval-harness/SKILL.md
+++ b/docs/zh-CN/skills/eval-harness/SKILL.md
@@ -208,7 +208,7 @@ npm test -- --testPathPattern="existing"
 ### 实施后

 ```
-/eval report feature-name
+/eval 报告 功能名称
 ```

 生成完整的评估报告
@@ -220,9 +220,9 @@ npm test -- --testPathPattern="existing"
 ```
 .claude/
  evals/
-    feature-xyz.md      # Eval definition
-    feature-xyz.log     # Eval run history
-    baseline.json       # Regression baselines
+    feature-xyz.md      # Eval定义
+    feature-xyz.log     # Eval运行历史
+    baseline.json       # 回归基线
 ```

 ## 最佳实践
--- a/docs/zh-CN/skills/exa-search/SKILL.md
+++ b/docs/zh-CN/skills/exa-search/SKILL.md
@@ -40,7 +40,7 @@ origin: ECC
 用于当前信息、新闻或事实的通用网页搜索。

 ```
-web_search_exa(query: "latest AI developments 2026", numResults: 5)
+web_search_exa(query: "2026年最新人工智能发展", numResults: 5)
 ```

 **参数：**
@@ -73,27 +73,27 @@ get_code_context_exa(query: "Python asyncio patterns", tokensNum: 3000)
 ### 快速查找

 ```
-web_search_exa(query: "Node.js 22 new features", numResults: 3)
+web_search_exa(query: "Node.js 22 新功能", numResults: 3)
 ```

 ### 代码研究

 ```
-get_code_context_exa(query: "Rust error handling patterns Result type", tokensNum: 3000)
+get_code_context_exa(query: "Rust错误处理模式Result类型", tokensNum: 3000)
 ```

 ### 公司或人物研究

 ```
-web_search_exa(query: "Vercel funding valuation 2026", numResults: 3, category: "company")
-web_search_exa(query: "site:linkedin.com/in AI safety researchers Anthropic", numResults: 5)
+web_search_exa(query: "Vercel 2026年融资估值", numResults: 3, category: "company")
+web_search_exa(query: "site:linkedin.com/in Anthropic AI安全研究员", numResults: 5)
 ```

 ### 技术深度研究

 ```
-web_search_exa(query: "WebAssembly component model status and adoption", numResults: 5)
-get_code_context_exa(query: "WebAssembly component model examples", tokensNum: 4000)
+web_search_exa(query: "WebAssembly 组件模型状态与采用情况", numResults: 5)
+get_code_context_exa(query: "WebAssembly 组件模型示例", tokensNum: 4000)
 ```

 ## 提示
--- a/docs/zh-CN/skills/fal-ai-media/SKILL.md
+++ b/docs/zh-CN/skills/fal-ai-media/SKILL.md
@@ -56,7 +56,7 @@ fal.ai MCP 提供以下工具：
 generate(
  app_id: "fal-ai/nano-banana-2",
  input_data: {
-    "prompt": "a futuristic cityscape at sunset, cyberpunk style",
+    "prompt": "未来主义日落城市景观，赛博朋克风格",
    "image_size": "landscape_16_9",
    "num_images": 1,
    "seed": 42
@@ -72,7 +72,7 @@ generate(
 generate(
  app_id: "fal-ai/nano-banana-pro",
  input_data: {
-    "prompt": "professional product photo of wireless headphones on marble surface, studio lighting",
+    "prompt": "专业产品照片，无线耳机置于大理石表面，影棚灯光",
    "image_size": "square",
    "num_images": 1,
    "guidance_scale": 7.5
@@ -95,10 +95,10 @@ generate(
 使用 Nano Banana 2 并输入图像进行修复、扩展或风格迁移：

 ```
-# First upload the source image
+# 首先上传源图像
 upload(file_path: "/path/to/image.png")

-# Then generate with image input
+# 然后使用图像输入进行生成
 generate(
  app_id: "fal-ai/nano-banana-2",
  input_data: {
@@ -137,7 +137,7 @@ generate(
 generate(
  app_id: "fal-ai/kling-video/v3/pro",
  input_data: {
-    "prompt": "ocean waves crashing on a rocky coast, dramatic clouds",
+    "prompt": "海浪拍打着岩石海岸，乌云密布",
    "duration": "5s",
    "aspect_ratio": "16:9"
  }
@@ -152,7 +152,7 @@ generate(
 generate(
  app_id: "fal-ai/veo-3",
  input_data: {
-    "prompt": "a bustling Tokyo street market at night, neon signs, crowd noise",
+    "prompt": "夜晚熙熙攘攘的东京街头市场，霓虹灯招牌，人群喧嚣",
    "aspect_ratio": "16:9"
  }
 )
--- a/docs/zh-CN/skills/frontend-slides/STYLE_PRESETS.md
+++ b/docs/zh-CN/skills/frontend-slides/STYLE_PRESETS.md
@@ -17,9 +17,9 @@
 ### 黄金法则

 ```text
-Each slide = exactly one viewport height.
-Too much content = split into more slides.
-Never scroll inside a slide.
+每个幻灯片 = 恰好一个视口高度。
+内容过多 = 分割成更多幻灯片。
+切勿在幻灯片内部滚动。
 ```

 ### 内容密度限制
--- a/docs/zh-CN/skills/golang-patterns/SKILL.md
+++ b/docs/zh-CN/skills/golang-patterns/SKILL.md
@@ -369,17 +369,17 @@ func WriteAndFlush(w io.Writer, data []byte) error {
 myproject/
 ├── cmd/
 │   └── myapp/
-│       └── main.go           # Entry point
+│       └── main.go           # 入口点
 ├── internal/
-│   ├── handler/              # HTTP handlers
-│   ├── service/              # Business logic
-│   ├── repository/           # Data access
-│   └── config/               # Configuration
+│   ├── handler/              # HTTP 处理器
+│   ├── service/              # 业务逻辑
+│   ├── repository/           # 数据访问
+│   └── config/               # 配置
 ├── pkg/
-│   └── client/               # Public API client
+│   └── client/               # 公共 API 客户端
 ├── api/
-│   └── v1/                   # API definitions (proto, OpenAPI)
-├── testdata/                 # Test fixtures
+│   └── v1/                   # API 定义（proto, OpenAPI）
+├── testdata/                 # 测试夹具
 ├── go.mod
 ├── go.sum
 └── Makefile
--- a/docs/zh-CN/skills/golang-testing/SKILL.md
+++ b/docs/zh-CN/skills/golang-testing/SKILL.md
@@ -21,10 +21,10 @@ origin: ECC
 ### 红-绿-重构循环

 ```
-RED     → Write a failing test first
-GREEN   → Write minimal code to pass the test
-REFACTOR → Improve code while keeping tests green
-REPEAT  → Continue with next requirement
+RED     → 首先编写一个失败的测试
+GREEN   → 编写最少的代码来通过测试
+REFACTOR → 改进代码，同时保持测试通过
+REPEAT  → 继续处理下一个需求
 ```

 ### Go 中的分步 TDD
--- a/docs/zh-CN/skills/iterative-retrieval/SKILL.md
+++ b/docs/zh-CN/skills/iterative-retrieval/SKILL.md
@@ -38,15 +38,15 @@ origin: ECC
 ┌─────────────────────────────────────────────┐
 │                                             │
 │   ┌──────────┐      ┌──────────┐            │
-│   │ DISPATCH │─────▶│ EVALUATE │            │
+│   │  调度    │─────▶│  评估    │            │
 │   └──────────┘      └──────────┘            │
 │        ▲                  │                 │
 │        │                  ▼                 │
 │   ┌──────────┐      ┌──────────┐            │
-│   │   LOOP   │◀─────│  REFINE  │            │
+│   │  循环    │◀─────│  优化    │            │
 │   └──────────┘      └──────────┘            │
 │                                             │
-│        Max 3 cycles, then proceed           │
+│        最多3次循环，然后继续                 │
 └─────────────────────────────────────────────┘
 ```

@@ -148,42 +148,42 @@ async function iterativeRetrieve(task, maxCycles = 3) {
 ### 示例 1：错误修复上下文

 ```
-Task: "Fix the authentication token expiry bug"
+任务："修复身份验证令牌过期错误"

-Cycle 1:
-  DISPATCH: Search for "token", "auth", "expiry" in src/**
-  EVALUATE: Found auth.ts (0.9), tokens.ts (0.8), user.ts (0.3)
-  REFINE: Add "refresh", "jwt" keywords; exclude user.ts
+循环 1:
+  分发：在 src/** 中搜索 "token"、"auth"、"expiry"
+  评估：找到 auth.ts (0.9)、tokens.ts (0.8)、user.ts (0.3)
+  优化：添加 "refresh"、"jwt" 关键词；排除 user.ts

-Cycle 2:
-  DISPATCH: Search refined terms
-  EVALUATE: Found session-manager.ts (0.95), jwt-utils.ts (0.85)
-  REFINE: Sufficient context (2 high-relevance files)
+循环 2:
+  分发：搜索优化后的关键词
+  评估：找到 session-manager.ts (0.95)、jwt-utils.ts (0.85)
+  优化：上下文已充分（2 个高相关文件）

-Result: auth.ts, tokens.ts, session-manager.ts, jwt-utils.ts
+结果：auth.ts、tokens.ts、session-manager.ts、jwt-utils.ts
 ```

 ### 示例 2：功能实现

 ```
-Task: "Add rate limiting to API endpoints"
+任务："为API端点添加速率限制"

-Cycle 1:
-  DISPATCH: Search "rate", "limit", "api" in routes/**
-  EVALUATE: No matches - codebase uses "throttle" terminology
-  REFINE: Add "throttle", "middleware" keywords
+周期 1：
+  分发：在 routes/** 中搜索 "rate"、"limit"、"api"
+  评估：无匹配项 - 代码库使用 "throttle" 术语
+  优化：添加 "throttle"、"middleware" 关键词

-Cycle 2:
-  DISPATCH: Search refined terms
-  EVALUATE: Found throttle.ts (0.9), middleware/index.ts (0.7)
-  REFINE: Need router patterns
+周期 2：
+  分发：搜索优化后的术语
+  评估：找到 throttle.ts (0.9)、middleware/index.ts (0.7)
+  优化：需要路由模式

-Cycle 3:
-  DISPATCH: Search "router", "express" patterns
-  EVALUATE: Found router-setup.ts (0.8)
-  REFINE: Sufficient context
+周期 3：
+  分发：搜索 "router"、"express" 模式
+  评估：找到 router-setup.ts (0.8)
+  优化：上下文已足够

-Result: throttle.ts, middleware/index.ts, router-setup.ts
+结果：throttle.ts、middleware/index.ts、router-setup.ts
 ```

 ## 与智能体集成
--- a/docs/zh-CN/skills/kotlin-coroutines-flows/SKILL.md
+++ b/docs/zh-CN/skills/kotlin-coroutines-flows/SKILL.md
@@ -23,9 +23,9 @@ origin: ECC
 ```
 Application
  └── viewModelScope (ViewModel)
-        └── coroutineScope { } (structured child)
-              ├── async { } (concurrent task)
-              └── async { } (concurrent task)
+        └── coroutineScope { } (结构化子作用域)
+              ├── async { } (并发任务)
+              └── async { } (并发任务)
 ```

 始终使用结构化并发——绝不使用 `GlobalScope`：
--- a/docs/zh-CN/skills/kotlin-ktor-patterns/SKILL.md
+++ b/docs/zh-CN/skills/kotlin-ktor-patterns/SKILL.md
@@ -24,28 +24,28 @@ origin: ECC
 ```text
 src/main/kotlin/
 ├── com/example/
-│   ├── Application.kt           # Entry point, module configuration
+│   ├── Application.kt           # 入口点，模块配置
 │   ├── plugins/
-│   │   ├── Routing.kt           # Route definitions
-│   │   ├── Serialization.kt     # Content negotiation setup
-│   │   ├── Authentication.kt    # Auth configuration
-│   │   ├── StatusPages.kt       # Error handling
-│   │   └── CORS.kt              # CORS configuration
+│   │   ├── Routing.kt           # 路由定义
+│   │   ├── Serialization.kt     # 内容协商设置
+│   │   ├── Authentication.kt    # 认证配置
+│   │   ├── StatusPages.kt       # 错误处理
+│   │   └── CORS.kt              # CORS 配置
 │   ├── routes/
-│   │   ├── UserRoutes.kt        # /users endpoints
-│   │   ├── AuthRoutes.kt        # /auth endpoints
-│   │   └── HealthRoutes.kt      # /health endpoints
+│   │   ├── UserRoutes.kt        # /users 端点
+│   │   ├── AuthRoutes.kt        # /auth 端点
+│   │   └── HealthRoutes.kt      # /health 端点
 │   ├── models/
-│   │   ├── User.kt              # Domain models
-│   │   └── ApiResponse.kt       # Response envelopes
+│   │   ├── User.kt              # 领域模型
+│   │   └── ApiResponse.kt       # 响应封装
 │   ├── services/
-│   │   ├── UserService.kt       # Business logic
-│   │   └── AuthService.kt       # Auth logic
+│   │   ├── UserService.kt       # 业务逻辑
+│   │   └── AuthService.kt       # 认证逻辑
 │   ├── repositories/
-│   │   ├── UserRepository.kt    # Data access interface
+│   │   ├── UserRepository.kt    # 数据访问接口
 │   │   └── ExposedUserRepository.kt
 │   └── di/
-│       └── AppModule.kt         # Koin modules
+│       └── AppModule.kt         # Koin 模块
 src/test/kotlin/
 ├── com/example/
 │   ├── routes/
--- a/docs/zh-CN/skills/kotlin-testing/SKILL.md
+++ b/docs/zh-CN/skills/kotlin-testing/SKILL.md
@@ -43,10 +43,10 @@ origin: ECC
 #### RED-GREEN-REFACTOR 周期

 ```
-RED     -> Write a failing test first
-GREEN   -> Write minimal code to pass the test
-REFACTOR -> Improve code while keeping tests green
-REPEAT  -> Continue with next requirement
+RED     -> 首先编写一个失败的测试
+GREEN   -> 编写最少的代码使测试通过
+REFACTOR -> 改进代码同时保持测试通过
+REPEAT  -> 继续下一个需求
 ```

 #### Kotlin 中逐步进行 TDD
--- a/docs/zh-CN/skills/laravel-patterns/SKILL.md
+++ b/docs/zh-CN/skills/laravel-patterns/SKILL.md
@@ -34,20 +34,20 @@ origin: ECC

 ```
 app/
-├── Actions/            # Single-purpose use cases
+├── Actions/            # 单一用途的用例
 ├── Console/
 ├── Events/
 ├── Exceptions/
 ├── Http/
 │   ├── Controllers/
 │   ├── Middleware/
-│   ├── Requests/       # Form request validation
-│   └── Resources/      # API resources
+│   ├── Requests/       # 表单请求验证
+│   └── Resources/      # API 资源
 ├── Jobs/
 ├── Models/
 ├── Policies/
 ├── Providers/
-├── Services/           # Coordinating domain services
+├── Services/           # 协调领域服务
 └── Support/
 config/
 database/
--- a/docs/zh-CN/skills/perl-patterns/SKILL.md
+++ b/docs/zh-CN/skills/perl-patterns/SKILL.md
@@ -372,19 +372,19 @@ for my $child (path('src')->children(qr/\.pl$/)) {
 MyApp/
 ├── lib/
 │   └── MyApp/
-│       ├── App.pm           # Main module
-│       ├── Config.pm        # Configuration
-│       ├── DB.pm            # Database layer
-│       └── Util.pm          # Utilities
+│       ├── App.pm           # 主模块
+│       ├── Config.pm        # 配置
+│       ├── DB.pm            # 数据库层
+│       └── Util.pm          # 工具集
 ├── bin/
-│   └── myapp                # Entry-point script
+│   └── myapp                # 入口脚本
 ├── t/
-│   ├── 00-load.t            # Compilation tests
-│   ├── unit/                # Unit tests
-│   └── integration/         # Integration tests
-├── cpanfile                 # Dependencies
-├── Makefile.PL              # Build system
-└── .perlcriticrc            # Linting config
+│   ├── 00-load.t            # 编译测试
+│   ├── unit/                # 单元测试
+│   └── integration/         # 集成测试
+├── cpanfile                 # 依赖项
+├── Makefile.PL              # 构建系统
+└── .perlcriticrc            # 代码检查配置
 ```

 ### 导出器模式
@@ -407,12 +407,12 @@ sub trim($str) { $str =~ s/^\s+|\s+$//gr }
 ### perltidy 配置 (.perltidyrc)

 ```text
-i=4        # 4-space indent
-l=100      # 100-char line length
-ci=4       # continuation indent
-ce         # cuddled else
-bar        # opening brace on same line
-nolq       # don't outdent long quoted strings
+-i=4        # 4 空格缩进
+-l=100      # 100 字符行宽
+-ci=4       # 续行缩进
+-ce         # else 与右花括号同行
+-bar        # 左花括号与语句同行
+-nolq       # 不对长引用字符串进行反向缩进
 ```

 ### perlcritic 配置 (.perlcriticrc)
--- a/Show More
+++ b/Show More