Check code for complex logic, duplication, naming issues, and oversized functions. Get a quality report with file locations and severity levels, plus guidance on splitting complex code and extracting shared logic during reviews or after refactoring.
代码质量校验关卡。检测复杂度、重复代码、命名规范、函数长度等质量指标。当用户提到代码质量、复杂度检查、代码异味、重构建议、lint检查、代码规范时使用。
在复杂模块、重构完成时自动触发。
Review the instructions the agent will receive before you install.
代码质量 = 可读性 + 可维护性 + 可测试性
劣质代码是技术债，技术债是道基裂痕
复杂度是 bug 的温床
运行质量检查脚本（跨平台）：
# 在 skill 目录下运行
node scripts/quality_checker.js <扫描路径>
node scripts/quality_checker.js <扫描路径> -v # 详细模式
node scripts/quality_checker.js <扫描路径> --json # JSON 输出
| 指标 | 阈值 | 超标后果 |
|---|---|---|
| 圈复杂度 | ≤ 10 | 🟠 警告，建议拆分 |
| 函数长度 | ≤ 50 行 | 🟠 警告，建议拆分 |
| 文件长度 | ≤ 500 行 | 🟡 提示，考虑拆分 |
| 参数数量 | ≤ 5 | 🟠 警告，考虑封装 |
| 嵌套深度 | ≤ 4 | 🟠 警告，建议重构 |
| 行长度 | ≤ 120 | 🔵 提示 |
| 类型 | 规范 | 示例 |
|---|---|---|
| 类名 | PascalCase | UserService, HttpClient |
| 函数名 | snake_case | get_user, process_data |
| 常量 | UPPER_SNAKE | MAX_RETRY, DEFAULT_TIMEOUT |
| 变量 | snake_case | user_id, total_count |
| 异味 | 说明 | 严重度 |
|---|---|---|
| 重复代码 | 相似代码块 > 10 行 | 🟠 High |
| 过长参数列表 | 参数 > 5 个 | 🟡 Medium |
| 魔法数字 | 未命名的常量 | 🟡 Medium |
| 死代码 | 未使用的函数/变量 | 🔵 Low |
| 注释代码 | 被注释的代码块 | 🔵 Low |
| 场景 | 触发条件 |
|---|---|
| 复杂模块 | 代码行数 > 200 |
| 重构完成 | 重构任务完成时 |
| 代码审查 | PR/MR 审查时 |
| 提交前 | 代码提交前检查 |
1. 扫描代码文件
2. 计算复杂度指标
3. 检测代码异味
4. 验证命名规范
5. 输出质量校验报告
## 代码质量校验报告
✓ 通过 | ✗ 未通过
### 复杂度指标
- 平均函数复杂度: N
- 超标函数数: N
- 最大文件行数: N
### 代码异味
- 🟠 High: N
- 🟡 Medium: N
- 🔵 Low: N
### 问题清单
| 文件 | 行号 | 类型 | 严重度 | 描述 |
|------|------|------|--------|------|
| ... | ... | ... | ... | ... |
### 结论
可交付 / 需重构后交付
# 🔴 高复杂度 - 道基不稳
def process(data):
if condition1:
if condition2:
if condition3:
# 深层嵌套
pass
# ✅ 低复杂度 - 道基稳固
def process(data):
if not condition1:
return
if not condition2:
return
if not condition3:
return
# 主逻辑
# 🔴 重复代码 - 异端
def func1():
# 10行相同逻辑
pass
def func2():
# 10行相同逻辑
pass
# ✅ 提取公共函数 - 正道
def common_logic():
# 公共逻辑
pass
def func1():
common_logic()
def func2():
common_logic()
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Adapts existing designs for phones, tablets, desktops, print, and email. Adjusts layouts, navigation, content priorities, and touch controls to suit each context, with guidance for responsive sizing and verification across devices and input methods.
Audit a website for Google AdSense application readiness or ongoing ad-serving issues. Check content, navigation, crawler access, and disclosures against official requirements, then receive evidence-based findings, specific fixes, and a complete checklist with unresolved questions clearly marked.
Routes AI development questions to focused references on agents, language model security, retrieval-augmented generation, which uses retrieved information in answers, and prompt design and evaluation. It also outlines principles for validation, safety boundaries, version control, and ongoing assessment.
Review an interface and add purposeful motion to buttons, forms, navigation, and state changes. Plan and implement animations that clarify actions and provide feedback, while checking performance and supporting users who prefer reduced motion.
Find the relevant architectural guidance for API design, security, cloud infrastructure, message queues, and caching. This skill acts as an index to specialized references and lists principles for structuring software, distributed systems, and access controls.
Improve interface layouts by reviewing spacing, alignment, content density, and visual hierarchy, the cues that show what matters most. Refine repetitive card grids and crowded sections into compositions with consistent spacing and responsive structure.