Menü
代码质量审查 - 进行上下文驱动的代码审查，专注于质量、可测试性和可维护性。适用于审查代码、提供反馈或建立审查实践。
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
设置并使用 1Password CLI (op)。在安装 CLI、启用桌面应用集成、登录（单个或多个帐户）或通过 op 读取/注入/运行密钥时使用。
停止等待提示词，让工作继续进行。
Agent 体验守护系统。解决AI助手常见体验问题 ：长时间无响应、任务卡死、中英文混用、状态不透明。包含看门狗监控、智能状态汇报、即时状态查询、语言一致性过滤、消息队列追踪。适用于所有渠道 （ QQ微信//Telegram飞书//Discord等 ）。当用户抱怨等太久没回复、 “回复中英文混着”、 “不知道在干什么”时使用此技能。
针对 AI 代理 (Agent) 失败的结构化自调试工作流，包括捕捉、诊断、受控恢复和内省报告。
AI 代理的记忆管理工具 - 列表显示、搜索查找、摘要生成及记忆文件维护。包含 AI 驱动的摘要功能。
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
| name | code-review-quality |
| description | 代码质量审查 - 进行上下文驱动的代码审查，专注于质量、可测试性和可维护性。适用于审查代码、提供反馈或建立审查实践。 |
| category | 开发实践 |
| priority | 高 |
| tokenEstimate | 900 |
| agents | ["qe-质量分析器","qe-安全扫描器","qe-性能测试器","qe-覆盖率分析器"] |
| implementation_status | 已优化 |
| optimization_version | 1 |
| last_optimized | "2025-12-02T00:00:00.000Z" |
| dependencies | [] |
| quick_reference_card | true |
| tags | ["code-review","feedback","quality","testability","maintainability","pr-review"] |
| trust_tier | 2 |
| validation | {"schema_path":"schemas/output.json","validator_path":"scripts/validate-config.json"} |
<default_to_action> When reviewing code or establishing review practices:
Quick Review Checklist:
Critical Success Factors:
| Level | Icon | Meaning | Action |
|---|---|---|---|
| Blocker | 🔴 | Bug/security/crash | Must fix before merge |
| Major | 🟡 | Logic issue/test gap | Should fix before merge |
| Minor | 🟢 | Style/naming | Nice to fix |
| Suggestion | 💡 | Alternative approach | Consider for future |
| Lines Changed | Recommendation |
|---|---|
| < 200 | Single review session |
| 200-400 | Review in chunks |
| > 400 | Request PR split |
| ✅ Review | ❌ Skip |
|---|---|
| Logic correctness | Formatting (use linter) |
| Security risks | Naming preferences |
| Test coverage | Architecture debates |
| Performance issues | Style opinions |
| Error handling | Trivial changes |
🔴 **BLOCKER: SQL Injection Risk**
This query is vulnerable to SQL injection:
```javascript
db.query(`SELECT * FROM users WHERE id = ${userId}`)
Fix: Use parameterized queries:
db.query('SELECT * FROM users WHERE id = ?', [userId])
Why: User input directly in SQL allows attackers to execute arbitrary queries.
### Major (Should Fix)
```markdown
🟡 **MAJOR: Missing Error Handling**
What happens if `fetchUser()` throws? The error bubbles up unhandled.
**Suggestion:** Add try/catch with appropriate error response:
```javascript
try {
const user = await fetchUser(id);
return user;
} catch (error) {
logger.error('Failed to fetch user', { id, error });
throw new NotFoundError('User not found');
}
### Minor (Nice to Fix)
```markdown
🟢 **minor:** Variable name could be clearer
`d` doesn't convey meaning. Consider `daysSinceLastLogin`.
💡 **suggestion:** Consider extracting this to a helper
This validation logic appears in 3 places. A `validateEmail()` helper would reduce duplication. Not blocking, but might be worth a follow-up PR.
Reviews must meet a minimum weighted finding score of 3.0 (CRITICAL=3, HIGH=2, MEDIUM=1, LOW=0.5, INFORMATIONAL=0.25). If the initial review falls short, run the qe-devils-advocate agent as a meta-reviewer to find additional observations. Every review should have at least 3 actionable observations.
// Comprehensive code review
await Task("Code Review", {
prNumber: 123,
checks: ['security', 'performance', 'testability', 'maintainability'],
feedbackLevels: ['blocker', 'major', 'minor'],
autoApprove: { maxBlockers: 0, maxMajor: 2 }
}, "qe-quality-analyzer");
// Security-focused review
await Task("Security Review", {
prFiles: changedFiles,
scanTypes: ['injection', 'auth', 'secrets', 'dependencies']
}, "qe-security-scanner");
// Test coverage review
await Task("Coverage Review", {
prNumber: 123,
requireNewTests: true,
minCoverageDelta: 0
}, "qe-coverage-analyzer");
aqe/code-review/
├── review-history/* - Past review decisions
├── patterns/* - Common issues by team/repo
├── feedback-templates/* - Reusable feedback
└── metrics/* - Review turnaround time
const reviewFleet = await FleetManager.coordinate({
strategy: 'code-review',
agents: [
'qe-quality-analyzer', // Logic, maintainability
'qe-security-scanner', // Security risks
'qe-performance-tester', // Performance issues
'qe-coverage-analyzer' // Test coverage
],
topology: 'parallel'
});
| ✅ Do | ❌ Don't |
|---|---|
| "Have you considered...?" | "This is wrong" |
| Explain why it matters | Just say "fix this" |
| Acknowledge good code | Only point out negatives |
| Suggest, don't demand | Be condescending |
| Review < 400 lines | Review 2000 lines at once |
Prioritize feedback: 🔴 Blocker → 🟡 Major → 🟢 Minor → 💡 Suggestion. Focus on bugs and security, not style. Ask questions, don't command. Review < 400 lines at a time. Fast feedback (< 24h) beats thorough feedback.
With Agents: Agents automate security, performance, and coverage checks, freeing human reviewers to focus on logic and design. Use agents for consistent, fast initial review.
/security-testing for security-focused review/qe-coverage-analysis on changed files/qe-quality-assessment