关于 review
review 是通过协调专业 Agent 开展代码审查的工作流技能,可评估代码质量、设计一致性和变更风险。它支持完整、快速、安全聚焦及 PR 审查模式,并综合结果给出结论和建议。
主要功能
- 01并行运行专业审查 Agent
- 02检查代码质量与可读性
- 03评估设计一致性和变更风险
- 04支持完整、快速、安全及 PR 模式
- 05综合审查结果并给出结论
适用场景
- 01合并前审查功能变更
- 02快速获取代码质量反馈
- 03评估变更中的安全问题
- 04审查拉取请求
安装
复制下面的命令,在终端中运行。
$
npx skills add https:/ / github.com/ parcadei/ continuous-claude-v3 --skill review安装后在 Claude Code 中输入/review确认已加载。
详细介绍
/review - 代码审查工作流
通过多个视角和并行专家进行代码审查。
使用场景
- “审查这段代码”
- “审查我的 PR”
- “合并前检查一下”
- “为实现获取反馈”
- 合并重大更改之前
- 质量门禁
工作流概览
┌──────────┐
│ critic │ ─┐
│ (code) │ │
└──────────┘ │
│
┌──────────┐ │ ┌──────────────┐
│plan-reviewer│ ─┼────▶ │ review-agent │
│ (plan) │ │ │ (synthesis) │
└──────────┘ │ └──────────────┘
│
┌──────────┐ │
│plan-reviewer│ ─┘
│ (change) │
└──────────┘
Parallel Sequential
perspectives synthesis
Agent 顺序
| # | Agent | 关注点 | 执行方式 |
|---|---|---|---|
| 1 | critic | 代码质量、模式、可读性 | 并行 |
| 1 | plan-reviewer | 架构、是否遵循计划 | 并行 |
| 1 | plan-reviewer | 更改影响、风险评估 | 并行 |
| 2 | review-agent | 综合所有审查结果,给出最终结论 | 在 1 之后 |
审查视角
- critic:这段代码写得好吗?(风格、模式、可读性)
- plan-reviewer:这是否符合设计?(架构、计划)
- plan-reviewer:这项更改是否安全?(风险、影响、回归问题)
- review-agent:总体评估和建议
执行
阶段 1:并行审查
# Code quality review
Task(
subagent_type="critic",
prompt="""
Review code quality: [SCOPE]
Evaluate:
- Code style and consistency
- Design patterns used
- Readability and maintainability
- Error handling
- Test coverage
Output: List of issues with severity (critical/major/minor)
""",
run_in_background=true
)
# Architecture review
Task(
subagent_type="plan-reviewer",
prompt="""
Review architecture alignment: [SCOPE]
Check:
- Follows established patterns
- Matches implementation plan (if exists)
- Consistent with system design
- No architectural violations
Output: Alignment assessment with concerns
""",
run_in_background=true
)
# Change impact review
Task(
subagent_type="plan-reviewer",
prompt="""
Review change impact: [SCOPE]
Assess:
- Risk level of changes
- Affected systems/components
- Backward compatibility
- Potential regressions
- Security implications
Output: Risk assessment with recommendations
""",
run_in_background=true
)
# Wait for all parallel reviews
[Check TaskOutput for all three]
阶段 2:综合
Task(
subagent_type="review-agent",
prompt="""
Synthesize reviews for: [SCOPE]
Reviews:
- critic: [code quality findings]
- plan-reviewer: [architecture findings]
- plan-reviewer: [change impact findings]
Create final review:
- Overall verdict (APPROVE / REQUEST_CHANGES / NEEDS_DISCUSSION)
- Prioritized action items
- Blocking vs non-blocking issues
- Summary for PR description
"""
)
审查模式
完整审查
User: /review
→ All four agents, comprehensive review
快速审查
User: /review --quick
→ critic only, fast feedback
安全重点审查
User: /review --security
→ Add aegis (security agent) to parallel phase
PR 审查
User: /review PR #123
→ Fetch PR diff, review changes
示例
User: /review the authentication changes
Claude: Starting /review workflow...
Phase 1: Running parallel reviews...
┌────────────────────────────────────────────┐
│ critic: Reviewing code quality... │
│ plan-reviewer: Checking architecture... │
│ plan-reviewer: Assessing change impact... │
└────────────────────────────────────────────┘
critic: Found 2 issues
- [minor] Inconsistent error messages in auth.ts
- [major] Missing input validation in login()
plan-reviewer: ✅ Matches authentication plan
plan-reviewer: Medium risk
- Affects: login, signup, password reset
- Breaking change: session token format
Phase 2: Synthesizing...
┌─────────────────────────────────────────────┐
│ Review Summary │
├─────────────────────────────────────────────┤
│ Verdict: REQUEST_CHANGES │
│ │
│ Blocking: │
│ 1. Add input validation to login() │
│ │
│ Non-blocking: │
│ 2. Standardize error messages │
│ │
│ Notes: │
│ - Document session token format change │
│ - Consider migration path for existing │
│ sessions │
└─────────────────────────────────────────────┘
结论
- APPROVE:可以合并,所有问题都较轻微
- REQUEST_CHANGES:必须修复阻塞性问题
- NEEDS_DISCUSSION:架构决策需要进一步讨论
评论
支持 Markdown