review by parcadei/continuous-claude-v3
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill review使用并行专家进行多视角代码审查。
┌──────────┐
│ critic │ ─┐
│ (code) │ │
└──────────┘ │
│
┌──────────┐ │ ┌──────────────┐
│plan-reviewer│ ─┼────▶ │ review-agent │
│ (plan) │ │ │ (synthesis) │
└──────────┘ │ └──────────────┘
│
┌──────────┐ │
│plan-reviewer│ ─┘
│ (change) │
└──────────┘
并行视角 顺序合成
---|---|---|---
1 | critic | 代码质量、模式、可读性 | 并行
1 | plan-reviewer | 架构、计划遵循性 | 并行
1 | plan-reviewer | 变更影响、风险评估 | 并行
2 | review-agent | 综合所有审查、最终裁决 | 在阶段1之后
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
# 代码质量审查
Task(
subagent_type="critic",
prompt="""
审查代码质量:[SCOPE]
评估:
- 代码风格和一致性
- 使用的设计模式
- 可读性和可维护性
- 错误处理
- 测试覆盖率
输出:问题列表及严重性(严重/主要/次要)
""",
run_in_background=true
)
# 架构审查
Task(
subagent_type="plan-reviewer",
prompt="""
审查架构对齐性:[SCOPE]
检查:
- 遵循既定模式
- 符合实施计划(如果存在)
- 与系统设计一致
- 无架构违规
输出:包含关注点的对齐性评估
""",
run_in_background=true
)
# 变更影响审查
Task(
subagent_type="plan-reviewer",
prompt="""
审查变更影响:[SCOPE]
评估:
- 变更的风险级别
- 受影响的系统/组件
- 向后兼容性
- 潜在的回归问题
- 安全影响
输出:包含建议的风险评估
""",
run_in_background=true
)
# 等待所有并行审查完成
[Check TaskOutput for all three]
Task(
subagent_type="review-agent",
prompt="""
综合审查结果:[SCOPE]
审查结果:
- critic:[代码质量发现]
- plan-reviewer:[架构发现]
- plan-reviewer:[变更影响发现]
创建最终审查:
- 整体裁决(通过/需要修改/需要讨论)
- 优先处理事项
- 阻塞性 vs 非阻塞性问题
- PR 描述摘要
"""
)
用户:/review
→ 所有四个代理,全面审查
用户:/review --quick
→ 仅 critic 代理,快速反馈
用户:/review --security
→ 在并行阶段添加 aegis(安全代理)
用户:/review PR #123
→ 获取 PR 差异,审查变更
用户:/review 认证相关变更
Claude:启动 /review 工作流...
阶段 1:运行并行审查...
┌────────────────────────────────────────────┐
│ critic:审查代码质量... │
│ plan-reviewer:检查架构... │
│ plan-reviewer:评估变更影响... │
└────────────────────────────────────────────┘
critic:发现 2 个问题
- [次要] auth.ts 中的错误消息不一致
- [主要] login() 中缺少输入验证
plan-reviewer:✅ 符合认证计划
plan-reviewer:中等风险
- 影响:登录、注册、密码重置
- 破坏性变更:会话令牌格式
阶段 2:综合中...
┌─────────────────────────────────────────────┐
│ 审查摘要 │
├─────────────────────────────────────────────┤
│ 裁决:需要修改 │
│ │
│ 阻塞性问题: │
│ 1. 为 login() 添加输入验证 │
│ │
│ 非阻塞性问题: │
│ 2. 标准化错误消息 │
│ │
│ 备注: │
│ - 记录会话令牌格式变更 │
│ - 考虑现有会话的迁移路径 │
└─────────────────────────────────────────────┘
202
3.6K
2026年1月22日
opencode193
codex191
gemini-cli190
cursor189
github-copilot187
amp184
Multi-perspective code review with parallel specialists.
┌──────────┐
│ critic │ ─┐
│ (code) │ │
└──────────┘ │
│
┌──────────┐ │ ┌──────────────┐
│plan-reviewer│ ─┼────▶ │ review-agent │
│ (plan) │ │ │ (synthesis) │
└──────────┘ │ └──────────────┘
│
┌──────────┐ │
│plan-reviewer│ ─┘
│ (change) │
└──────────┘
Parallel Sequential
perspectives synthesis
---|---|---|---
1 | critic | Code quality, patterns, readability | Parallel
1 | plan-reviewer | Architecture, plan adherence | Parallel
1 | plan-reviewer | Change impact, risk assessment | Parallel
2 | review-agent | Synthesize all reviews, final verdict | After 1
# 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]
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
"""
)
User: /review
→ All four agents, comprehensive review
User: /review --quick
→ critic only, fast feedback
User: /review --security
→ Add aegis (security agent) to parallel phase
User: /review PR #123
→ Fetch PR diff, review changes
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 │
└─────────────────────────────────────────────┘
Weekly Installs
202
Repository
GitHub Stars
3.6K
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode193
codex191
gemini-cli190
cursor189
github-copilot187
amp184
agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试
150,000 周安装