Back to Details

performance-testing-review-multi-agent-review

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Multi-Agent Code Review Orchestration Tool

多Agent代码评审编排工具

Use this skill when

使用本技能的场景

  • Working on multi-agent code review orchestration tool tasks or workflows
  • Needing guidance, best practices, or checklists for multi-agent code review orchestration tool
  • 处理多Agent代码评审编排工具相关任务或工作流时
  • 需要多Agent代码评审编排工具的指导、最佳实践或检查清单时

Do not use this skill when

不使用本技能的场景

  • The task is unrelated to multi-agent code review orchestration tool
  • You need a different domain or tool outside this scope
  • 任务与多Agent代码评审编排工具无关时
  • 需要该范围之外的其他领域或工具时

Instructions

操作说明

  • Clarify goals, constraints, and required inputs.
  • Apply relevant best practices and validate outcomes.
  • Provide actionable steps and verification.
  • If detailed examples are required, open 
    resources/implementation-playbook.md
    .
  • 明确目标、约束条件和所需输入。
  • 应用相关最佳实践并验证结果。
  • 提供可执行步骤和验证方法。
  • 若需要详细示例，请打开
    resources/implementation-playbook.md
    。

Role: Expert Multi-Agent Review Orchestration Specialist

角色：多Agent评审编排专家

A sophisticated AI-powered code review system designed to provide comprehensive, multi-perspective analysis of software artifacts through intelligent agent coordination and specialized domain expertise.
一个基于AI的高级代码评审系统，通过智能Agent协作和专业领域知识，对软件工件进行全面、多视角的分析。

Context and Purpose

背景与目标

The Multi-Agent Review Tool leverages a distributed, specialized agent network to perform holistic code assessments that transcend traditional single-perspective review approaches. By coordinating agents with distinct expertise, we generate a comprehensive evaluation that captures nuanced insights across multiple critical dimensions:
  • Depth: Specialized agents dive deep into specific domains
  • Breadth: Parallel processing enables comprehensive coverage
  • Intelligence: Context-aware routing and intelligent synthesis
  • Adaptability: Dynamic agent selection based on code characteristics
多Agent评审工具利用分布式的专业Agent网络，执行超越传统单视角评审方法的全面代码评估。通过协调具备不同专业知识的Agent，我们生成的综合评估能够捕捉多个关键维度的细致洞察：
  • 深度：专业Agent深入特定领域进行分析
  • 广度：并行处理实现全面覆盖
  • 智能：上下文感知的路由与智能合成
  • 适应性：根据代码特性动态选择Agent

Tool Arguments and Configuration

工具参数与配置

Input Parameters

输入参数

  • $ARGUMENTS
    : Target code/project for review
    • Supports: File paths, Git repositories, code snippets
    • Handles multiple input formats
    • Enables context extraction and agent routing
  • $ARGUMENTS
    : 待评审的目标代码/项目
    • 支持：文件路径、Git仓库、代码片段
    • 兼容多种输入格式
    • 支持上下文提取与Agent路由

Agent Types

Agent类型

  1. Code Quality Reviewers
  2. Security Auditors
  3. Architecture Specialists
  4. Performance Analysts
  5. Compliance Validators
  6. Best Practices Experts
  1. 代码质量评审Agent
  2. 安全审计Agent
  3. 架构专家Agent
  4. 性能分析Agent
  5. 合规验证Agent
  6. 最佳实践专家Agent

Multi-Agent Coordination Strategy

多Agent协作策略

1. Agent Selection and Routing Logic

1. Agent选择与路由逻辑

  • Dynamic Agent Matching:
    • Analyze input characteristics
    • Select most appropriate agent types
    • Configure specialized sub-agents dynamically
  • Expertise Routing:
    python
    def route_agents(code_context):
    agents = []
    if is_web_application(code_context):
        agents.extend([
            "security-auditor",
            "web-architecture-reviewer"
        ])
    if is_performance_critical(code_context):
        agents.append("performance-analyst")
    return agents
  • 动态Agent匹配:
    • 分析输入特性
    • 选择最适合的Agent类型
    • 动态配置专业子Agent
  • 专业能力路由:
    python
    def route_agents(code_context):
    agents = []
    if is_web_application(code_context):
        agents.extend([
            "security-auditor",
            "web-architecture-reviewer"
        ])
    if is_performance_critical(code_context):
        agents.append("performance-analyst")
    return agents

2. Context Management and State Passing

2. 上下文管理与状态传递

  • Contextual Intelligence:
    • Maintain shared context across agent interactions
    • Pass refined insights between agents
    • Support incremental review refinement
  • Context Propagation Model:
    python
    class ReviewContext:
    def __init__(self, target, metadata):
        self.target = target
        self.metadata = metadata
        self.agent_insights = {}

    def update_insights(self, agent_type, insights):
        self.agent_insights[agent_type] = insights
  • 上下文智能:
    • 在Agent交互间维护共享上下文
    • 在Agent间传递优化后的洞察
    • 支持增量评审优化
  • 上下文传播模型:
    python
    class ReviewContext:
    def __init__(self, target, metadata):
        self.target = target
        self.metadata = metadata
        self.agent_insights = {}

    def update_insights(self, agent_type, insights):
        self.agent_insights[agent_type] = insights

3. Parallel vs Sequential Execution

3. 并行与串行执行

  • Hybrid Execution Strategy:
    • Parallel execution for independent reviews
    • Sequential processing for dependent insights
    • Intelligent timeout and fallback mechanisms
  • Execution Flow:
    python
    def execute_review(review_context):
    # Parallel independent agents
    parallel_agents = [
        "code-quality-reviewer",
        "security-auditor"
    ]

    # Sequential dependent agents
    sequential_agents = [
        "architecture-reviewer",
        "performance-optimizer"
    ]
  • 混合执行策略:
    • 独立评审采用并行执行
    • 依赖型洞察采用串行处理
    • 智能超时与回退机制
  • 执行流程:
    python
    def execute_review(review_context):
    # 并行执行的独立Agent
    parallel_agents = [
        "code-quality-reviewer",
        "security-auditor"
    ]

    # 串行执行的依赖型Agent
    sequential_agents = [
        "architecture-reviewer",
        "performance-optimizer"
    ]

4. Result Aggregation and Synthesis

4. 结果聚合与合成

  • Intelligent Consolidation:
    • Merge insights from multiple agents
    • Resolve conflicting recommendations
    • Generate unified, prioritized report
  • Synthesis Algorithm:
    python
    def synthesize_review_insights(agent_results):
    consolidated_report = {
        "critical_issues": [],
        "important_issues": [],
        "improvement_suggestions": []
    }
    # Intelligent merging logic
    return consolidated_report
  • 智能整合:
    • 合并多个Agent的洞察
    • 解决相互冲突的建议
    • 生成统一、优先级明确的报告
  • 合成算法:
    python
    def synthesize_review_insights(agent_results):
    consolidated_report = {
        "critical_issues": [],
        "important_issues": [],
        "improvement_suggestions": []
    }
    # 智能合并逻辑
    return consolidated_report

5. Conflict Resolution Mechanism

5. 冲突解决机制

  • Smart Conflict Handling:
    • Detect contradictory agent recommendations
    • Apply weighted scoring
    • Escalate complex conflicts
  • Resolution Strategy:
    python
    def resolve_conflicts(agent_insights):
    conflict_resolver = ConflictResolutionEngine()
    return conflict_resolver.process(agent_insights)
  • 智能冲突处理:
    • 检测Agent间相互矛盾的建议
    • 应用加权评分
    • 升级处理复杂冲突
  • 解决策略:
    python
    def resolve_conflicts(agent_insights):
    conflict_resolver = ConflictResolutionEngine()
    return conflict_resolver.process(agent_insights)

6. Performance Optimization

6. 性能优化

  • Efficiency Techniques:
    • Minimal redundant processing
    • Cached intermediate results
    • Adaptive agent resource allocation
  • Optimization Approach:
    python
    def optimize_review_process(review_context):
    return ReviewOptimizer.allocate_resources(review_context)
  • 效率提升技术:
    • 最小化冗余处理
    • 缓存中间结果
    • 自适应Agent资源分配
  • 优化方法:
    python
    def optimize_review_process(review_context):
    return ReviewOptimizer.allocate_resources(review_context)

7. Quality Validation Framework

7. 质量验证框架

  • Comprehensive Validation:
    • Cross-agent result verification
    • Statistical confidence scoring
    • Continuous learning and improvement
  • Validation Process:
    python
    def validate_review_quality(review_results):
    quality_score = QualityScoreCalculator.compute(review_results)
    return quality_score > QUALITY_THRESHOLD
  • 全面验证:
    • 跨Agent结果验证
    • 统计置信度评分
    • 持续学习与改进
  • 验证流程:
    python
    def validate_review_quality(review_results):
    quality_score = QualityScoreCalculator.compute(review_results)
    return quality_score > QUALITY_THRESHOLD

Example Implementations

示例实现

1. Parallel Code Review Scenario

1. 并行代码评审场景

python
multi_agent_review(
    target="/path/to/project",
    agents=[
        {"type": "security-auditor", "weight": 0.3},
        {"type": "architecture-reviewer", "weight": 0.3},
        {"type": "performance-analyst", "weight": 0.2}
    ]
)
python
multi_agent_review(
    target="/path/to/project",
    agents=[
        {"type": "security-auditor", "weight": 0.3},
        {"type": "architecture-reviewer", "weight": 0.3},
        {"type": "performance-analyst", "weight": 0.2}
    ]
)

2. Sequential Workflow

2. 串行工作流

python
sequential_review_workflow = [
    {"phase": "design-review", "agent": "architect-reviewer"},
    {"phase": "implementation-review", "agent": "code-quality-reviewer"},
    {"phase": "testing-review", "agent": "test-coverage-analyst"},
    {"phase": "deployment-readiness", "agent": "devops-validator"}
]
python
sequential_review_workflow = [
    {"phase": "design-review", "agent": "architect-reviewer"},
    {"phase": "implementation-review", "agent": "code-quality-reviewer"},
    {"phase": "testing-review", "agent": "test-coverage-analyst"},
    {"phase": "deployment-readiness", "agent": "devops-validator"}
]

3. Hybrid Orchestration

3. 混合编排

python
hybrid_review_strategy = {
    "parallel_agents": ["security", "performance"],
    "sequential_agents": ["architecture", "compliance"]
}
python
hybrid_review_strategy = {
    "parallel_agents": ["security", "performance"],
    "sequential_agents": ["architecture", "compliance"]
}

Reference Implementations

参考实现

  1. Web Application Security Review
  2. Microservices Architecture Validation
  1. Web应用安全评审
  2. 微服务架构验证

Best Practices and Considerations

最佳实践与注意事项

  • Maintain agent independence
  • Implement robust error handling
  • Use probabilistic routing
  • Support incremental reviews
  • Ensure privacy and security
  • 保持Agent独立性
  • 实现健壮的错误处理
  • 使用概率路由
  • 支持增量评审
  • 确保隐私与安全

Extensibility

可扩展性

The tool is designed with a plugin-based architecture, allowing easy addition of new agent types and review strategies.
本工具采用插件化架构设计，可轻松添加新的Agent类型和评审策略。

Invocation

调用方式

Target for review: $ARGUMENTS
待评审目标：$ARGUMENTS