多智能体团队编排与任务协作框架

---
name: agent-organization-expert
description: Multi-agent orchestration skill for team assembly, task decomposition, workflow optimization, and coordination strategies to achieve optimal team performance and resource utilization.
---

# 智能体编排

通过系统化的任务分析、能力映射和工作流设计，组建并协调多智能体团队。

## 配置

- **智能体数量**：${agent_count:3}
- **任务类型**：${task_type:general}
- **编排模式**：${orchestration_pattern:parallel}
- **最大并发数**：${max_concurrency:5}
- **超时时间（秒）**：${timeout_seconds:300}
- **重试次数**：${retry_count:3}

## 核心流程

1. **分析需求**：理解任务范围、约束和成功标准
2. **映射能力**：将可用智能体与所需技能匹配
3. **设计工作流**：创建包含依赖关系与检查点的执行计划
4. **编排执行**：协调 ${agent_count:3} 个智能体并监控进度
5. **持续优化**：根据性能反馈进行调整

## 任务分解

### 需求分析
- 将复杂任务拆分为离散的子任务
- 明确每个子任务的输入/输出要求
- 评估每个组件的复杂度和资源需求
- 为每个单元定义清晰的成功标准

### 依赖映射
- 记录任务执行顺序约束
- 识别子任务之间的数据依赖
- 梳理资源共享需求
- 检测潜在瓶颈和冲突

### 时间线规划
- 在尊重依赖关系的前提下安排任务顺序
- 识别可并行的机会（最多 ${max_concurrency:5} 个并发）
- 为高风险组件预留缓冲时间
- 为进度验证设定检查点

## 智能体选择

### 能力匹配
依据以下因素选择智能体：
- 所需技能与智能体专长的对应程度
- 在类似任务上的历史表现
- 当前可用性与工作负载承载能力
- 针对任务复杂度的成本效益

### 选择标准优先级
1. **能力匹配**：智能体必须具备所需技能
2. **业绩记录**：优先选择已证明成功的智能体
3. **可用性**：具备足够的承载能力以按时完成
4. **成本**：在约束范围内优化资源利用

### 备份规划
- 为关键角色确定备选智能体
- 定义故障切换触发条件和交接流程
- 为存在单点故障的任务保留冗余

## 团队组建

### 组成原则
- 确保所有子任务的技能覆盖完整
- 在 ${agent_count:3} 名团队成员之间平衡工作负载
- 尽量减少沟通开销
- 为关键功能保留冗余

### 角色分配
- 根据优势将智能体与子任务匹配
- 明确归属与责任
- 在相互依赖的角色之间建立沟通渠道
- 记录遇到阻碍时的升级路径

### 团队规模
- 紧密耦合的任务用小团队
- 可并行的工作负载用大团队
- 规模决策中需考虑协调开销
- 根据进度动态调整规模

## 编排模式

### 顺序执行
在任务有严格先后要求时使用：
- 任务 B 需要任务 A 的输出
- 各步骤之间的状态必须保持一致
- 错误处理需要按顺序回滚

### 并行处理
在任务相互独立时使用（${orchestration_pattern:parallel}）：
- 任务之间没有数据依赖
- 资源需求彼此分离
- 完成后可汇总结果
- 最多 ${max_concurrency:5} 个并发操作

### 流水线模式
用于流式或持续处理：
- 每个阶段处理结果并将其转交下一阶段
- 允许不同阶段并发执行
- 降低多步骤工作流的整体延迟

### 层级委派
用于需要子编排的复杂任务：
- 主导智能体协调各子团队
- 每个子团队负责一个领域
- 结果逐级向上汇总

### Map-Reduce
用于大规模数据处理：
- Map 阶段将工作分配给各智能体
- 每个智能体处理一个分区
- Reduce 阶段合并结果

## 工作流设计

### 流程结构
1. **入口点**：验证输入并初始化状态
2. **执行阶段**：有序的任务分组
3. **检查点**：状态持久化与验证节点
4. **出口点**：结果汇总与清理

### 控制流
- 为替代路径定义分支条件
- 为临时性故障指定重试策略（最多 ${retry_count:3} 次重试）
- 为每个阶段设定超时阈值（默认 ${timeout_seconds:300} 秒）
- 针对部分失败规划平稳降级

### 数据流
- 记录各阶段之间的数据转换
- 指定数据格式和验证规则
- 在检查点规划数据持久化
- 任务完成后处理数据清理

## 协调策略

### 通信模式
- **直接通信**：智能体之间点对点，适用于紧密耦合
- **广播**：一对多，用于状态更新
- **基于队列**：异步，用于解耦的任务
- **事件驱动**：响应状态变化

### 同步
- 为相互依赖的任务定义同步点
- 以超时机制实现等待（${timeout_seconds:300} 秒）
- 妥善处理乱序完成的情况
- 在所有智能体之间保持状态一致

### 冲突解决
- 为资源竞争建立优先级规则
- 为冲突定义仲裁机制
- 记录死锁的回滚流程
- 通过合理调度预防冲突

## 性能优化

### 负载均衡
- 根据智能体承载能力分配工作
- 监控利用率并动态再平衡
- 避免过度加载高性能智能体
- 对数据密集型任务考虑智能体的位置

### 瓶颈管理
- 通过监控识别速度慢的阶段
- 为受限资源增加承载能力
- 重构工作流以减少依赖
- 在有益时缓存中间结果

### 资源效率
- 在智能体之间共享资源池
- 用完后及时释放资源
- 批量处理相似操作以降低开销
- 监控资源浪费并发出告警

## 监控与调整

### 进度跟踪
- 监控每项任务的完成状态
- 对比实际耗时与预估时间
- 识别有延误风险的任务
- 向相关方汇总汇报进度

### 性能指标
- 任务完成率与延迟
- 智能体利用率与吞吐量
- 错误率与恢复时间
- 资源消耗与成本

### 动态调整
- 根据进度重新分配智能体
- 根据阻碍因素调整优先级
- 根据工作负载调整团队规模
- 根据经验修改工作流

## 错误处理

### 故障检测
- 监控任务失败与超时（${timeout_seconds:300} 秒阈值）
- 及时发现智能体不可用
- 识别级联故障模式
- 对异常行为发出告警

### 恢复流程
- 以退避方式重试临时性故障（最多 ${retry_count:3} 次）
- 必要时切换至备用智能体
- 关键故障时回滚到最近的检查点
- 无法恢复的问题升级处理

### 预防
- 执行前验证输入
- 分配前测试智能体可用性
- 设计时考虑平稳降级
- 在关键路径中建立冗余

## 质量保证

### 验证关卡
- 在每个检查点验证输出
- 交叉核对并行任务的结果
- 验证最终汇总结果
- 确认满足成功标准

### 性能标准
- 智能体选择准确率目标：>${agent_selection_accuracy:95}%
- 任务完成率目标：>${task_completion_rate:99}%
- 响应时间目标：<${response_time_threshold:5} 秒
- 资源利用率：最佳范围 ${utilization_min:60}-${utilization_max:80}%

## 最佳实践

### 规划
- 投入充足时间进行深入的任务分析
- 记录假设与约束
- 预先规划失败场景
- 明确成功指标

### 执行
- 从最小可行团队（${agent_count:3} 个智能体）开始
- 根据观察到的需求逐步扩展
- 保持清晰的沟通渠道
- 按里程碑跟踪进度

### 学习
- 收集性能数据用于分析
- 识别成功与失败中的规律
- 改进选择与协调策略
- 在后续编排中分享经验

---
name: agent-organization-expert
description: Multi-agent orchestration skill for team assembly, task decomposition, workflow optimization, and coordination strategies to achieve optimal team performance and resource utilization.
---

# Agent Organization

Assemble and coordinate multi-agent teams through systematic task analysis, capability mapping, and workflow design.

## Configuration

- **Agent Count**: ${agent_count:3}
- **Task Type**: ${task_type:general}
- **Orchestration Pattern**: ${orchestration_pattern:parallel}
- **Max Concurrency**: ${max_concurrency:5}
- **Timeout (seconds)**: ${timeout_seconds:300}
- **Retry Count**: ${retry_count:3}

## Core Process

1. **Analyze Requirements**: Understand task scope, constraints, and success criteria
2. **Map Capabilities**: Match available agents to required skills
3. **Design Workflow**: Create execution plan with dependencies and checkpoints
4. **Orchestrate Execution**: Coordinate ${agent_count:3} agents and monitor progress
5. **Optimize Continuously**: Adapt based on performance feedback

## Task Decomposition

### Requirement Analysis
- Break complex tasks into discrete subtasks
- Identify input/output requirements for each subtask
- Estimate complexity and resource needs per component
- Define clear success criteria for each unit

### Dependency Mapping
- Document task execution order constraints
- Identify data dependencies between subtasks
- Map resource sharing requirements
- Detect potential bottlenecks and conflicts

### Timeline Planning
- Sequence tasks respecting dependencies
- Identify parallelization opportunities (up to ${max_concurrency:5} concurrent)
- Allocate buffer time for high-risk components
- Define checkpoints for progress validation

## Agent Selection

### Capability Matching
Select agents based on:
- Required skills versus agent specializations
- Historical performance on similar tasks
- Current availability and workload capacity
- Cost efficiency for the task complexity

### Selection Criteria Priority
1. **Capability fit**: Agent must possess required skills
2. **Track record**: Prefer agents with proven success
3. **Availability**: Sufficient capacity for timely completion
4. **Cost**: Optimize resource utilization within constraints

### Backup Planning
- Identify alternate agents for critical roles
- Define failover triggers and handoff procedures
- Maintain redundancy for single-point-of-failure tasks

## Team Assembly

### Composition Principles
- Ensure complete skill coverage for all subtasks
- Balance workload across ${agent_count:3} team members
- Minimize communication overhead
- Include redundancy for critical functions

### Role Assignment
- Match agents to subtasks based on strength
- Define clear ownership and accountability
- Establish communication channels between dependent roles
- Document escalation paths for blockers

### Team Sizing
- Smaller teams for tightly coupled tasks
- Larger teams for parallelizable workloads
- Consider coordination overhead in sizing decisions
- Scale dynamically based on progress

## Orchestration Patterns

### Sequential Execution
Use when tasks have strict ordering requirements:
- Task B requires output from Task A
- State must be consistent between steps
- Error handling requires ordered rollback

### Parallel Processing
Use when tasks are independent (${orchestration_pattern:parallel}):
- No data dependencies between tasks
- Separate resource requirements
- Results can be aggregated after completion
- Maximum ${max_concurrency:5} concurrent operations

### Pipeline Pattern
Use for streaming or continuous processing:
- Each stage processes and forwards results
- Enables concurrent execution of different stages
- Reduces overall latency for multi-step workflows

### Hierarchical Delegation
Use for complex tasks requiring sub-orchestration:
- Lead agent coordinates sub-teams
- Each sub-team handles a domain
- Results aggregate upward through hierarchy

### Map-Reduce
Use for large-scale data processing:
- Map phase distributes work across agents
- Each agent processes a partition
- Reduce phase combines results

## Workflow Design

### Process Structure
1. **Entry point**: Validate inputs and initialize state
2. **Execution phases**: Ordered task groupings
3. **Checkpoints**: State persistence and validation points
4. **Exit point**: Result aggregation and cleanup

### Control Flow
- Define branching conditions for alternative paths
- Specify retry policies for transient failures (max ${retry_count:3} retries)
- Establish timeout thresholds per phase (${timeout_seconds:300}s default)
- Plan graceful degradation for partial failures

### Data Flow
- Document data transformations between stages
- Specify data formats and validation rules
- Plan for data persistence at checkpoints
- Handle data cleanup after completion

## Coordination Strategies

### Communication Patterns
- **Direct**: Agent-to-agent for tight coupling
- **Broadcast**: One-to-many for status updates
- **Queue-based**: Asynchronous for decoupled tasks
- **Event-driven**: Reactive to state changes

### Synchronization
- Define sync points for dependent tasks
- Implement waiting mechanisms with timeouts (${timeout_seconds:300}s)
- Handle out-of-order completion gracefully
- Maintain consistent state across agents

### Conflict Resolution
- Establish priority rules for resource contention
- Define arbitration mechanisms for conflicts
- Document rollback procedures for deadlocks
- Prevent conflicts through careful scheduling

## Performance Optimization

### Load Balancing
- Distribute work based on agent capacity
- Monitor utilization and rebalance dynamically
- Avoid overloading high-performing agents
- Consider agent locality for data-intensive tasks

### Bottleneck Management
- Identify slow stages through monitoring
- Add capacity to constrained resources
- Restructure workflows to reduce dependencies
- Cache intermediate results where beneficial

### Resource Efficiency
- Pool shared resources across agents
- Release resources promptly after use
- Batch similar operations to reduce overhead
- Monitor and alert on resource waste

## Monitoring and Adaptation

### Progress Tracking
- Monitor completion status per task
- Track time spent versus estimates
- Identify tasks at risk of delay
- Report aggregated progress to stakeholders

### Performance Metrics
- Task completion rate and latency
- Agent utilization and throughput
- Error rates and recovery times
- Resource consumption and cost

### Dynamic Adjustment
- Reallocate agents based on progress
- Adjust priorities based on blockers
- Scale team size based on workload
- Modify workflow based on learning

## Error Handling

### Failure Detection
- Monitor for task failures and timeouts (${timeout_seconds:300}s threshold)
- Detect agent unavailability promptly
- Identify cascade failure patterns
- Alert on anomalous behavior

### Recovery Procedures
- Retry transient failures with backoff (up to ${retry_count:3} attempts)
- Failover to backup agents when needed
- Rollback to last checkpoint on critical failure
- Escalate unrecoverable issues

### Prevention
- Validate inputs before execution
- Test agent availability before assignment
- Design for graceful degradation
- Build redundancy into critical paths

## Quality Assurance

### Validation Gates
- Verify outputs at each checkpoint
- Cross-check results from parallel tasks
- Validate final aggregated results
- Confirm success criteria are met

### Performance Standards
- Agent selection accuracy target: >${agent_selection_accuracy:95}%
- Task completion rate target: >${task_completion_rate:99}%
- Response time target: <${response_time_threshold:5} seconds
- Resource utilization: optimal range ${utilization_min:60}-${utilization_max:80}%

## Best Practices

### Planning
- Invest time in thorough task analysis
- Document assumptions and constraints
- Plan for failure scenarios upfront
- Define clear success metrics

### Execution
- Start with minimal viable team (${agent_count:3} agents)
- Scale based on observed needs
- Maintain clear communication channels
- Track progress against milestones

### Learning
- Capture performance data for analysis
- Identify patterns in successes and failures
- Refine selection and coordination strategies
- Share learnings across future orchestrations