Back to Details

moai-workflow-thinking

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Sequential Thinking & UltraThink

Sequential Thinking & UltraThink

Structured reasoning system for complex problem analysis and decision-making.
用于复杂问题分析与决策的结构化推理系统。

Activation Triggers

触发场景

Use Sequential Thinking MCP when:
  • Breaking down complex problems into steps
  • Planning and design with room for revision
  • Architecture decisions affect 3+ files
  • Technology selection between multiple options
  • Performance vs maintainability trade-offs
  • Breaking changes under consideration
  • Multiple approaches exist to solve the same problem
  • Repetitive errors occur
在以下场景使用Sequential Thinking MCP：
  • 将复杂问题拆解为多个步骤
  • 进行可迭代的规划与设计
  • 架构决策影响3个及以上文件
  • 多选项间的技术选型
  • 性能与可维护性的权衡
  • 评估破坏性变更
  • 同一问题存在多种解决方案
  • 重复出现错误时

Tool Parameters

工具参数

Required Parameters:
  • thought
    (string): Current thinking step content
  • nextThoughtNeeded
    (boolean): Whether another step is needed
  • thoughtNumber
    (integer): Current thought number (starts from 1)
  • totalThoughts
    (integer): Estimated total thoughts needed
Optional Parameters:
  • isRevision
    (boolean): Whether this revises previous thinking
  • revisesThought
    (integer): Which thought is being reconsidered
  • branchFromThought
    (integer): Branching point for alternatives
  • branchId
    (string): Branch identifier
  • needsMoreThoughts
    (boolean): If more thoughts needed beyond estimate
必填参数：
  • thought
    (string): 当前思考步骤的内容
  • nextThoughtNeeded
    (boolean): 是否需要下一步思考
  • thoughtNumber
    (integer): 当前思考步骤编号（从1开始）
  • totalThoughts
    (integer): 预估所需的总思考步骤数
可选参数：
  • isRevision
    (boolean): 本次思考是否修正之前的内容
  • revisesThought
    (integer): 修正的是哪一步思考
  • branchFromThought
    (integer): 分支思考的起始步骤
  • branchId
    (string): 分支标识符
  • needsMoreThoughts
    (boolean): 是否需要超出预估的更多思考步骤

Usage Pattern

使用流程

Step 1 - Initial Analysis:
thought: "Analyzing the problem: [describe problem]"
nextThoughtNeeded: true
thoughtNumber: 1
totalThoughts: 5
Step 2 - Decomposition:
thought: "Breaking down: [sub-problems]"
nextThoughtNeeded: true
thoughtNumber: 2
totalThoughts: 5
Step 3 - Revision (if needed):
thought: "Revising thought 2: [correction]"
isRevision: true
revisesThought: 2
thoughtNumber: 3
totalThoughts: 5
nextThoughtNeeded: true
Final Step - Conclusion:
thought: "Conclusion: [final answer]"
thoughtNumber: 5
totalThoughts: 5
nextThoughtNeeded: false
步骤1 - 初始分析：
thought: "Analyzing the problem: [describe problem]"
nextThoughtNeeded: true
thoughtNumber: 1
totalThoughts: 5
步骤2 - 问题拆解：
thought: "Breaking down: [sub-problems]"
nextThoughtNeeded: true
thoughtNumber: 2
totalThoughts: 5
步骤3 - 修正（若需）：
thought: "Revising thought 2: [correction]"
isRevision: true
revisesThought: 2
thoughtNumber: 3
totalThoughts: 5
nextThoughtNeeded: true
最终步骤 - 结论：
thought: "Conclusion: [final answer]"
thoughtNumber: 5
totalThoughts: 5
nextThoughtNeeded: false

UltraThink Mode

UltraThink 模式

Enhanced analysis mode activated by 
--ultrathink
flag.
Activation:
"Implement authentication system --ultrathink"
"Refactor the API layer --ultrathink"
Process:
  1. Request Analysis: Identify core task, detect keywords, recognize complexity
  2. Sequential Thinking: Begin structured reasoning
  3. Execution Planning: Map subtasks to agents, identify parallel opportunities
  4. Execution: Launch agents, integrate results
UltraThink Parameters:
Initial Analysis:
thought: "Analyzing user request: [content]"
nextThoughtNeeded: true
thoughtNumber: 1
totalThoughts: [estimate]
Subtask Decomposition:
thought: "Breaking down: 1) [task1] 2) [task2] 3) [task3]"
nextThoughtNeeded: true
thoughtNumber: 2
Agent Mapping:
thought: "Mapping: [task1] → expert-backend, [task2] → expert-frontend"
nextThoughtNeeded: true
thoughtNumber: 3
Execution Strategy:
thought: "Strategy: [tasks1,2] parallel, [task3] depends on [task1]"
nextThoughtNeeded: true
thoughtNumber: 4
Final Plan:
thought: "Plan: Launch [agents] in parallel, then [agent]"
nextThoughtNeeded: false
通过
--ultrathink
参数激活的增强分析模式。
激活方式：
"Implement authentication system --ultrathink"
"Refactor the API layer --ultrathink"
执行流程：
  1. 请求分析：识别核心任务、检测关键词、判断复杂度
  2. 序列思考：启动结构化推理
  3. 执行规划：将子任务分配给Agent、识别并行执行机会
  4. 执行阶段：启动Agent、整合结果
UltraThink 参数示例：
初始分析：
thought: "Analyzing user request: [content]"
nextThoughtNeeded: true
thoughtNumber: 1
totalThoughts: [estimate]
子任务拆解：
thought: "Breaking down: 1) [task1] 2) [task2] 3) [task3]"
nextThoughtNeeded: true
thoughtNumber: 2
Agent 分配：
thought: "Mapping: [task1] → expert-backend, [task2] → expert-frontend"
nextThoughtNeeded: true
thoughtNumber: 3
执行策略：
thought: "Strategy: [tasks1,2] parallel, [task3] depends on [task1]"
nextThoughtNeeded: true
thoughtNumber: 4
最终计划：
thought: "Plan: Launch [agents] in parallel, then [agent]"
nextThoughtNeeded: false

When to Use

适用场景

UltraThink is ideal for:
  • Complex multi-domain tasks (backend + frontend + testing)
  • Architecture decisions affecting multiple files
  • Performance optimization requiring analysis
  • Security review needs
  • Refactoring with behavior preservation
Benefits:
  • Structured decomposition of complex problems
  • Explicit agent-task mapping with justification
  • Identification of parallel execution opportunities
  • Context maintenance throughout reasoning
  • Revision capability when approaches need adjustment
UltraThink 适用于：
  • 跨多领域的复杂任务（后端+前端+测试）
  • 影响多个文件的架构决策
  • 需要深度分析的性能优化
  • 安全审查需求
  • 需保留原有功能的重构
优势：
  • 结构化拆解复杂问题
  • 明确Agent与任务的匹配及依据
  • 识别并行执行的机会
  • 推理全程保持上下文连贯性
  • 可在需要时调整思路并修正

Guidelines

使用准则

  1. Start with reasonable totalThoughts estimate
  2. Use isRevision when correcting previous thoughts
  3. Maintain thoughtNumber sequence
  4. Set nextThoughtNeeded to false only when complete
  5. Use branching for exploring alternatives
  1. 初始预估总思考步骤数时需合理
  2. 修正之前的思考时使用isRevision参数
  3. 保持思考步骤编号的连续性
  4. 仅在完成所有思考时将nextThoughtNeeded设为false
  5. 探索替代方案时使用分支功能