顺序思考方法论：构建可追溯的复杂推理链条，提升问题解决与决策质量

thinking-sequentially by doanchienthangdev/omgkit

1 周安装量

3 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/doanchienthangdev/omgkit --skill thinking-sequentially

方法论项目管理调试

🇨🇳中文介绍

顺序思考

目的

通过编号的思考序列来构建复杂的推理过程：

将多步骤问题分解为可追溯的链条
明确跟踪见解之间的依赖关系
为定期回顾创建检查点
在假设改变时支持修订
支持并行假设探索

快速开始

定义 - 将问题清晰地陈述为 THOUGHT 1
分解 - 将问题分解为带有依赖关系的编号思考
跟踪 - 明确标记依赖关系："depends on THOUGHT 2"
检查点 - 每 5-10 个思考进行一次总结
修订 - 当假设改变时更新思考，并使依赖项失效
分支 - 在需要时探索并行假设

功能特性

功能	描述	指南
编号链条	明确的 THOUGHT 1, 2, 3... 带有 ID	为每个见解编号，永不跳过
依赖关系	标记每个思考所依赖的内容	`[THOUGHT 4] <- depends on [2, 3]`

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

联系我们

相关 Skills

开源项目教练指南 - 诊断问题、制定行动计划、优化开源项目运营

31,600 周安装

飞书日程待办摘要工作流：AI自动生成每日/每周开工报告，提升个人生产力

24,200 周安装

Lark Task CLI 任务管理工具 - 飞书任务创建、分配、更新与协作完整指南

23,400 周安装

BMAD工作流编排与SSD结构化系统设计 - 多代理AI开发流程自动化

10,600 周安装

# 问题分析模式
THOUGHT 1: 问题陈述
THOUGHT 2: 成功标准
THOUGHT 3: 约束条件
THOUGHT 4: 假设（需验证！）
THOUGHT 5-N: 解决方案探索
=== 检查点 ===

# 决策制定模式
THOUGHT 1: 需要做出的决策
THOUGHT 2: 已识别的选项
THOUGHT 3-N: 评估每个选项
THOUGHT N+1: 比较矩阵
THOUGHT N+2: 建议

# 调查模式
THOUGHT 1: 我们观察到的现象
THOUGHT 2: 我们预期的结果
THOUGHT 3: 差距分析
THOUGHT 4-N: 假设检验
=== 检查点：根本原因 ===

# 可视化思考映射
        [THOUGHT 1: 问题]
               |
        +----------+----------+
        |                     |
    [THOUGHT 2]         [THOUGHT 3]
        |                     |
        +----------+----------+
                   |
            [THOUGHT 4: 综合]

需要可追溯推理链的多步骤调试
具有复杂权衡分析的架构决策
需要系统检查多个关注点的代码审查
带有假设跟踪的根本原因分析
需要依赖感知规划的复杂重构

应做	应避免
明确为每个思考编号	为"显而易见"的思考跳过编号
清晰地标记依赖关系	在叙述中隐藏依赖关系
在检查点进行总结	超过 20 个思考没有检查点
允许有理由的修订	删除无效的思考（应划掉）
为每个思考设定时间限制	无限制地无限探索
为并行探索创建分支	分支深度超过 3 层
尽早验证假设	在依赖项失效的情况下继续推进

请参阅这些相关技能文档以获取补充技术：

writing-plans - 将计划构建为编号的思考序列
debugging-systematically - 应用顺序调试步骤
tracing-root-causes - 使用编号的调查链
brainstorming-ideas - 在思考步骤中生成选项

🇺🇸English

Thinking Sequentially

Purpose

Structure complex reasoning through numbered thought sequences:

Decompose multi-step problems into traceable chains
Track dependencies between insights explicitly
Create checkpoints for periodic review
Enable revision when assumptions change
Support parallel hypothesis exploration

Quick Start

Define - State the problem clearly as THOUGHT 1
Decompose - Break into numbered thoughts with dependencies
Track - Mark dependencies explicitly: "depends on THOUGHT 2"
Checkpoint - Summarize every 5-10 thoughts
Revise - Update thoughts when assumptions change, invalidate dependents
Branch - Explore parallel hypotheses when needed

Features

Feature	Description	Guide
Numbered Chains	Explicit THOUGHT 1, 2, 3... with IDs	Number every insight, never skip
Dependencies	Mark what each thought relies on	`[THOUGHT 4] <- depends on [2, 3]`
Checkpoints	Periodic summaries of findings	Every 5-10 thoughts, list key findings
Revisions	Update previous thoughts with new data	Mark original as revised, create new
Branching	Explore multiple hypotheses in parallel	Create named branches, select winner
Visual Maps	Diagram thought relationships	ASCII diagrams for complex chains

Common Patterns

# Problem Analysis Pattern
THOUGHT 1: Problem statement
THOUGHT 2: Success criteria
THOUGHT 3: Constraints
THOUGHT 4: Assumptions (validate!)
THOUGHT 5-N: Solution exploration
=== CHECKPOINT ===

# Decision Making Pattern
THOUGHT 1: Decision to make
THOUGHT 2: Options identified
THOUGHT 3-N: Evaluate each option
THOUGHT N+1: Comparison matrix
THOUGHT N+2: Recommendation

# Investigation Pattern
THOUGHT 1: What we observed
THOUGHT 2: What we expected
THOUGHT 3: Gap analysis
THOUGHT 4-N: Hypothesis testing
=== CHECKPOINT: Root cause ===



# Visual thought mapping
        [THOUGHT 1: Problem]
               |
    +----------+----------+
    |                     |
[THOUGHT 2]         [THOUGHT 3]
    |                     |
    +----------+----------+
               |
        [THOUGHT 4: Synthesis]

Use Cases

Multi-step debugging requiring traceable reasoning chains
Architectural decisions with complex trade-off analysis
Code review requiring systematic examination of multiple concerns
Root cause analysis with hypothesis tracking
Complex refactoring requiring dependency-aware planning

Best Practices

Do	Avoid
Number every thought explicitly	Skipping numbers for "obvious" thoughts
Mark dependencies clearly	Hiding dependencies in prose
Summarize at checkpoints	Exceeding 20 thoughts without checkpoint
Allow revision with reason	Deleting invalid thoughts (strike through)
Time-box each thought	Infinite exploration without bounds
Branch for parallel exploration	Branching more than 3 levels deep
Validate assumptions early	Proceeding with invalidated dependencies

Related Skills

See also these related skill documents for complementary techniques:

writing-plans - Structure plans as numbered thought sequences
debugging-systematically - Apply sequential debugging steps
tracing-root-causes - Use numbered investigation chains
brainstorming-ideas - Generate options in thought steps

Weekly Installs

Repository

doanchienthangdev/omgkit

GitHub Stars

First Seen

1 day ago

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

zencoder1

amp1

cline1

openclaw1

opencode1

cursor1

站立会议模板：敏捷开发每日站会指南与工具（含远程团队异步模板）

10,500 周安装