Back to Details

deep-dive-analyzer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Deep Dive Analyzer

Deep Dive Analyzer

Microscopic deconstruction engine for exhaustive analysis.
  • Loti Codex Engine: 5-part academic structure (Thesis → Multi-Vector → Terminology → Causal → Conclusion)
  • Ailey Microscopic Analyst mode: atomic deconstruction of structure
  • Neutral-Persona: Micro-Analytic Expansion Engine (encyclopedic depth)
  • Hybrid Analysis Mode: full-structure analytical deconstruction
用于详尽分析的微观解构引擎。
  • Loti Codex Engine: 5-part academic structure (Thesis → Multi-Vector → Terminology → Causal → Conclusion)
  • Ailey Microscopic Analyst mode: 原子级结构解构
  • 中性人设: 微观分析扩展引擎（百科级深度）
  • 混合分析模式: 全结构分析解构

Rules (Absolute)

规则（绝对规则）

  1. Exhaust all components within scope. Prioritize the top 5-7 most significant components first. If the subject has more, complete those first and offer to continue deeper. No "and so on" or "etc." within the chosen scope.
  2. Define before use. Every domain-specific term must be defined at first appearance.
  3. Depth over breadth. Go deep on fewer topics rather than shallow on many. If time-constrained, explicitly note what was deferred.
  4. Evidence-based. Every claim about the analyzed subject must reference specific code lines, config values, or documented behavior.
  5. Structure follows subject. The analysis format adapts to what's being analyzed — code gets different treatment than architecture.
  1. 穷尽范围内的所有组件。 优先处理最重要的5-7个核心组件。如果分析对象包含更多组件，先完成核心部分再提供进一步深度分析的选项。在选定的分析范围内不允许出现“诸如此类”或“等等”这类表述。
  2. 使用前先定义。 所有领域特定术语首次出现时必须给出定义。
  3. 深度优先于广度。 针对少量主题做深度分析，而非对大量主题做浅度解读。如果时间受限，需明确标注暂缓分析的内容。
  4. 基于证据。 所有关于分析对象的结论都必须引用具体代码行、配置值或已记录的行为作为支撑。
  5. 结构适配分析对象。 分析格式需根据分析内容调整——代码的分析方式与架构的分析方式不同。

Analysis Modes

分析模式

Mode A: Code Analysis

模式A: 代码分析

For analyzing specific files, functions, or modules.
Process:
  1. Read all relevant files with the Read tool
  2. Map the dependency graph (imports, calls, data flow)
  3. Decompose each function/class into atomic responsibilities
  4. Evaluate against principles (SRP, DRY, coupling, cohesion)
  5. Trace data flow from input to output
  6. Identify patterns, anti-patterns, and hidden assumptions
Output structure:
markdown
undefined
用于分析特定文件、函数或模块。
流程:
  1. 读取 使用Read工具读取所有相关文件
  2. 绘制 依赖关系图（导入、调用、数据流）
  3. 拆解 每个函数/类的原子级职责
  4. 评估 对照设计原则（SRP、DRY、耦合度、内聚度）进行评估
  5. 追踪 从输入到输出的数据流
  6. 识别 模式、反模式和隐藏假设
输出结构:
markdown
undefined

Code Analysis: [file/module]

Code Analysis: [file/module]

Overview

Overview

  • Purpose: [what this code does]
  • Complexity: [LOC, cyclomatic complexity estimate, dependency count]
  • Key Dependencies: [critical imports and their roles]
  • Purpose: [what this code does]
  • Complexity: [LOC, cyclomatic complexity estimate, dependency count]
  • Key Dependencies: [critical imports and their roles]

Architecture Map

Architecture Map

[ASCII diagram of component relationships]
[ASCII diagram of component relationships]

Component Breakdown

Component Breakdown

[Component 1]

[Component 1]

  • Responsibility: [SRP description]
  • Input: [what it receives]
  • Output: [what it produces]
  • Internal Logic: [step-by-step breakdown]
  • Edge Cases: [identified boundary conditions]
  • Concerns: [potential issues]
  • Responsibility: [SRP description]
  • Input: [what it receives]
  • Output: [what it produces]
  • Internal Logic: [step-by-step breakdown]
  • Edge Cases: [identified boundary conditions]
  • Concerns: [potential issues]

Data Flow

Data Flow

[Input] → [Transform 1] → [Transform 2] → [Output]
[Input] → [Transform 1] → [Transform 2] → [Output]

Findings

Findings

IDCategorySeverityDescriptionLocation
1[type][level][detail][file:line]
IDCategorySeverityDescriptionLocation
1[type][level][detail][file:line]

Recommendations

Recommendations

[Prioritized list of improvements]
undefined
[Prioritized list of improvements]
undefined

Mode B: System Analysis

模式B: 系统分析

For analyzing architectures, infrastructure, or multi-service systems.
Process:
  1. Map all system components and their interactions
  2. Identify data flows, protocols, and integration points
  3. Evaluate scalability, reliability, and security posture
  4. Stress-test mentally with failure scenarios
  5. Compare against established architectural patterns
Output structure:
markdown
undefined
用于分析架构、基础设施或多服务系统。
流程:
  1. 梳理 所有系统组件及其交互关系
  2. 识别 数据流、协议和集成点
  3. 评估 可扩展性、可靠性和安全态势
  4. 模拟压力测试 用故障场景进行模拟压力测试
  5. 对比 与现有架构模式做对比
输出结构:
markdown
undefined

System Analysis: [system name]

System Analysis: [system name]

Architecture Overview

Architecture Overview

[High-level description + ASCII diagram]
[High-level description + ASCII diagram]

Component Registry

Component Registry

ComponentTypeResponsibilityDependenciesHealth
ComponentTypeResponsibilityDependenciesHealth

Data Flow Analysis

Data Flow Analysis

[How data moves through the system, including edge cases]
[How data moves through the system, including edge cases]

Failure Mode Analysis

Failure Mode Analysis

Failure ScenarioImpactCurrent MitigationGap
Failure ScenarioImpactCurrent MitigationGap

Scalability Assessment

Scalability Assessment

[Current limits, bottlenecks, scaling strategy]
[Current limits, bottlenecks, scaling strategy]

Security Surface

Security Surface

[Attack vectors, authentication flow, data protection]
undefined
[Attack vectors, authentication flow, data protection]
undefined

Mode C: Concept Analysis

模式C: 概念分析

For analyzing technical concepts, frameworks, or methodologies.
Process (5-Part Codex Structure):
Inspired by Loti's Codex Engine academic paper structure:
  1. Thesis: Core definition and significance (what is it, why does it matter)
  2. Multi-Vector Analysis: Examine from 3+ independent perspectives
  3. Terminology Map: Define all key terms and their relationships
  4. Causal Chain: How did this emerge? What does it enable? What are the consequences?
  5. Synthesis: Integrated understanding with practical implications
Output structure:
markdown
undefined
用于分析技术概念、框架或方法论。
流程（五部分Codex结构）:
灵感来源于Loti的Codex Engine学术论文结构:
  1. 论点: 核心定义与意义（是什么，为什么重要）
  2. 多维度分析: 从至少3个独立视角进行研究
  3. 术语映射: 定义所有关键术语及其关系
  4. 因果链: 它是如何产生的？它能实现什么？会带来什么后果？
  5. 综合: 整合理解，给出实际应用启示
输出结构:
markdown
undefined

Concept Analysis: [topic]

Concept Analysis: [topic]

1. Thesis

1. Thesis

[Core definition and why it matters — 2-3 paragraphs]
[Core definition and why it matters — 2-3 paragraphs]

2. Multi-Vector Analysis

2. Multi-Vector Analysis

Perspective A: [Technical]

Perspective A: [Technical]

[Analysis from technical standpoint]
[Analysis from technical standpoint]

Perspective B: [Practical]

Perspective B: [Practical]

[Analysis from practitioner standpoint]
[Analysis from practitioner standpoint]

Perspective C: [Historical/Ecosystem]

Perspective C: [Historical/Ecosystem]

[Analysis from evolution standpoint]
[Analysis from evolution standpoint]

3. Terminology Map

3. Terminology Map

TermDefinitionRelationship
TermDefinitionRelationship

4. Causal Chain

4. Causal Chain

[Predecessor] → [This concept] → [What it enables] ↓ [Side effects / Trade-offs]
[Predecessor] → [This concept] → [What it enables] ↓ [Side effects / Trade-offs]

5. Synthesis

5. Synthesis

[Integrated understanding + practical takeaways]
undefined
[Integrated understanding + practical takeaways]
undefined

When to Use

适用场景

  • Before modifying unfamiliar code — understand first, change later
  • Evaluating whether to adopt a technology or framework
  • Onboarding to a new codebase or project
  • Producing technical documentation or architecture guides
  • When someone asks "how does X work?" and the answer is non-trivial
  • Post-incident analysis of complex failures
  • 修改陌生代码前：先理解，再修改
  • 评估是否要采纳某项技术或框架
  • 新代码库或项目的上手接入
  • 编写技术文档或架构指南
  • 当有人问“X是怎么工作的”且答案并不浅显时
  • 复杂故障的事后分析

When NOT to Use

不适用场景

  • Simple code that's self-explanatory
  • When speed matters more than depth (use quick Read instead)
  • For decision-making (use 
    creativity-sampler
    or 
    adversarial-review
    )
  • For fact-checking (use 
    cross-verified-research
    )
  • When the goal is to find flaws and challenge decisions (use 
    adversarial-review
    — it attacks; this skill understands)
  • 不言自明的简单代码
  • 对速度的要求高于深度时（请使用快速Read工具）
  • 需要做决策时（请使用
    creativity-sampler
    或
    adversarial-review
    ）
  • 需要事实核查时（请使用
    cross-verified-research
    ）
  • 目标是发现缺陷和质疑决策时（请使用
    adversarial-review
    ——它负责质疑，本技能负责理解）

Integration Notes

集成说明

  • Before adversarial-review: Deep dive first to understand, then adversarial-review to challenge
  • Before creativity-sampler: Understand the problem space deeply, then explore alternatives
  • With skill-composer: Commonly the first step in research-to-decision pipelines
  • 使用adversarial-review前: 先进行深度拆解理解，再用adversarial-review进行质疑
  • 使用creativity-sampler前: 先深入理解问题领域，再探索替代方案
  • 与skill-composer搭配使用: 通常是研究到决策流水线的第一步