analyze

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

<Purpose> Analyze performs deep investigation of architecture, bugs, performance issues, and dependencies. It routes to the architect agent or Codex MCP for thorough analysis and returns structured findings with evidence. </Purpose>

<Use_When>

User says "analyze", "investigate", "debug", "why does", or "what's causing"
User needs to understand a system's architecture or behavior before making changes
User wants root cause analysis of a bug or performance issue
User needs dependency analysis or impact assessment for a proposed change
A complex question requires reading multiple files and reasoning across them </Use_When>

<Do_Not_Use_When>

User wants code changes made -- use executor agents or
```
ralph
```
instead
User wants a full plan with acceptance criteria -- use
```
plan
```
skill instead
User wants a quick file lookup or symbol search -- use
```
explore
```
agent instead
User asks a simple factual question that can be answered from one file -- just read and answer directly </Do_Not_Use_When>

<Why_This_Exists> Deep investigation requires a different approach than quick lookups or code changes. Analysis tasks need broad context gathering, cross-file reasoning, and structured findings. Routing these to the architect agent or Codex ensures the right level of depth without the overhead of a full planning or execution workflow. </Why_This_Exists>

<Execution_Policy>

Prefer Codex MCP for analysis when available (faster, lower cost)
Fall back to architect Claude agent when Codex is unavailable
Always provide context files to the analysis tool for grounded reasoning
Return structured findings, not just raw observations </Execution_Policy>

<Steps> 1. **Identify the analysis type**: Architecture, bug investigation, performance, or dependency analysis 2. **Gather relevant context**: Read or identify the key files involved 3. **Route to analyzer**: - Preferred: `ask_codex` with `agent_role: "architect"` and relevant `context_files` - Fallback: `Task(subagent_type="oh-my-claudecode:architect", model="opus", prompt="Analyze: ...")` 4. **Return structured findings**: Present the analysis with evidence, file references, and actionable recommendations </Steps>

<Tool_Usage>

Before first MCP tool use, call
```
ToolSearch("mcp")
```
to discover deferred MCP tools
Use
```
ask_codex
```
with
```
agent_role: "architect"
```
as the preferred analysis route
Pass
```
context_files
```
with all relevant source files for grounded analysis
Use
```
Task(subagent_type="oh-my-claudecode:architect", model="opus", ...)
```
as fallback when ToolSearch finds no MCP tools or Codex is unavailable
For broad analysis, use
```
explore
```
agent first to identify relevant files before routing to architect </Tool_Usage>

<Examples> <Good> User: "analyze why the WebSocket connections drop after 30 seconds" Action: Gather WebSocket-related files, route to architect with context, return root cause analysis with specific file:line references and a recommended fix. Why good: Clear investigation target, structured output with evidence. </Good> <Good> User: "investigate the dependency chain from src/api/routes.ts" Action: Use explore agent to map the import graph, then route to architect for impact analysis. Why good: Uses explore for fact-gathering, architect for reasoning. </Good> <Bad> User: "analyze the auth module" Action: Returning "The auth module handles authentication." Why bad: Shallow summary without investigation. Should examine the module's structure, patterns, potential issues, and provide specific findings with file references. </Bad> <Bad> User: "fix the bug in the parser" Action: Running analysis skill. Why bad: This is a fix request, not an analysis request. Route to executor or ralph instead. </Bad> </Examples>

<Escalation_And_Stop_Conditions>

If analysis reveals the issue requires code changes, report findings and recommend using
```
ralph
```
or executor for the fix
If the analysis scope is too broad ("analyze everything"), ask the user to narrow the focus
If Codex is unavailable and the architect agent also fails, report what context was gathered and suggest manual investigation paths </Escalation_And_Stop_Conditions>

<Final_Checklist>

Analysis addresses the specific question or investigation target
Findings reference specific files and line numbers where applicable
Root causes are identified (not just symptoms) for bug investigations
Actionable recommendations are provided
Analysis distinguishes between confirmed facts and hypotheses </Final_Checklist>

Task: {{ARGUMENTS}}

<Purpose> Analyze（分析）功能可对架构、Bug、性能问题及依赖项展开深度调查。它会将任务转交给architect agent（架构师代理）或Codex MCP进行全面分析，并返回带有证据的结构化调查结果。 </Purpose>

<Use_When>

用户提及“analyze”“investigate”“debug”“why does”或“what's causing”等词汇时
用户需要在进行变更前了解系统的架构或行为时
用户希望对Bug或性能问题进行根本原因分析时
用户需要对拟议变更进行依赖项分析或影响评估时
复杂问题需要读取多个文件并进行跨文件推理时 </Use_When>

<Do_Not_Use_When>

用户希望进行代码变更时——请改用executor agents或
```
ralph
```
用户需要包含验收标准的完整计划时——请改用
```
plan
```
技能
用户需要快速文件查找或符号搜索时——请改用
```
explore
```
agent
用户提出可从单个文件中找到答案的简单事实性问题时——直接读取并作答即可 </Do_Not_Use_When>

<Why_This_Exists> 深度调查所需的方法与快速查找或代码变更不同。分析任务需要广泛收集上下文、进行跨文件推理，并生成结构化调查结果。将这些任务转交给architect agent或Codex，可确保达到合适的深度，同时避免完整规划或执行工作流带来的额外开销。 </Why_This_Exists>

<Execution_Policy>

若可用，优先使用Codex MCP进行分析（速度更快、成本更低）
当Codex不可用时，回退使用architect Claude agent
始终向分析工具提供上下文文件，以实现基于事实的推理
返回结构化调查结果，而非仅原始观察数据 </Execution_Policy>

<Steps> 1. **确定分析类型**：架构分析、Bug调查、性能分析或依赖项分析 2. **收集相关上下文**：读取或确定涉及的关键文件 3. **转交给分析工具**: - 首选方式：调用`ask_codex`，设置`agent_role: "architect"`并传入相关`context_files` - 回退方式：创建`Task(subagent_type="oh-my-claudecode:architect", model="opus", prompt="Analyze: ...")` 4. **返回结构化调查结果**：呈现带有证据、文件引用和可操作建议的分析内容 </Steps>

<Tool_Usage>

在首次使用MCP工具前，调用
```
ToolSearch("mcp")
```
以发现延迟加载的MCP工具
优先使用设置
```
agent_role: "architect"
```
的
```
ask_codex
```
作为分析路径
传入包含所有相关源文件的
```
context_files
```
，以实现基于事实的分析
当ToolSearch未找到MCP工具或Codex不可用时，使用
```
Task(subagent_type="oh-my-claudecode:architect", model="opus", ...)
```
作为回退方案
对于大范围分析，先使用
```
explore
```
agent确定相关文件，再转交给architect agent </Tool_Usage>

<Examples> <Good> 用户：“analyze why the WebSocket connections drop after 30 seconds” 操作：收集与WebSocket相关的文件，将任务转交给带有上下文的architect agent，返回包含具体文件:行号引用及建议修复方案的根本原因分析。为何优秀：调查目标明确，输出结果结构化且带有证据。 </Good> <Good> 用户：“investigate the dependency chain from src/api/routes.ts” 操作：使用explore agent映射导入链，然后转交给architect agent进行影响分析。为何优秀：先用explore agent收集事实，再用architect agent进行推理。 </Good> <Bad> 用户：“analyze the auth module” 操作：返回“The auth module handles authentication.” 为何不佳：仅为浅层摘要，未进行深入调查。应检查模块的结构、模式、潜在问题，并提供带有文件引用的具体调查结果。 </Bad> <Bad> 用户：“fix the bug in the parser” 操作：运行分析技能。为何不佳：这是一个修复请求，而非分析请求。应转交给executor或ralph处理。 </Bad> </Examples>

<Escalation_And_Stop_Conditions>

若分析发现问题需要进行代码变更，报告调查结果并建议使用
```
ralph
```
或executor进行修复
若分析范围过宽（如“analyze everything”），请用户缩小关注范围
若Codex不可用且architect agent也失败，报告已收集的上下文并建议手动调查路径 </Escalation_And_Stop_Conditions>

<Final_Checklist>

分析内容针对具体问题或调查目标
调查结果在适用情况下引用了具体文件和行号
针对Bug调查，已确定根本原因（而非仅症状）
提供了可操作的建议
分析区分了已确认的事实与假设 </Final_Checklist>

任务：{{ARGUMENTS}}