deep-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Deep Research

深度研究

Orchestrate multi-phase deep research campaigns that gather, cross-reference, and synthesize information from multiple sources.

编排多阶段深度研究任务，从多个来源收集、交叉引用并合成信息。

When to use

使用场景

When you need to investigate a complex topic thoroughly — spanning web sources, codebase patterns, stored memory, and external documentation — and produce a structured synthesis.

当你需要全面调查复杂主题时——涵盖网页来源、代码库模式、存储内存和外部文档——并生成结构化的合成结果。

Steps

步骤

Define research scope — break the question into 3-7 sub-questions that together answer the main question

Search existing knowledge — call

mcp__claude-flow__memory_search_unified

and

mcp__claude-flow__agentdb_pattern-search

to check what's already known

Web research — use
```
WebSearch
```
and
```
WebFetch
```
to gather external information for each sub-question
Codebase analysis — use
```
Bash
```
(grep/find),
```
Read
```
to examine relevant source files
Cross-reference — compare findings across sources, identify agreements and contradictions
Store findings — call
```
mcp__claude-flow__memory_store
```
with namespace
```
research
```
for each key finding
Store patterns — call
```
mcp__claude-flow__agentdb_pattern-store
```
for reusable patterns discovered
Synthesize — produce a structured research report with:
- Executive summary (2-3 sentences)
- Key findings (bulleted)
- Evidence quality assessment (high/medium/low per finding)
- Open questions remaining
- Recommended next steps

定义研究范围——将主问题拆解为3-7个子问题，共同解答主问题

搜索现有知识——调用

mcp__claude-flow__memory_search_unified

和

mcp__claude-flow__agentdb_pattern-search

检查已知信息

网页研究——使用
```
WebSearch
```
和
```
WebFetch
```
为每个子问题收集外部信息
代码库分析——使用
```
Bash
```
（grep/find）、
```
Read
```
检查相关源文件
交叉引用——对比不同来源的发现，识别共识与矛盾点
存储发现——调用
```
mcp__claude-flow__memory_store
```
，使用
```
research
```
命名空间存储每个关键发现
存储模式——调用
```
mcp__claude-flow__agentdb_pattern-store
```
存储发现的可复用模式
合成结果——生成结构化研究报告，包含：
- 执行摘要（2-3句话）
- 关键发现（项目符号列表）
- 证据质量评估（每个发现对应高/中/低等级）
- 遗留未解决问题
- 建议下一步行动

Research depth levels

研究深度级别

Quick — memory search + 1-2 web queries, 2-3 minutes
Standard — memory + web + codebase scan, 5-10 minutes
Deep — all sources + cross-referencing + pattern storage, 15-30 minutes
Exhaustive — deep + spawn sub-agents for parallel research threads, 30+ minutes

快速——内存搜索 + 1-2次网页查询，耗时2-3分钟
标准——内存搜索 + 网页搜索 + 代码库扫描，耗时5-10分钟
深度——所有来源 + 交叉引用 + 模式存储，耗时15-30分钟
全面——深度研究 + 生成子Agent进行并行研究线程，耗时30分钟以上

Memory namespaces

内存命名空间

```
research
```
— raw findings keyed by topic
```
research-synthesis
```
— completed synthesis reports
```
research-sources
```
— source URLs and references

```
research
```
——按主题分类的原始发现
```
research-synthesis
```
——已完成的合成报告
```
research-sources
```
——来源URL和参考文献