Multi-Topic In-Depth Research Skill

Overview

An intelligent multi-topic in-depth research tool that automatically analyzes materials and generates systematic research documents. It supports input of any materials, and forms a streamlined research knowledge base by launching multiple independent research Agents in parallel for in-depth retrieval.

Core Principles:

Only perform information retrieval, induction and professional expression conversion
Do not add new facts or fabricate information
Focus on single issues, output streamlined content that suffices to solve the problem
Universal design, applicable to fields such as law, business, technology, academia, etc.

Trigger Conditions

Trigger with the

/multi-search

command, or when the user requests:

In-depth research on multiple related topics
Systematic information retrieval
Integration of multi-angle analysis
Generation of structured research reports

Input Formats

Method 1: Based on Files

/multi-search @document-path.md

Method 2: Direct Paste

/multi-search
[paste material content]

Method 3: Specify Topics

/multi-search
Project: [Project Name]
Research Topics:
1. [Topic 1]
2. [Topic 2]
3. [Topic 3]

Processing Flow

Phase 1: Analysis & Preparation

Read input materials
Extract research topic list
- With explicit topics: use directly
- Without explicit topics: automatically extract from materials
Topic splitting principles:
- Clear direction: Each topic corresponds to a unique retrieval direction
- Avoid overlap: Ensure no duplicate retrieval keywords between topics
- Focus on problem: Each topic solves one specific problem
Confirm project name and output location

Phase 2: Intelligent Output Directory Detection

Detect project structure by priority:

Priority detection:
```
output/
```
directory → Use
```
output/[Project Name]/
```
Secondary detection: Current working directory → Use
```
./[Project Name]/
```
Fallback solution: User's current directory → Use
```
./research/
```

Create directory:

[Output Directory]/03 - 🔍 In-Depth Research/

Phase 3: Parallel In-Depth Research

Launch independent

general-purpose

research Agents for each research topic.

Context Transfer (Main Agent → Independent Research Agent):

Key project information (background, objectives, core issues)
Complete topic list and retrieval scope for each topic
Assigned keyword directions (basis for avoiding duplicates)
Specific requirement background

Duplication Check Mechanism:

Each independent research Agent must follow this process before starting retrieval:

Pre-retrieval Declaration:
- Declare in the current context: "I will retrieve [Keyword A, Keyword B] for researching [Topic Name]"
- Wait for confirmation from the Main Agent that there is no duplication before starting
Main Agent Review:
- Check if the keywords declared by the Agent overlap with already assigned directions
- If duplication is found, notify the Agent to switch to other directions promptly
Dynamic Adjustment:
- If a direction has been covered by other Agents, this Agent should switch to a related but different angle
- Record the adjusted retrieval direction

In-Depth Retrieval Requirements:

4-6 rounds of in-depth retrieval
Automatically select WebSearch (search discovery) or WebFetch (full content acquisition)
Differentiated keywords to ensure each Agent covers a unique angle

Document Generation:

Focus on solving a single core problem
Concise and clear, sufficient to solve the problem
Include key source links
Provide directly usable conclusions and suggestions

Phase 4: Integration & Output

Generate research overview document (000.Research Overview.md)
Integrate core findings from all independent research Agents
Create navigation links between documents
Add comprehensive suggestions and immediate action checklist

Output Formats

Directory Structure

[Output Directory]/
└── [Project Name]/
    └── 03 - 🔍 In-Depth Research/
        ├── 000.Research Overview.md
        ├── YYMMDD [Research Topic 1].md
        ├── YYMMDD [Research Topic 2].md
        └── ...

Overview Document Format

markdown

# [Project Name] In-Depth Research Overview

**Generation Time**: YYYY-MM-DD
**Research Method**: N independent research Agents, each conducting 4-6 rounds of in-depth retrieval
**Total Retrieval Rounds**: XX+ rounds
**Total Document Size**: XX KB

---

## Research Results List

### Completed N Streamlined Research Reports

| No. | Research Topic | File Size | Core Value |
|------|---------|---------|---------|
| 01 | [Topic 1](./YYMMDD%20Topic%201.md) | XX KB | Brief description |

---

## Core Findings

### Finding 1: [Most Important Finding]

**Basis**: [Brief explanation]

**Conclusion**: [Specific conclusion]

---

## Comprehensive Suggestions

### 1. Strategic Recommendations

**Recommended Solution**: [Specific plan]

### 2. Immediate Action Checklist

- [ ] Action Item 1
- [ ] Action Item 2

Detailed Research Document Format

markdown

# [Research Topic Title]

**Generation Time**: YYYY-MM-DD
**Research Depth**: XX+ rounds of in-depth retrieval, covering XXXX, XXXX, XXXX

---

## Core Conclusion

[Most important findings and conclusions, 2-3 paragraphs, sufficiently detailed]

---

## 1. [Main Content 1]

### (1) Subtitle

Body paragraphs. Use inline link format for citations:
- According to [Source Name](https://link)...
- Based on [Data](https://link)...

---

## 2. [Main Content 2]

[Continue structured content]

---

## 3. Application Suggestions

### (1) Key Suggestions

**Content**: [Specific content]

### (2) Notes

⚠️ [Key Note]

Link Specifications

Core Principle

All source links must be embedded in the corresponding position in the body text

markdown

✅ Correct:
According to [Research Report](https://link)...

❌ Incorrect:
According to a certain report...
(List citations separately at the end of the document)

Link Label Conventions

🔗 → General web resources
📚 → Academic literature
🏛️ → Institutional official websites
📄 → Data sources

Document Naming Specifications

Numbering System

```
00.
```
- Research Overview
```
01-09.
```
- Core Research
```
10-19.
```
- Important Research
```
20+.
```
- Extended Research

Topic Specifications

✅ Use concise Chinese titles
✅ Avoid special characters
✅ Within 15 characters
✅ Clearly reflect the research object

Quality Standards

Independent Research Agent Research Quality

Focus on single problem: Each independent research Agent only solves one core problem
Retrieval depth: 4-6 rounds of retrieval (sufficient is enough)
Streamlined output: Concise and clear, sufficient to solve the problem
Key citations: Cite key sources (sufficient is enough)
Directly usable: Provide directly usable conclusions and suggestions

Document Quality Standards

Clear structure: Hierarchical chapter titles
Coherent narrative: Paragraph-based narration, avoid excessive listing
Accurate links: All links embedded in corresponding positions in the body text
Unified format: Follow unified format specifications
High operability: Provide specific steps, tools, commands

Notes

Prohibited Behaviors

❌ Do not create secondary subdirectories (e.g., "Reference Materials/")
❌ Do not generate separate executive summary files
❌ Do not use excessive bullet point formats
❌ Do not list citations separately at the end of the document
❌ Do not add redundant progress tracking sections

Recommended Practices

✅ Use narrative paragraph expression
✅ Embed links in corresponding positions in the body text
✅ Keep research overview concise
✅ Provide specific action suggestions
✅ Use clear document numbering

Dependencies

This skill relies on built-in tools of Claude Code, no additional configuration required:

WebSearch: Search discovery
WebFetch: Full content acquisition
Task: Launch independent research Agents

Change History

Version	Date	Update Content
v1.0.0	2026-02-15	Migrated from Command to Skill, renamed to Multi-Topic In-Depth Research (multi-search)

multi-search

NPX Install

Tags

SKILL.md Content (Chinese)

Multi-Topic In-Depth Research Skill

Overview

Trigger Conditions

Input Formats

Method 1: Based on Files

Method 2: Direct Paste

Method 3: Specify Topics

Processing Flow

Phase 1: Analysis & Preparation

Phase 2: Intelligent Output Directory Detection

Phase 3: Parallel In-Depth Research

Phase 4: Integration & Output

Output Formats

Directory Structure

Overview Document Format

Detailed Research Document Format

Link Specifications

Core Principle

Link Label Conventions

Document Naming Specifications

Numbering System

Topic Specifications

Quality Standards

Independent Research Agent Research Quality

Document Quality Standards

Notes

Prohibited Behaviors

Recommended Practices

Dependencies

Change History