Skip to main content
skill CX Codex

deep-research · claude-office-skills — Claude Code skill: structured research reports

Runs a topic through five research phases and returns a structured report with findings, recommendations and sources. Useful when you need analysis, not a link dump.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add claude-office-skills/skills --skill deep-research -a claude-code
Open on GitHub

What deep-research does

The skill lays out a five-phase method: scope the question, gather material, analyse it by theme, synthesise insights, then write the report. Market and industry topics get a PESTEL pass, anything else gets 5W1H and an argument map with counter-arguments. Output follows a markdown template — executive summary, table of contents, analysis sections, conclusions, recommendations, sources.

You pick the shape of the deliverable: an executive brief, a standard report, a deep dive, or slide-ready bullets. Scope, perspectives and depth are set by the person asking, so the same skill covers a quick overview and a long investigation.

There is no live internet access unless search tools are wired in. Surveys and interviews are out, paywalled databases are out, and the skill does not promise that synthesised facts are correct — verify anything that feeds a real decision. Export to docx and xlsx is listed through the office-mcp server and its create_docx and create_xlsx tools.

What it helps with

  • break an unfamiliar topic into sub-questions and boundaries
  • collect arguments for and against a single question
  • turn scattered notes into a report with a table of contents
  • run a PESTEL pass over a market or industry
  • pull conclusions and recommendations out of gathered material

Example prompts for the agent

  • Do a deep research pass on the risks quantum computing poses to cryptography. Standard report format.
  • Write an executive brief on AI adoption in customer service, covering business and technical angles.
  • Analyse universal basic income with PESTEL and give me slide-ready bullets.

How to install deep-research

1Skills CLI (Vercel)

npx skills add claude-office-skills/skills --skill deep-research -a claude-code

2Manually: put the files in place

~/.claude/skills/deep-research/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/deep-research/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about deep-research

How do I install deep-research in Claude?

Run npx skills add claude-office-skills/skills --skill deep-research -a claude-code. The skill file then lives at ~/.claude/skills/deep-research/SKILL.md.

What does deep-research do?

It walks a topic through five research phases and packages the result as a structured report: executive summary, analysis sections, conclusions, recommendations and sources.

Does the skill need internet access?

No, it has no real-time access on its own. If you need fresh data, search tools have to be connected separately.

Source text

SKILL.md · MIT
---
# ═══════════════════════════════════════════════════════════════════════════════
# CLAUDE OFFICE SKILL - Deep Research
# ═══════════════════════════════════════════════════════════════════════════════

name: deep-research
description: "Conduct comprehensive research on any topic. Synthesize information from multiple angles, provide structured analysis, and generate detailed research reports."
version: "1.0.0"
author: claude-office-skills
license: MIT

category: research
tags:
  - research
  - analysis
  - synthesis
  - report
  - investigation
department: Research/Strategy

models:
  recommended:
    - claude-sonnet-4
    - claude-opus-4
  compatible:
    - claude-3-5-sonnet
    - gpt-4
    - gpt-4o

mcp:
  server: office-mcp
  tools:
    - create_docx
    - create_xlsx

capabilities:
  - topic_research
  - information_synthesis
  - multi_perspective_analysis
  - report_generation
  - source_compilation

languages:
  - en
  - zh

related_skills:
  - web-search
  - academic-search
  - company-research
  - competitive-analysis
---

# Deep Research Skill

## Overview

I help you conduct comprehensive, multi-faceted research on any topic. I analyze information from multiple perspectives, synthesize findings, and deliver structured research reports suitable for decision-making.

**What I can do:**
- Systematic topic exploration
- Multi-angle analysis (pros/cons, different viewpoints)
- Information synthesis and structuring
- Key insight extraction
- Comprehensive report generation
- Source organization and citation

**What I cannot do:**
- Access real-time internet (unless tools provided)
- Conduct primary research (surveys, interviews)
- Access paywalled or proprietary databases
- Guarantee 100% accuracy of synthesized information

---

## How to Use Me

### Step 1: Define Research Question

Provide:
- Main research question or topic
- Specific sub-questions (if any)
- Context and purpose of research
- Any constraints or focus areas

### Step 2: Set Research Parameters

- **Scope**: Broad overview vs. narrow deep-dive
- **Perspectives**: Technical, business, social, legal, etc.
- **Time frame**: Historical, current, future-focused
- **Depth**: Surface-level vs. comprehensive

### Step 3: Specify Output Format

- **Executive Brief**: 1-2 page summary
- **Standard Report**: 5-10 page comprehensive report
- **Deep Dive**: 15+ page detailed analysis
- **Presentation**: Slide-ready bullet points

---

## Research Methodology

### Phase 1: Scoping
```
1. Understand the research question
2. Identify key concepts and terms
3. Define boundaries and constraints
4. Establish success criteria
```

### Phase 2: Information Gathering
```
1. Explore primary aspects of the topic
2. Identify relevant subtopics
3. Collect diverse perspectives
4. Note key facts, data, and quotes
```

### Phase 3: Analysis
```
1. Organize information by theme
2. Identify patterns and trends
3. Compare different viewpoints
4. Assess reliability and bias
```

### Phase 4: Synthesis
```
1. Develop key insights
2. Draw conclusions
3. Identify gaps and limitations
4. Formulate recommendations
```

### Phase 5: Reporting
```
1. Structure findings logically
2. Present balanced perspectives
3. Cite sources appropriately
4. Provide actionable takeaways
```

---

## Research Frameworks

### PESTEL Analysis (for market/industry topics)
| Factor | Questions to Explore |
|--------|---------------------|
| Political | Regulations, government policy, political stability |
| Economic | Growth, inflation, employment, currency |
| Social | Demographics, culture, consumer behavior |
| Technological | Innovation, automation, R&D |
| Environmental | Sustainability, climate, resources |
| Legal | Laws, compliance, litigation |

### 5W1H Framework (for any topic)
- **What**: Definition, scope, components
- **Why**: Causes, motivations, rationale
- **Who**: Stakeholders, actors, affected parties
- **When**: Timeline, milestones, history
- **Where**: Geography, context, application
- **How**: Mechanisms, processes, methods

### Argument Mapping
```
Claim: [Main thesis or finding]
├── Supporting Evidence 1
│   └── Source & strength
├── Supporting Evidence 2
│   └── Source & strength
├── Counter-argument 1
│   └── Rebuttal
└── Counter-argument 2
    └── Rebuttal
```

---

## Output Format

```markdown
# Research Report: [Topic]

**Research Question**: [Main question being addressed]
**Date**: [Date]
**Prepared by**: AI Research Assistant

---

## Executive Summary

[3-5 sentence overview of key findings and conclusions]

**Key Findings**:
1. [Finding 1]
2. [Finding 2]
3. [Finding 3]

**Recommendation**: [Brief actionable recommendation]

---

## Table of Contents

1. Introduction
2. Background
3. [Main Section 1]
4. [Main Section 2]
5. [Main Section 3]
6. Analysis & Discussion
7. Conclusions
8. Recommendations
9. Sources & Further Reading

---

## 1. Introduction

### Research Objective
[What this research aims to accomplish]

### Scope & Boundaries
[What is and isn't covered]

### Methodology
[How the research was conducted]

---

## 2. Background

### Context
[Relevant background information]

### Key Terms & Definitions
| Term | Definition |
|------|------------|
| [Term 1] | |
| [Term 2] | |

### Historical Overview
[Brief history if relevant]

---

## 3. [Main Section 1]

### Overview
[Introduction to this aspect]

### Key Points

#### [Subsection 1.1]
[Detailed analysis]

#### [Subsection 1.2]
[Detailed analysis]

### Summary
[Key takeaways from this section]

---

## 4. [Main Section 2]

[Similar structure...]

---

## 5. [Main Section 3]

[Similar structure...]

---

## 6. Analysis & Discussion

### Key Patterns & Trends
[Patterns identified across the research]

### Multiple Perspectives

#### Perspective A: [Viewpoint]
[Analysis of this viewpoint]

#### Perspective B: [Viewpoint]
[Analysis of this viewpoint]

### Strengths & Weaknesses
| Strengths | Weaknesses |
|-----------|------------|
| | |

### Gaps & Limitations
[What the research couldn't fully address]

---

## 7. Conclusions

### Main Findings
1. [Conclusion 1]
2. [Conclusion 2]
3. [Conclusion 3]

### Implications
[What these findings mean for the reader]

---

## 8. Recommendations

### Immediate Actions
1. [Action 1]
2. [Action 2]

### Further Research Needed
1. [Area 1]
2. [Area 2]

---

## 9. Sources & Further Reading

### Primary Sources
1. [Source 1]
2. [Source 2]

### Additional Resources
1. [Resource 1]
2. [Resource 2]

---

## Appendices

### Appendix A: [Supporting Data]
### Appendix B: [Detailed Analysis]

---

*Research conducted using AI-assisted analysis. Findings should be verified with primary sources for critical decisions.*
```

---

## Example Research Topics

1. **Technology**: "What are the implications of quantum computing for cybersecurity?"
2. **Business**: "How are companies successfully implementing AI in customer service?"
3. **Policy**: "What are the pros and cons of universal basic income?"
4. **Science**: "What is the current state of CRISPR gene editing technology?"
5. **Market**: "What factors are driving the growth of electric vehicles?"

---

## Tips for Better Results

1. **Be specific** about your research question
2. **Provide context** about why you need this research
3. **Specify perspectives** you want explored
4. **Indicate depth** required (overview vs deep dive)
5. **Ask for sources** if you need to verify information
6. **Request multiple viewpoints** for balanced analysis

---

## Limitations

- Cannot access real-time web data
- Cannot access paywalled content
- Knowledge has a training cutoff date
- Cannot conduct primary research
- May have biases in synthesized information
- Cannot guarantee accuracy of all facts

---

*Built by the Claude Office Skills community. Contributions welcome!*

© claude-office-skills · MIT · claude-office-skills/skills

Similar skills

Everything for Science and research →

deep-research by other authors comes first.

deep-research affaan-m Turns a vague “research this” request into a cited report: sub-questions, 15–30 sources, an inline reference under each finding and a confidence level. CX Codex +1 5,100installs deep-research bytedance A skill for thorough web research using multi-angle analysis methodology. Use it instead of basic search when you need to understand a topic from all angles before writing content or tackling a complex question. CX Codex +1 2,800installs deep-research 199-biotechnologies Runs multi-stage research, checks claims against sources, and assembles structured reports. Use it for complex analysis and comparisons, not quick lookups. CX Codex +1 10,200installs deep-research ruvnet Orchestrates multi-phase research using web search, codebase analysis, and memory storage. It generates structured findings with evidence ratings for complex topics. CX Codex +1 893installs deep-research HKUSTDial Runs a topic investigation in the shape of a survey paper: pins the questions, searches from several angles, checks every reference and answers each question in the final report. Useful before you commit to a topic. CX Codex +1 496installs github-deep-research bytedance Runs multi-round research on any GitHub repository and writes a structured markdown report with a timeline, metrics and Mermaid diagrams. CX Codex +1 2,900installs research-summarizer Alireza Rezvani Turns papers, market research, user interviews and competitive analysis into short, structured takeaways you can act on. ★ 28,733repo stars academic-deep-research kesslerio A skill that runs multi-step research: two search cycles per theme, an evidence hierarchy and APA 7 citations. Useful for literature reviews and competitive intelligence. CX Codex +1 560installs research-workflow agent-skills Walks an agent through planning, multiple search queries, source checks and a written synthesis. Useful when you need a report instead of one quick lookup. CX Codex +1 519installs synthesize-research official anthropics This skill turns interview notes, survey responses and support tickets into a structured synthesis with themes, frequency counts and priorities. Useful when the pile of feedback has outgrown your ability to read it. CX Codex +1 3,000installs firecrawl-deep-research firecrawl Turns a hard topic into a cited analytical report: it gathers sources from the open web with Firecrawl, works several angles and links the evidence. CX Codex +1 35,400installs

From the same set109

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor