Deep Research logo

Deep Research

Organization
claude-office-skills
deep-research

Conduct comprehensive research on any topic. Synthesize information from multiple angles, provide structured analysis, and generate detailed research reports.

Overview

Publisherclaude-office-skills
Repositoryskills
Skill namedeep-research
Stars
514
Forks
97
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by claude-office-skills on GitHub. Read the source before you install it.

Installation

Install the Deep Research AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/claude-office-skills/skills/tree/main/deep-research
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/claude-office-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/deep-research .claude/skills/deep-research
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Deep Research in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Deep Research on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Deep Research is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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)

FactorQuestions to Explore
PoliticalRegulations, government policy, political stability
EconomicGrowth, inflation, employment, currency
SocialDemographics, culture, consumer behavior
TechnologicalInnovation, automation, R&D
EnvironmentalSustainability, climate, resources
LegalLaws, 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!

Frequently asked questions

What does the Deep Research AI skill do?

Conduct comprehensive research on any topic. Synthesize information from multiple angles, provide structured analysis, and generate detailed research reports.

Why use Deep Research on TypingMind?

Because you install it once and use it with any model. Deep Research is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Deep Research in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/claude-office-skills/skills/tree/main/deep-research. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Deep Research?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Deep Research?

As many as you like. As long as a model supports skills, you can use Deep Research with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Deep Research AI skill free?

Yes. It is published on GitHub by claude-office-skills under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇