by liangdabiao
Use the claude code agent framework to implement deep research step by step! Very powerful and simple skills. I will introduce the implementation of deep research step by step, because deep research is the first application of the agent framework. Comparing various frameworks to implement deep research, you will know which framework is really powerful.
# Add to your Claude Code skills
git clone https://github.com/liangdabiao/Claude-Code-Deep-Research-mainA sophisticated multi-agent research framework that implements OpenAI's Deep Research and Google Gemini's Deep Research capabilities using Claude Code's native features.
This project leverages Claude Code's Skills and Commands system to conduct comprehensive, citation-backed research through:
git clone <repository-url>
cd Claude-Code-Deep-Research-main
.claude/ directoryThe simplest way to conduct deep research:
/deep-research [your research topic]
Example:
/deep-research AI applications in clinical diagnosis
This single command will:
RESEARCH/[topic]/ directoryFor more control over the research process:
/refine-question Should I use WebAssembly for my project?
The Question Refiner will ask 5-6 clarifying questions about:
/plan-research [structured prompt from step 1]
Creates a detailed execution plan showing:
/deep-research [your topic]
/synthesize-findings RESEARCH/[topic]/research_notes/
/validate-citations RESEARCH/[topic]/full_report.md
claude-code-deep-research/
├── .claude/
│ ├── skills/ # Research skills
│ │ ├── question-refiner/ # Question refinement
│ │ ├── research-executor/ # Main research execution
│ │ ├── got-controller/ # Graph of Thoughts controller
│ │ ├── citation-validator/ # Citation validation
│ │ └── synthesizer/ # Research synthesis
│ ├── commands/ # User commands
│ │ ├── deep-research.md # Main research command
│ │ ├── refine-question.md # Question refinement
│ │ ├── plan-research.md # Research planni...