Claude Code Deep Research Agent - Implementation Guide
Description
Claude Code Deep Research Agent - Implementation Guide skill
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
Repository README
This is the README for liangdabiao/Claude-Code-Deep-Research-main, shared by 6 entries
in this directory. It describes the repository, not this entry specifically.
Claude Code Deep Research Agent - Implementation Guide
Overview
This guide explains how to use the Claude Code Deep Research Agent framework to conduct comprehensive, multi-agent research with proper citations and high-quality outputs.
Quick Start
1. Basic Usage - Single Command
The simplest way to conduct deep research:
/deep-research [your research topic]
**Example**:
/deep-research AI applications in clinical diagnosis
This command will:
- Refine your research question (ask clarifying questions)
- Create a research plan
- Deploy multiple research agents in parallel
- Synthesize findings into a comprehensive report
- Validate all citations
- Output results to
RESEARCH/[topic]/directory
2. Step-by-Step Usage
For more control, use commands sequentially:
Step 1: Refine Your Question
/refine-question [your raw question]
The Question Refiner will:
- Ask 5-6 clarifying questions
- Understand your specific needs
- Generate a structured research prompt
Step 2: Plan Research (Optional)
/plan-research [structured prompt from Step 1]
This creates a detailed research execution plan showing:
- How the topic will be broken into subtopics
- Which agents will be deployed
- Expected timeline
Step 3: Execute Research
/deep-research [your topic]
Or use the research-executor skill directly with the structured prompt.
Step 4: Synthesize Findings (If needed)
/synthesize-findings RESEARCH/[topic]/research_notes/
Step 5: Validate Citations
/validate-citations RESEARCH/[topic]/full_report.md
Project Structure
claude-code-deep-research/
├── .claude/
│ ├── skills/ # Skills definitions
│ │ ├── question-refiner/ # Question refinement skill
│ │ │ ├── skill.json
│ │ │ ├── instructions.md
│ │ │ └── examples.md
│ │ ├── research-executor/ # Main research execution skill
│ │ │ ├── skill.json
│ │ │ ├── instructions.md
│ │ │ └── examples.md
│ │ ├── got-controller/ # Graph of Thoughts controller
│ │ │ ├── skill.json
│ │ │ ├── instructions.md
│ │ │ └── examples.md
│ │ ├── citation-validator/ # Citation validation skill
│ │ │ ├── skill.json
│ │ │ ├── instructions.md
│ │ │ └── examples.md
│ │ └── synthesizer/ # Research synthesis skill
│ │ ├── skill.json
│ │ ├── instructions.md
│ │ └── examples.md
│ └── commands/ # User-facing commands
│ ├── deep-research/ # Main deep research command
│ ├── refine-question/ # Question refinement command
│ ├── plan-research/ # Research planning command
│ ├── validate-citations/ # Citation validation command
│ └── synthesize-findings/ # Synthesis command
├── CLAUDE.md # Main documentation
├── CLAUDE2.md # GoT framework documentation
├── PROJECT_
Related Skills
Awesome Go
A curated list of awesome Go frameworks, libraries and software
Development next.js
| The React Framework | 138360 | 1503 | 1 |
Development sharing-skills
skill for guidance.
Development root-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger.
Development Template Skill
Minimal skeleton for a new skill project structure.
Development Third-party Notices
THE FOLLOWING SETS FORTH ATTRIBUTION NOTICES FOR THIRD PARTY SOFTWARE THAT MAY BE CONTAINED IN PORTIONS OF THI
Development