Overview
Claude Code is an agentic AI assistant that lives in your terminal, designed to help you manage research projects through natural language commands. Unlike traditional AI chat interfaces, Claude Code can directly read files, create folders, run analyses, and manage your entire research workflow. Key Benefits for Research Memex:- File-aware AI: Reference papers with @filename syntax
- Project memory: CLAUDE.md stores your research protocol
- Custom commands: Create slash commands for repetitive tasks
- MCP integration: Connect to Zotero, filesystems, web search
- Autonomous execution: Plan and execute multi-step workflows
- Version control: Built-in Git integration
Not Just for Coding: Despite the name, Claude Code is excellent for research workflows - managing literature, analyzing papers, drafting sections, and organizing complex projects. It’s agentic AI for researchers!
Step 1: Installation
1.1 Prerequisites
System Requirements:- Node.js 18 or newer
- Terminal/command-line access
- Claude.ai account or API key
1.2 Install Claude Code
Via npm (Terminal):Official Documentation: For detailed installation instructions, see Claude Code Overview | GitHub Repository
1.3 Alternative: VS Code Extension
For users who prefer a graphical interface:- Open VS Code
- Install “Claude Code” extension from marketplace
- Configure API key in settings
- Access via sidebar
Step 2: Core Concepts
2.1 What is CLAUDE.md?
CLAUDE.md
is a special file that Claude automatically reads at the start of every conversation. It acts as your project’s “memory” or “constitution.”
What to put in CLAUDE.md:
- Project overview and goals
- File structure explanation
- Research protocol or methodology
- Custom commands you’ve created
- Style guidelines (citation format, writing tone)
- Important context Claude should always know
Best Practice: Keep CLAUDE.md concise and updated. Claude reads this at the start of EVERY conversation, so it should contain essential context, not your entire literature review!
2.2 Plan Mode vs Act Mode
Plan Mode (Default - Recommended):- Claude shows you what it will do BEFORE executing
- You approve/reject each action
- Perfect for learning and complex operations
- Toggle:
Shift+Tab
(Mac/Linux) orAlt+M
(Windows)
- Claude executes immediately
- Faster for trusted operations
- Use for simple tasks (reading files, searches)
Recommendation: Stay in Plan Mode when working with research data! Preview operations before they modify your files.
2.3 File References with @ Syntax
Add files to context:@/literature/
- Adds entire folder to context@CLAUDE.md
- Always available as project memory
Step 3: Creating Custom Slash Commands
3.1 What Are Slash Commands?
Slash commands are reusable prompt templates you create once and invoke with/commandname
. They’re perfect for repetitive research tasks.
Examples for research:
/summarize
- Structured paper summary/compare
- Compare two papers/extract
- Pull out specific information/critique
- Review writing for quality
3.2 Create Your First Command
Step 1: Create the commands folder.claude/commands/summarize.md
:
**ARGUMENTS` keyword gets replaced with whatever you type after the slash command. This makes commands flexible and reusable!
3.3 Useful Research Commands
Create.claude/commands/compare.md
:
.claude/commands/gaps.md
:
Step 4: MCP Servers for Research
MCP (Model Context Protocol) servers extend Claude Code’s capabilities with specialized tools.4.1 Essential MCP Servers for Research
Zotero MCP:- Search your Zotero library from terminal
- Get paper metadata instantly
- Installation: See Zotero Setup Guide
- Already built-in to Claude Code
- Navigate and search project files
- Create and modify documents
- Step-by-step reasoning for complex analysis
- Perfect for theoretical arguments
- Install: Smithery - Sequential Thinking
- Real-time literature discovery
- Verify recent developments
- Fact-checking and citation validation
4.2 Installing MCP Servers
Via Smithery (Easiest):- Visit smithery.ai
- Search for MCP server you want
- Click “Install”
- Follow one-click setup
- Restart Claude Code
~/.config/claude-code/config.json
to add MCP servers.
For complete MCP exploration, see the MCP Explorer Guide
Step 5: Project Structure for Research
5.1 Recommended Folder Structure
General research project:5.2 Setting Up a New Project
Option 1: Ask Claude to do itStep 6: Common Research Workflows
6.1 Literature Analysis
Analyze a single paper:6.2 Data Management
Organize files:6.3 Drafting and Writing
Generate section outlines:Step 7: Keyboard Shortcuts & Navigation
7.1 Essential Shortcuts
Shortcut | Action |
---|---|
Shift+Tab | Toggle Plan/Act mode (Mac/Linux) |
Alt+M | Toggle Plan/Act mode (Windows) |
Esc Esc | Navigate command history (double-tap) |
Ctrl+C | Cancel current operation |
Ctrl+D | Exit Claude Code |
7.2 Command History
Double-tapEsc
to jump back through previous commands:
- Modify and re-run analyses
- Fix typos without retyping
- Compare different approaches quickly
Step 8: Learning Resources
8.1 Official Documentation
- Claude Code Overview - Official intro
- Best Practices Guide - CLAUDE.md tips
- GitHub Repository - Source code and issues
- Latest Updates - New features
8.2 Video Tutorials
Beginner Series:- SeanMatthewAI YouTube Series - Claude Code essentials
- Claude Code Beginners Guide 2025 - Comprehensive walkthrough
- Build a YouTube Research Agent - Slash commands in action
- Cooking with Claude Code - Complete app build
8.3 Online Courses
- DeepLearning.AI: Claude Code - Comprehensive course
- Anthropic Training - Official certification
- DataCamp Tutorial - Practical examples
8.4 Blog Posts & Guides
- How I Use Claude Code - Pro tips from Builder.io
- No-BS Quick Start Guide - July 2025 guide
- ClaudeLog - Best practices collection
Step 9: Integration with Research Memex
9.1 Connect to Zotero
Setup Zotero MCP:- Follow Zotero Setup Guide
- Install Zotero MCP server
- In Claude Code: Search your library with natural language
- Example: “Search my Zotero for papers on AI in education”
9.2 Export Papers for Analysis
From Zotero to Claude Code:- Export papers from Zotero as markdown (via OCR)
- Save to
/literature/
folder - Reference with
@/literature/author2024.md
- Claude can now analyze full text!
9.3 Workflow with Obsidian
Obsidian for synthesis, Claude Code for execution:- Use Obsidian for literature notes
- Export synthesis to markdown
- Move to Claude Code project folder
- Claude Code automates analysis and drafting
Step 10: Example Research Workflows
10.1 General Literature Analysis
Create CLAUDE.md:.claude/commands/analyze.md
:
10.2 Multi-Paper Comparison
Workflow:10.3 Theory Building
Use Sequential Thinking MCP:Step 11: Advanced Features
11.1 Parallel Agents
Run multiple analyses simultaneously:11.2 Git Integration
Built-in version control:11.3 Task Tracking with TodoWrite
Claude Code has built-in task management:Step 12: Troubleshooting
Installation Issues
“npm command not found”- Install Node.js from nodejs.org
- Restart terminal after installation
- Use:
sudo npm install -g @anthropic-ai/claude-code
- Or fix npm permissions: npm docs
CLAUDE.md Not Loading
- Verify filename is exactly
CLAUDE.md
(case-sensitive) - Must be in project root directory
- Restart Claude Code:
exit
thenclaude
Slash Commands Not Working
- Check folder exists:
.claude/commands/
- Verify file naming:
commandname.md
(no slashes) - Restart Claude Code after creating commands
- Test with:
/help
(built-in command)
File References Failing
- Use absolute paths from project root:
@/literature/file.md
- Check filename spelling and case
- Verify file exists:
ls literature/
Step 13: Best Practices for Research
13.1 Project Organization
DRY Principle (Don’t Repeat Yourself):- Create slash commands for repetitive tasks
- Document protocols in CLAUDE.md once
- Reuse across multiple papers/projects
- Use Git for tracking changes
- Commit after major analyses
- Branch for experimental approaches
13.2 Quality Control
Always verify AI outputs:- Check citations against your Zotero library
- Validate statistical claims
- Review for coherence and logic
- See: Failure Museum
- File modifications
- Data extraction
- Writing operations
- Complex multi-step tasks
13.3 Ethical Guidelines
Transparency:- Document AI use in CLAUDE.md
- Track which tasks were AI-assisted
- Maintain audit trail of prompts used
- Never trust AI-generated citations blindly
- Verify every factual claim
- Check for hallucinations and errors
Step 14: Advanced Use Cases
14.1 For Systematic Literature Reviews
For a complete SLR workflow with Claude Code (screening, extraction, PRISMA), see: Claude Code SLR Workflow14.2 For Qualitative Analysis
Coding transcripts:14.3 For Theory Development
Build conceptual frameworks:Checklist
By the end of this guide, you should have:- Installed Claude Code (terminal or VS Code)
- Created a research project folder
- Written a CLAUDE.md file with project context
- Created at least one custom slash command
- Tested file references with @ syntax
- Understood Plan vs Act mode
- Installed at least one MCP server (Zotero or Sequential Thinking)
- Watched at least one tutorial video
- Tested a basic analysis workflow
Next Steps: For a complete example of Claude Code in action, see the SLR Workflow Guide which shows screening, extraction, and synthesis in detail.
Resources
Official Anthropic Resources
Community Resources
Research Memex Integration
- Zotero Setup - Library integration
- MCP Explorer - More MCP servers
- Session 4: Agentic Workflows - Multi-agent systems
- SLR Workflow - Complete example