Claude Data Analysis Assistant
September 29, 2025 ยท View on GitHub
A modern, intelligent data analysis platform built with Claude Code's sub-agents, slash-commands, and hooks. Transform your data analysis workflow with AI-powered assistance.
๐ Quick Start
1. Set Up Your Data
Place your dataset in the data_storage/ directory:
cp your_data.csv ./data_storage/
2. Start Analysis
Use intuitive slash commands to analyze your data:
# Basic exploratory analysis
/analyze user_behavior_sample.csv exploratory
# Create visualizations
/visualize user_behavior_sample.csv all
# Generate analysis code
/generate python data-cleaning
# Create comprehensive report
/report user_behavior_sample.csv complete markdown
๐ฏ Key Features
Intelligent Sub-Agents
- data-explorer: Expert statistical analysis and pattern discovery
- visualization-specialist: Beautiful, insightful charts and graphs
- code-generator: Production-ready analysis code
- report-writer: Comprehensive analysis reports
- quality-assurance: Data validation and quality control
- hypothesis-generator: Research hypothesis and insights
Intuitive Slash Commands
/analyze [dataset] [type]- Perform data analysis/visualize [dataset] [type]- Create visualizations/generate [language] [type]- Generate analysis code/report [dataset] [format]- Generate reports/quality [dataset] [action]- Quality assurance/hypothesis [dataset] [domain]- Generate hypotheses
Automated Workflows
- Data Validation: Automatic quality checks on data upload
- Smart Context: Project-aware analysis suggestions
- Reproducible Analysis: Complete documentation and code generation
๐ Usage Examples
User Behavior Analysis
# Complete analysis workflow
/analyze user_behavior.csv exploratory
/visualize user_behavior.csv trends
/quality user_behavior.csv clean
/report user_behavior.csv complete html
/generate python user-segmentation
Sales Data Analysis
# Sales performance analysis
/analyze sales_data.csv statistical
/visualize sales_data.csv trends
/generate sql revenue-analysis
/report sales_data.csv executive pdf
Customer Analytics
# Customer segmentation
/analyze customer_data.csv predictive
/visualize customer_data.csv distribution
/generate r clustering-analysis
/hypothesis customer_data churn-prediction
๐ ๏ธ Project Structure
claude-data-analysis/
โโโ .claude/
โ โโโ agents/ # Sub-agent configurations
โ โโโ commands/ # Slash command definitions
โ โโโ hooks/ # Automation scripts
โ โโโ settings.json # Claude Code settings
โโโ data_storage/ # Your data files
โโโ visualizations/ # Generated charts
โโโ generated_code/ # Analysis code
โโโ analysis_reports/ # Analysis reports
โโโ examples/ # Example datasets and workflows
โโโ docs/ # Documentation
๐จ Sample Data
The project includes sample data to get you started:
- user_behavior_sample.csv: Sample user behavior data with user actions, devices, locations, and revenue
- Field descriptions: user_id, session_id, timestamp, action, page_url, device_type, location, revenue
๐ง Configuration
Environment Setup
The project uses Claude Code's configuration system. Key settings:
- Hooks: Automated validation and context loading
- Sub-agents: Specialized AI assistants for different tasks
- Commands: Custom slash commands for common operations
Requirements
- Python 3.8+ for data analysis
- Claude Code with sub-agents enabled
- Data files in CSV, JSON, or Excel format
๐ Getting Started Guide
For New Users
- Place your data in
data_storage/ - Run exploratory analysis:
/analyze your_data.csv exploratory - Create visualizations:
/visualize your_data.csv all - Generate report:
/report your_data.csv complete markdown
For Advanced Users
- Customize agents: Modify
.claude/agents/configurations - Create custom commands: Add new commands in
.claude/commands/ - Set up automation: Configure hooks in
.claude/settings.json - Extend functionality: Add custom analysis scripts
๐ฏ Analysis Types
Exploratory Analysis
- Data quality assessment
- Summary statistics
- Pattern discovery
- Initial insights
Statistical Analysis
- Hypothesis testing
- Correlation analysis
- Regression analysis
- Confidence intervals
Predictive Analysis
- Feature importance
- Predictive modeling
- Variable relationships
- Model recommendations
Complete Analysis
- All analysis types
- Comprehensive reports
- Visualizations
- Actionable insights
๐ Visualization Types
All Visualizations
- Comprehensive dashboard
- Multiple chart types
- Interactive exploration
- Executive summary
Specific Charts
- Trends: Time series, moving averages
- Distribution: Histograms, box plots, density plots
- Correlation: Heatmaps, scatter plots, correlation matrices
- Comparison: Bar charts, grouped charts, small multiples
๐ Code Generation
Supported Languages
- Python: Pandas, NumPy, Scikit-learn, Matplotlib
- R: Tidyverse, ggplot2, caret
- SQL: All major dialects
- JavaScript: D3.js, Plotly.js, TensorFlow.js
Analysis Types
- Data cleaning and preprocessing
- Statistical analysis
- Machine learning
- Visualization code
- Custom analysis
๐ Project Status
Current Phase: Week 1.1 - Project Initialization โ
Completed Features
- Project structure and configuration
- Data Explorer sub-agent
- Visualization Specialist sub-agent
- Core slash commands (/analyze, /visualize, /generate)
- Automation hooks
- Sample data and documentation
Upcoming Features
- Report Writer sub-agent
- Quality Assurance sub-agent
- Hypothesis Generator sub-agent
- Advanced slash commands
- Interactive dashboards
- Integration with external tools
๐ค Contributing
We welcome contributions! Please follow these steps:
- Fork the repository
- Create a feature branch
- Add your improvements
- Test your changes
- Submit a pull request
Development Guidelines
- Follow the established code style
- Add comprehensive documentation
- Include unit tests for new features
- Update the README as needed
๐ License
This project is licensed under the MIT License. See the LICENSE file for details.
๐ Acknowledgments
- Built with Claude Code
- Inspired by the DATAGEN project
- Powered by modern data science tools and frameworks
๐ Support
For support and questions:
- Check the documentation in the
docs/directory - Review the examples in
examples/ - Use the
/helpcommand for usage assistance
Start analyzing your data smarter, not harder! ๐