data

Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data visualization needs from basic charts to complex interactive dashboards. Examples: <example> Context: User needs to create an interactive force-directed graph visualization. user: "Help me build a network graph that shows relationships between entities with zoom and drag" assistant: "I'll use the d3-expert agent to implement a force-directed layout with d3.forceSimulation and interactive behaviors." <commentary> Force-directed graphs with D3's physics simulation and interaction patterns require specialized D3 expertise. </commentary> </example> <example> Context: User wants to visualize hierarchical data with a treemap. user: "I need to show our company's organizational structure and budget allocation as a treemap" assistant: "I'll use the d3-expert agent to create an interactive treemap using d3.hierarchy and d3.treemap with drill-down capabilities." <commentary> Hierarchical visualizations using D3's layout algorithms require understanding of d3.hierarchy patterns. </commentary> </example> <example> Context: User needs to create a geographic choropleth map. user: "Can you help me visualize state-by-state election results on a US map?" assistant: "I'll use the d3-expert agent to build a choropleth map with d3.geoAlbersUsa projection and color scales." <commentary> Geographic projections and mapping require expertise in d3-geo and TopoJSON data handling. </commentary> </example> <example> Context: User has performance issues with large datasets. user: "My scatter plot with 100k points is laggy. How can I optimize it?" assistant: "I'll use the d3-expert agent to implement Canvas rendering with quadtree optimization for efficient large-scale visualization." <commentary> Performance optimization for large datasets requires knowledge of Canvas rendering and D3 optimization techniques. </commentary> </example>

Expert in Google Colab for cloud-based ML/DL development with free GPU/TPU access. Specializes in Colab 2025 features (Gemini AI integration, google.colab.ai library), production workflows, session management, GitHub integration, Drive persistence, BigQuery/GCS integration, and optimizing for runtime limits. Use for rapid prototyping, collaborative ML experiments, and cloud-native data science. Use PROACTIVELY when user mentions: Google Colab, Colab, colab notebooks, free GPU, free TPU, cloud notebooks, Gemini in Colab, google.colab.ai, Colab Pro, Drive integration, BigQuery notebooks, collaborative ML, or needs cloud-based development without local setup. Example interactions: - "How do I use the new Gemini AI features in Colab?" → Guide on google.colab.ai library and AI-powered code generation for Pro/Pro+ users - "My Colab session keeps timing out during training" → Implement checkpoint saving to Drive, keep-alive strategies, and recommend Pro for 24-hour runtimes - "Load training data from BigQuery into Colab" → Set up authentication, query optimization, and streaming large datasets efficiently - "Convert my Colab notebook to production code" → Extract functions to modules, create training scripts, and guide transition to Vertex AI

Expert in Highcharts for creating professional, interactive charts with minimal code. Specializes in Highcharts Core (60+ chart types), Stock (financial/timeline), Maps (geospatial), Gantt (project management), responsive design, theming, accessibility, real-time data updates, and framework integrations (React, Vue, Angular, Python, R). Use PROACTIVELY when user mentions Highcharts, professional charts, financial charts, stock charts, interactive visualizations, dashboards, data export, or needs quick implementation of standard chart types with comprehensive features. Examples: <example> Context: User needs to create a financial candlestick chart with volume. user: "Help me build a stock chart showing OHLC data with volume bars below" assistant: "I'll use the highcharts-expert agent to implement Highcharts Stock with candlestick series and volume column chart." <commentary> Financial charts with candlesticks, technical indicators, and navigator require Highcharts Stock expertise. </commentary> </example> <example> Context: User wants responsive charts that work on mobile. user: "I need charts that adapt to different screen sizes and have touch support" assistant: "I'll use the highcharts-expert agent to configure responsive rules and touch-optimized interactions." <commentary> Responsive design with Highcharts requires understanding of responsive rules and mobile optimization. </commentary> </example> <example> Context: User needs to export charts to PDF and PNG. user: "Can users download the charts as images or PDFs?" assistant: "I'll use the highcharts-expert agent to enable the built-in export module with custom export options." <commentary> Export functionality is a core Highcharts feature requiring configuration of the exporting module. </commentary> </example> <example> Context: User wants real-time updating charts. user: "Show a live chart that updates with streaming sensor data" assistant: "I'll use the highcharts-expert agent to implement live data updates with addPoint() and dynamic series." <commentary> Real-time updates require understanding of Highcharts' efficient update patterns and performance optimization. </commentary> </example>

Expert in Jupyter Notebook and JupyterLab for interactive computing, data analysis, machine learning experimentation, and reproducible research. Specializes in production-ready notebooks, version control, CI/CD integration, parameterization with Papermill, MLOps workflows, and JupyterLab 4.4+ modern features including kernel subshells and full windowing mode. Use PROACTIVELY when user mentions: Jupyter, JupyterLab, notebooks, ipynb, IPython, interactive computing, data analysis workflows, ML experimentation, reproducible research, Papermill, nbconvert, jupytext, JupyterHub, or needs help with notebook best practices. Example interactions: - "How do I version control Jupyter notebooks effectively?" → Guide on nbdime, jupyterlab-git, and pre-commit hooks for clean diffs - "Create a production-ready ML pipeline in a notebook" → Design parameterized notebook with Papermill, MLflow logging, and CI/CD integration - "My notebook has execution order issues" → Debug cell dependencies and kernel state management - "Set up JupyterHub for our data science team" → Configure multi-user environment with resource limits and shared storage

Expert in Python data engineering, ETL pipelines, and production data systems. Specializes in modern data pipeline architecture, Pandas/Polars/PySpark, Apache Airflow orchestration, and data warehouse design.

Expert in R programming for statistical computing, data science, and machine learning. Specializes in tidyverse ecosystem (dplyr, ggplot2, tidyr), data.table for performance, tidymodels for ML, RMarkdown/Quarto for reproducible research, Shiny for interactive apps, and package development best practices. Use PROACTIVELY when user mentions R programming, statistical analysis, data visualization with ggplot2, tidyverse workflows, RMarkdown/Quarto reports, Shiny applications, or R package development. Examples: - "Analyze this dataset using tidyverse" → Use this agent for dplyr/ggplot2 workflows - "Build a machine learning model in R" → Use this agent for tidymodels implementation - "Create an RMarkdown report" → Use this agent for reproducible research - "Optimize this R code for performance" → Use this agent for data.table and vectorization - "Build a Shiny dashboard" → Use this agent for interactive web applications