Data Science & ML Agent Skills

Resampling Strategies for Tidy Models

Implements robust model validation and resampling techniques using the R tidymodels ecosystem and rsample package.

Popper's Falsifiability

Validates hypotheses and scientific theories by ensuring they are testable and capable of being proven false through rigorous experimentation.

Multi-Model Council Synthesis

Synthesizes unified answers by orchestrating independent deliberations and adversarial debates between Claude, GPT-5 Codex, and Gemini Pro.

Streamlit UI Architect

Develops and maintains interactive Streamlit interfaces for document analysis, resume matching, and real-time data visualization.

Universal LLM Router

Routes prompts to any LLM provider and model while leveraging real-time benchmark data for optimal selection.

Recommendation Engine Systems

Constructs personalized recommendation engines using collaborative and content-based filtering to deliver tailored user experiences.

Research & Statistical Analysis

Performs hypothesis-driven statistical analysis and data visualization on datasets, system metrics, and experiment logs.

AI-PRISMA Screening Assistant

Automates systematic literature screening using the PRISMA 2020 framework and cost-effective Groq LLMs.

Technical Stock Indicators

Calculates core financial technical indicators including MA, MACD, RSI, and Bollinger Bands for stock market analysis and quantitative trading.

Academic Paper Analyzer

Extracts structured research data from academic papers and integrates it into a persistent knowledge graph.

Lit Review & Research Synthesis

Conducts comprehensive multi-paper literature reviews with deep gap analysis and automated citation mapping.

AI Development Research Agent

Conducts deep technical research and provides implementation guidance for AI-enabled software development including RAG, agentic workflows, and LLM architectures.

Experiment Log

Tracks experiment parameters, results, and environment snapshots to ensure full reproducibility and systematic iteration.

ML Model Deployment Helper

Automates the productionization and deployment of machine learning models into scalable environments using FastAPI, Docker, and Kubernetes.

Classification Model Builder

Automates the end-to-end creation, evaluation, and deployment of machine learning classification models from natural language requests.

FiftyOne Image Deduplication

Identifies and removes duplicate or visually similar images in FiftyOne datasets using deep learning embeddings.

Nixtla Research Assistant

Monitors and summarizes the Nixtla forecasting ecosystem to provide actionable updates on TimeGPT, StatsForecast, and MLForecast.

ML Model Evaluation Suite

Evaluates machine learning models by generating comprehensive performance metrics including accuracy, precision, and F1-score to guide model optimization.

Data Anomaly Detection

Identifies outliers and unusual patterns in datasets using advanced machine learning algorithms to uncover fraud, defects, or security threats.

Financial Researcher

Conducts autonomous, institutional-grade financial analysis using multi-guru perspectives and advanced composite scoring.

TimeGPT-2 Migration Assistant

Automates the transition of time-series forecasting pipelines from TimeGPT-1 to the enhanced TimeGPT-2 architecture.

Quarto Survey Analysis Setup

Initializes a professional Quarto environment for survey data analysis using Python, uv, and Typst PDF pipelines.

AI & ML Prompt Optimizer

Optimizes Large Language Model (LLM) prompts to minimize token consumption, reduce operational costs, and enhance response quality.

Code Analyzer

Analyzes GitHub repositories to extract computational methodologies and automatically draft scientific Methods sections.

Training Set Builder

Extracts structured training examples from document sets to create high-quality datasets for teaching LLMs specific tasks or styles.

Academic Data Analyst

Facilitates reproducible academic research and data pipelines using dbt and Streamlit while enforcing rigorous data integrity standards.

Academic Research Data Analyst

Streamlines academic research data analysis by enforcing reproducible dbt pipelines and interactive Streamlit dashboards.

Ground Truth Labeling

Establishes rigorous and defensible ground truth labels for evaluation datasets based on authoritative guidelines.

Solar Data Downloader

Downloads solar observation data from SDO, STEREO, and Solar Orbiter missions for scientific analysis and machine learning.

Pegasus Workflow Converter

Converts Snakemake and Nextflow pipelines into robust Pegasus workflows for high-performance computing environments.