Data Science & ML Agent Skills

PyMC Bayesian Modeling

Streamlines the creation, fitting, and validation of Bayesian models using PyMC's modern probabilistic programming interface.

FRED Economic Data

Queries the Federal Reserve Economic Data (FRED) API to retrieve over 800,000 economic time series for financial research and macroeconomic analysis.

ReasoningBank AgentDB Adaptive Learning

Implements high-performance adaptive learning and memory distillation for self-improving AI agents using AgentDB.

RAG Implementation & Optimization

Builds and optimizes Retrieval-Augmented Generation (RAG) systems using advanced vector search, semantic chunking, and retrieval patterns.

Genomics & Transcriptomics Analysis

Provides strategies, implementation patterns, and workflows for genomics and transcriptomics data analysis.

Excel & Data Analysis Toolkit

Creates, edits, and analyzes Excel spreadsheets with professional formatting, automated formula recalculation, and integrated data visualization.

Polars Data Engineering

Accelerates data manipulation and ETL pipelines with the high-performance Polars DataFrame library.

ML Pipeline Workflow

Build and orchestrate end-to-end MLOps pipelines from data preparation through production deployment.

SHAP Model Explainability

Explains machine learning model predictions and feature importance using SHAP values and comprehensive visualizations.

Flow Nexus Neural Networks

Trains and deploys complex neural network architectures within distributed E2B sandbox environments for scalable machine learning workflows.

RAG Implementation & AI Knowledge Systems

Implements Retrieval-Augmented Generation (RAG) architectures to ground LLM responses in proprietary data using vector databases and semantic search.

Scikit-learn Machine Learning

Builds, evaluates, and deploys production-ready machine learning models using the industry-standard scikit-learn library.

LangChain & LangGraph Architecture

Architects sophisticated LLM applications using LangChain 1.x and LangGraph for stateful agents, complex workflows, and advanced memory management.

RAG System Implementation

Builds sophisticated Retrieval-Augmented Generation (RAG) systems to ground LLM responses in proprietary data and external knowledge bases.

RLOO Reinforcement Learning

Implements Reinforcement Learning with Leave-One-Out (RLOO) estimation for stable policy optimization and reasoning model training.

AgentDB Learning Plugins

Implements and trains advanced reinforcement learning algorithms to create autonomous agents that evolve through experience.

Finance DRIVER Workflow

Implements the DRIVER framework for structured, collaborative financial tool development and quantitative analysis.

Analyze Goodreads Export

Queries and analyzes personal book libraries from Goodreads CSV exports to provide reading insights and statistics.

Supervised Fine-Tuning (SFT) with Unsloth

Accelerates LLM instruction-tuning using Unsloth-optimized SFTTrainer for faster, memory-efficient model adaptation.

RAG Pipeline Implementation

Implements Retrieval-Augmented Generation (RAG) workflows to ground AI responses with external document context and reduce hallucinations.

Model Fine-Tuning & Training

Fine-tunes large language models using PyTorch, HuggingFace, and Unsloth to adapt AI behaviors to specific datasets and tasks.

HuggingFace Model Importer

Imports GGUF models from HuggingFace directly into Ollama for local inference and model management.

PyTorch Geometric (PyG)

Develops and trains Graph Neural Networks (GNNs) for node classification, link prediction, and geometric deep learning tasks.

Transformer Architecture & Implementation

Provides technical blueprints and implementation patterns for the Transformer architecture to guide LLM development and fine-tuning.

Optimized ML Inference

Accelerates machine learning inference using Unsloth and vLLM backends for 2x faster token generation.

LLM Evaluation with Evidently.ai

Evaluates LLM output quality and optimizes prompt templates using Evidently.ai metrics and LLM-as-a-Judge patterns.

Reward Model Training

Streamlines the development and training of reward models for RLHF pipelines and thinking quality scoring.

Plotly Interactive Visualization

Generates interactive, publication-quality Python charts and dashboards for data exploration and presentation.

Finance DRIVER Project Initializer

Initializes a standardized project structure for financial underwriting and quant development using the DRIVER methodology.

Context Optimization

Optimizes AI agent context through compression, masking, and strategic partitioning to maximize token efficiency and model performance.