Data Science & ML Agent Skills

LangChain Agents & RAG

Architects sophisticated LLM applications using autonomous agents, retrieval-augmented generation (RAG), and complex memory management patterns.

Data Visualization

Generates professional data visualizations and plots using industry-standard Python libraries like Matplotlib, Seaborn, and Plotly.

PyMC Bayesian Modeling

Streamlines the creation, sampling, and diagnostics of Bayesian statistical models using PyMC and ArviZ.

SHAP Model Explainability

Explains machine learning model predictions using Shapley values to provide interpretable feature importance and attribution.

Polars Data Science Specialist

Optimizes data processing and analysis using the high-performance Polars DataFrame library for lightning-fast execution.

Scientific Computing

Empowers researchers and developers with specialized Python expertise for astronomy, bioinformatics, symbolic mathematics, and advanced statistical modeling.

Memory Systems & Agent Persistence

Implements advanced agent memory architectures including knowledge graphs, temporal tracking, and cross-session persistence to maintain long-term context.

Scientific Visualization & Figure Design

Generates publication-ready scientific figures and multi-panel layouts optimized for top-tier academic journals like Nature and Science.

Multimodal Models (Vision, Audio & Image Gen)

Integrates pre-trained models like CLIP, Whisper, and Stable Diffusion for advanced vision, speech recognition, and image generation tasks.

Multi-Agent Architecture Patterns

Architects complex LLM workflows using advanced multi-agent patterns like supervisors, swarms, and hierarchical delegation for optimized context management.

Prompt Engineering & RAG Guide

Optimizes LLM performance through advanced prompt engineering, RAG system design, and agent workflow orchestration.

Dask Parallel Computing

Scales Python data workflows across multiple cores or clusters to handle datasets exceeding available memory.

DSPy Declarative Prompting

Optimizes AI system prompts automatically using the DSPy framework to build modular, data-driven LLM pipelines.

LLM Training & Finetuning

Streamlines the process of training and finetuning large language models using industry-standard frameworks and memory optimization techniques.

Market Sizing Analysis

Calculates TAM, SAM, and SOM using top-down, bottom-up, and value theory methodologies to quantify business opportunities.

Vector Databases

Guides developers through selecting, implementing, and optimizing vector search solutions for AI applications and RAG pipelines.

Trading Strategy Backtester

Backtests and evaluates quantitative trading strategies using historical stock market data to generate performance metrics and visualizations.

GPU-Aware ML Training Configuration

Optimizes PPO training performance on A100 and H100 GPUs by automatically aligning hyperparameters with hardware capabilities.

Stitched Image Quality Control

Automates quality control for stitched microscopy images by detecting saturation failures and visible tile grid patterns.

Reward Scaling Calibration

Calibrates reinforcement learning reward scales to eliminate unrealistic drawdown metrics in algorithmic trading models.

Trading Symbol Database Selection

Optimizes financial market universe selection using a multi-stage pipeline and SQLite-backed data management.

MaxFuse Notebook Import Conventions

Standardizes import patterns and file paths for MaxFuse Jupyter notebooks to ensure reliable package integration.

Model Version Protocol

Manages version compatibility between trained trading models and live trading environments by embedding metadata into checkpoints.

Training Code Verification

Validates machine learning training scripts and configurations to ensure path accuracy, weight consistency, and environment compatibility.

Trading Backtest Capital Accounting

Corrects financial logic in trading simulators to prevent inflated equity curves and inaccurate drawdown metrics.

Multi-Timeframe RL Training

Trains Reinforcement Learning models across multiple market timeframes with automated data resampling and professional market alignment.

Trading Prediction Outcome Tracker

Automates the recording of actual trading results against predicted signals to enable accurate performance metrics and model retraining.

RL Trading Reward Function Optimizer

Eliminates HOLD bias in reinforcement learning trading models by calibrating reward functions and slippage penalties.

Python Dataclass Optimizer

Optimizes Python dataclasses for memory efficiency, immutability, and validation using advanced PEP 557 patterns.

Multiplex Imaging Analysis

Optimizes segmentation, feature extraction, and spatial analysis workflows for high-dimensional multiplex immunofluorescence imaging data.