Data Science & ML Agent Skills

Context Engineering Fundamentals

Master the core principles and mechanics of context management to build more efficient and accurate AI agent architectures.

RAG Implementation Guide

Builds sophisticated Retrieval-Augmented Generation systems to ground LLM applications with proprietary data and external knowledge.

ServiceX for ATLAS xAOD

Generates and optimizes ServiceX queries in func_adl for analyzing ATLAS xAOD high-energy physics data.

LLM Application Evaluation

Implement comprehensive evaluation frameworks for LLM applications using automated metrics, human feedback, and benchmarking.

Amazon Bedrock Multi-Agent Orchestrator

Orchestrates complex multi-agent systems on AWS using the Bedrock AgentCore Agent-to-Agent (A2A) protocol.

RAG Implementation

Implements Retrieval-Augmented Generation (RAG) systems with vector databases and semantic search to build grounded, knowledge-aware AI applications.

Prompt Engineering Patterns

Optimizes LLM performance and reliability through advanced techniques like few-shot learning, chain-of-thought reasoning, and modular prompt templates.

Excel & Spreadsheet Mastery

Enables professional spreadsheet creation, data analysis, and financial modeling with rigorous formula verification and industry-standard formatting.

LLM Evaluation Suite

Implements comprehensive evaluation frameworks for LLM applications using automated metrics, human feedback, and LLM-as-judge patterns.

LLM Evaluation & Benchmarking

Implements systematic evaluation strategies for LLM applications using automated metrics, human feedback loops, and benchmarking frameworks.

LangChain Architecture & Agent Design

Architects sophisticated LLM applications using LangChain agents, multi-step workflows, and advanced memory management systems.

Prompt Engineering Patterns

Optimizes LLM performance and reliability through advanced prompting techniques like few-shot learning and chain-of-thought reasoning.

Data Import and Profiling

Systematizes the process of discovering, profiling, and importing CSV data into relational databases with comprehensive quality checks.

Machine Learning Pipeline Workflow

Builds and orchestrates end-to-end MLOps pipelines from data preparation and training through to production deployment.

SpatialData

Manages, analyzes, and visualizes multi-modal spatial omics data using the SpatialData Python ecosystem and OME-NGFF standards.

Aristotle Math Prover

Formally verifies mathematical statements and generates Lean 4 proofs using Harmonic's Aristotle engine.

Vector Database Management

Facilitates seamless integration with vector databases for semantic search, retrieval-augmented generation (RAG), and high-dimensional embedding management.

System Skill Source

Implements the System Skill Pattern to build persistent, data-driven CLI tools that evolve through continuous user interaction.

Excel & Spreadsheet Management

Automates the creation, editing, and analysis of professional Excel spreadsheets with advanced formula support and financial modeling standards.

Parakeet Audio Transcription

Converts audio files into high-quality timestamped transcriptions using NVIDIA's Parakeet model optimized for Apple Silicon.

LangGraph Fine-Tuning

Optimizes LangGraph application performance by iteratively refining prompts and node-level processing logic based on quantitative evaluation criteria.

FiftyOne Dataset Inference

Automates the creation of FiftyOne datasets from local media files and executes machine learning model inference pipelines.

Tidymodels Workflow Patterns

Implements end-to-end machine learning pipelines in R using the modern tidymodels ecosystem.

Analyze Goodreads Export

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

Recipes Feature Engineering

Streamlines machine learning data preprocessing in R using standardized Tidymodels recipes patterns.

Dorado ONT Basecalling Bench

Automates Oxford Nanopore basecalling workflows on HPC clusters with integrated provenance tracking and GPU optimization.

Health Economics Analysis in R

Performs advanced health economic evaluations including cost-effectiveness analysis, Markov modeling, and probabilistic sensitivity analysis in R.

Beam Tracking ML & RL Pipeline

Design and refactor machine learning pipelines for 5G beam tracking using teacher-student distillation architectures.

R Diagnostic Accuracy Analysis

Performs comprehensive diagnostic test accuracy analysis in R, including ROC curves, cutpoint optimization, and meta-analysis.

Tidymodels Review Patterns

Automates code review for R Tidymodels workflows to prevent data leakage and ensure statistical best practices.