Data Science & ML Agent Skills

Excel & Spreadsheet Professional

Manages complex spreadsheet tasks including professional financial modeling, data cleaning, and automated formula validation.

Google Gemini API Integration

Integrates the latest Google Gemini 3 and 2.5 models using the modern @google/genai SDK for multimodal processing and advanced reasoning.

ε-Yajña

Compresses verbose agent memories into a dense, symbolic format for efficient knowledge retrieval and context management.

Streamlit for Snowflake

Builds and deploys production-ready Streamlit data applications natively within the Snowflake Data Cloud environment.

Data Science Output-First Implementation

Enforces rigorous output-first verification and subagent delegation for reliable data science workflows in Claude Code.

Morgus Research & Deep Analysis

Conducts systematic, high-rigor research and data synthesis to transform raw information into actionable insights and structured reports.

Notebook Debugger

Debugs and verifies Jupyter, Marimo, and Jupytext notebooks by enforcing rigorous execution and traceback checks.

Data Science Verification & Reproducibility

Enforces rigorous technical validation and user acceptance testing for data science workflows to ensure reproducible results.

Cloudflare Vectorize Implementation

Implements high-performance semantic search and RAG workflows using Cloudflare Vectorize V2 with optimized metadata filtering and batch processing.

Domain Advisor

Recommends optimized experiment plans and development tasks by analyzing historical project data across machine learning and GPU computing domains.

C++ Anti-Slop for Rcpp

Optimizes Rcpp and C++ extensions by enforcing memory safety, const-correctness, and high-performance vectorized patterns.

Bayesian Survival Models

Implements robust Bayesian survival analysis models including Weibull and Cox-like piecewise hazards with censoring support.

Prompt Engineering Patterns

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

Demographic Fiscal Trap Analyzer

Analyzes the intersection of aging populations and sovereign debt to quantify fiscal vulnerability and potential currency dilution paths.

Google Gemini Embeddings

Implements production-ready RAG systems and semantic search using Google's Gemini embedding models with Cloudflare integration.

Phoenix XIRR & Fees Validator

Validates financial calculations for XIRR and management fees to ensure accuracy and parity with industry-standard Excel models.

Hybrid Search Implementation

Combines vector similarity and keyword-based search to improve retrieval accuracy and recall in RAG systems.

Bayesian Meta-Analysis

Implements robust Bayesian meta-analysis models using Stan and JAGS to synthesize data across multiple studies with advanced statistical precision.

LLM SDK Integration & Orchestration

Provides standardized patterns for integrating multi-provider LLMs and advanced Claude orchestration via CLI-based SDK architectures.

ML-NMR Methodology Guide

Provides expert methodological guidance and implementation patterns for conducting rigorous Multilevel Network Meta-Regression (ML-NMR).

LLM Embedding Strategies

Optimizes semantic search and RAG applications by selecting, implementing, and fine-tuning high-performance embedding models and chunking strategies.

Prompt Engineering Patterns

Implements advanced prompt engineering techniques to optimize LLM performance and output reliability in production applications.

Similarity Search Patterns

Implements high-performance similarity search and vector database patterns for AI-driven applications.

Embedding Comparison

Evaluates and benchmarks different embedding models to optimize semantic search and vector retrieval performance on your specific data.

Data Science Toolkit

Provides discovery and management of specialized data science plugins, MCP servers, and data access tools within Claude Code.

Marimo Reactive Notebooks

Develops, debugs, and manages reactive Marimo Python notebooks with strict adherence to dependency tracking and cell structure.

Structural Rewilding (A-Life Framework)

Implements a homotopical framework for Artificial Life that treats organisms as morphisms and verifies structural changes at interaction time.

Apache Airflow DAG Patterns

Implements production-grade Apache Airflow workflows using industry-standard patterns for orchestration, error handling, and testing.

Data Science Project Brainstormer

Refines vague data analysis requests into clear, actionable objectives using Socratic questioning before any code is written.

ML Pipeline Workflow

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