Data Science & ML Agent Skills

Qiskit Quantum Computing

Develops, optimizes, and executes quantum circuits on IBM Quantum hardware and simulators using the industry-standard Qiskit framework.

MarkItDown File-to-Markdown Converter

Converts diverse file formats and office documents into clean, LLM-ready Markdown for improved AI processing.

Scientific Literature Review

Conducts systematic, multi-database literature reviews and meta-analyses with verified academic citations and professional PDF output.

Scientific Critical Thinking

Evaluates the rigor of scientific research by assessing methodology, statistical validity, and evidence quality using industry-standard frameworks.

Scholar Evaluation

Evaluates scholarly research papers and academic work using the systematic ScholarEval framework to provide structured feedback and quality scores.

Ollama Model Management & Optimization

Optimizes local LLM orchestration and GPU performance for Ollama-integrated AI environments.

Context Degradation & Engineering

Diagnose and mitigate performance loss in agentic systems caused by large, conflicting, or poisoned context windows.

Gas-Fertilizer Shock Analyst

Verifies causal narratives between natural gas price surges and fertilizer market disruptions using automated statistical analysis.

Agentica Multi-Agent Infrastructure

Orchestrates complex multi-agent AI workflows using standardized coordination patterns and robust infrastructure primitives.

Autonomous Trading

Orchestrates end-to-end stock trading operations by performing automated screening, multi-model AI analysis, and order execution via Alpaca.

Prompt Engineering Patterns

Optimizes Large Language Model performance through advanced prompting techniques like few-shot learning and chain-of-thought reasoning.

Clinical Trials Statistical Analysis

Provides R-based statistical methods and best practices for clinical trial design, analysis, and regulatory reporting.

Similarity Search Patterns

Implements efficient similarity search and vector database patterns for semantic retrieval and RAG systems.

Real-World Evidence Analysis in R

Generates real-world evidence from observational data using advanced R-based causal inference and target trial emulation techniques.

Hybrid Search Implementation Patterns

Implements high-performance hybrid search by combining vector similarity with keyword-based retrieval for RAG and search applications.

Prompt Engineering Patterns

Implement industry-standard prompt engineering techniques to improve LLM accuracy, reliability, and structured output handling.

DSPy.rb LLM Framework

Builds type-safe, composable, and optimized LLM applications using the programmatic DSPy paradigm in Ruby.

Data Storytelling & Analytics

Transforms raw datasets into persuasive narratives and executive-ready presentations using structured storytelling frameworks and visualization techniques.

GPT CLI Access

Facilitates direct interaction with OpenAI GPT models through a command-line interface within the Claude environment.

Gemini AI Integration

Delegates complex tasks and analysis to Google's Gemini models directly within your Claude Code environment.

Embedding Optimization & Strategies

Implements high-performance embedding pipelines and vector search strategies for RAG applications.

Quantitative Design Consultant

Architects optimized quantitative research designs, experimental methodologies, and sampling strategies using an enhanced three-phase validation process.

Psychometric Scale Architect (d4)

Builds and validates psychometrically sound measurement instruments for social science research.

Qualitative Research Coding Specialist (E2)

Automates and guides systematic qualitative data coding, theme development, and rigorous research methodology implementation.

LangChain Application Architecture

Architects and implements sophisticated LLM applications using LangChain for agents, memory management, and complex workflows.

I3 RAG Builder & Document Processor

Builds cost-free RAG systems using parallel document processing and local vector embeddings.

Diverga E1: Advanced Research & Statistical Analysis

Automates complex quantitative and qualitative research workflows with 5-phase methodological guidance and multi-language code generation.

PRISMA Systematic Review Orchestrator

Automates and manages the end-to-end 7-stage PRISMA 2020 systematic literature review pipeline from research question to RAG system.

Quantitative Risk Metrics

Calculates comprehensive portfolio risk metrics including VaR, CVaR, and risk-adjusted return ratios for quantitative trading strategies.

Backtesting Frameworks

Builds robust, production-grade backtesting systems for trading strategies with specialized handling for look-ahead bias and transaction costs.