Data Science & ML Agent Skills

Streaming Inference

Implements real-time machine learning architectures for processing unbounded data streams with sub-100ms prediction latency.

Popper's Falsifiability

Validates hypotheses and scientific theories by ensuring they are testable and capable of being proven false through rigorous experimentation.

ML Streaming Inference Pattern

Implements real-time machine learning prediction patterns for high-throughput data streams with sub-second latency.

Stock and Flow System Dynamics

Models complex system dynamics using stocks, flows, and feedback loops to quantitatively predict behavior and test policy interventions.

Normal Distribution Thinking Pattern

Analyzes and applies Gaussian statistical patterns to data for improved prediction, quality control, and anomaly detection.

Bayesian Updating

Refines confidence in hypotheses and technical decisions by systematically weighting prior beliefs against new evidence.

Apophenia Pattern Validator

Prevents flawed decision-making by identifying and debunking illusory patterns or spurious correlations in data and observations.

Agent Data Processor

Processes and prepares data files for AI agent testing and deployment workflows.

Academic Paper Analyzer

Extracts structured research data from academic papers and integrates it into a persistent knowledge graph.

Jupyter Notebook Manager

Programmatically creates, edits, and optimizes Jupyter and Google Colab notebooks with precise JSON formatting and metadata management.

Excel & Spreadsheet Management

Manages complex Excel workbooks with automated formula creation, financial modeling standards, and data analysis.

Academic Review Training Extractor

Extracts structured training pairs from academic peer reviews and source documents to build high-quality datasets for LLM fine-tuning.

Thematic Analysis

Performs systematic qualitative thematic analysis on document collections to extract deep structural insights and categorized themes.

Lit Review & Research Synthesis

Conducts comprehensive multi-paper literature reviews with deep gap analysis and automated citation mapping.

Production Python Developer

Develops production-grade Python code with a focus on type safety, fail-fast logic, and rigorous testing for research environments.

Research & Statistical Analysis

Performs hypothesis-driven statistical analysis and data visualization on datasets, system metrics, and experiment logs.

Agno AI Agent Framework

Build and deploy production-ready multi-agent systems with MCP integration and automated workflows.

GEPS v5: Evolutionary Portfolio Search

Automates multi-stage research idea generation and evaluation using graph-guided search and tournament-style ranking.

Multi-Agent System Optimizer

Optimizes multi-agent AI systems through intelligent coordination, performance profiling, and cost-aware orchestration.

Pegasus Workflow Scaffolder

Automates the creation of production-grade Pegasus scientific workflows from high-level pipeline descriptions.

Solar Data Visualization (SSW-Viz)

Visualizes solar observation data, EUV imagery, and machine learning model outputs using SunPy and Matplotlib.

SSW Solar Data Preprocessing

Transforms raw SDO/AIA solar observation data into standardized, ML-ready formats through automated calibration and registration pipelines.

Excel Interactive Agent

Enables Claude to interactively explore, analyze, and modify open Microsoft Excel workbooks using natural language commands.

SSW Solar Machine Learning

Develops and deploys deep learning models for solar physics using preprocessed Sun and Space Weather data.

Pegasus Workflow Converter

Converts Snakemake and Nextflow pipelines into robust Pegasus workflows for high-performance computing environments.

Solar Data Downloader

Downloads solar observation data from SDO, STEREO, and Solar Orbiter missions for scientific analysis and machine learning.

Ground Truth Labeling

Establishes rigorous and defensible ground truth labels for evaluation datasets based on authoritative guidelines.

Theory2 Physics & Math Tooling

Performs advanced mathematical physics computations, symbolic algebra, and automated theorem proving using the Theory2 suite.

AI Development Research Agent

Conducts deep technical research and provides implementation guidance for AI-enabled software development including RAG, agentic workflows, and LLM architectures.

Fireworks AI Inference & Fine-tuning

Integrates high-performance inference and LoRA fine-tuning for 100+ open-source LLMs via OpenAI-compatible APIs and the firectl CLI.