Data Science & ML Agent Skills

Intelligent Research Orchestrator

Orchestrates specialized AI agents to conduct systematic, multi-disciplinary research and synthesis on complex topics.

Critical Analysis & Research

Conducts rigorous evaluations of claims, evidence, and logical arguments to detect bias and validate research methodologies.

Nushell Data Processing

Enables high-performance data manipulation and analysis in Nushell using Polars DataFrames and LazyFrames.

Risk of Bias Assessment

Evaluates methodological quality and potential bias in research studies using standardized frameworks like RoB 2 and ROBINS-I.

Sensitivity Analysis

Evaluates the robustness of research findings by testing how results change under different analytical assumptions and data conditions.

Research Randomization Logic

Implements rigorous randomization procedures for experimental research and unbiased participant allocation.

Experiment Design & Research Rigor

Facilitates the creation of methodologically sound research studies following NIH rigor standards and experimental best practices.

Publication Prep Research Assistant

Prepares submission-ready research manuscripts by automating formatting, reporting guideline compliance, and journal selection workflows.

Hybrid RAG Retrieval

Implements high-precision search by combining semantic dense vectors with keyword-based sparse retrieval for optimized RAG results.

Meta-Analysis Research Assistant

Conducts quantitative synthesis of research data by pooling effect sizes across multiple studies to derive summary conclusions.

Hypothesis Testing Guide

Guides the selection, assumption checking, and interpretation of statistical hypothesis tests for rigorous research data analysis.

ML & AI Engineering Assistant

Accelerates the development of machine learning models and AI systems through expert guidance on MLOps, RAG architectures, and model deployment.

Inclusion Criteria for Research

Applies systematic inclusion and exclusion criteria to automate literature screening and ensure PRISMA compliance.

Research Question Optimizer

Formulates and refines high-quality research questions using the scientifically recognized FINER criteria.

Statistical Power Analysis

Calculates statistical power and determines required sample sizes for research studies to ensure experimental rigor and reproducibility.

Statistical Results Interpretation

Interprets and reports complex statistical findings with high precision, focusing on effect sizes, confidence intervals, and p-value accuracy.

PolicyEngine Core Microsimulation

Powers tax and benefit microsimulations with a vectorized engine for calculating complex economic policy impacts.

Data Cleaning & Quality Remediation

Performs systematic data quality remediation by detecting duplicates, handling outliers, and standardizing datasets for reliable analysis.

AnnData Scientific Data Management

Manages annotated data matrices for single-cell genomics and large-scale biological datasets using the Python AnnData framework.

PolicyEngine Data Science

Analyzes survey microdata using weighted pandas DataFrames to calculate inequality, poverty, and distributional metrics.

Guided Investigation Framework

Conducts systematic, multi-phase investigations into complex, open-ended data questions using structured decomposition and incremental synthesis.

AgentDB Memory Patterns

Implements high-performance persistent memory and reinforcement learning patterns for AI agents using AgentDB and ReasoningBank.

Comparative Data Analysis

Performs rigorous, systematic comparisons of data segments, cohorts, and time periods to uncover actionable drivers of difference.

Data Storytelling Analyst

Transforms raw datasets into impactful visual narratives using advanced data visualization techniques and narrative design principles.

Exploratory Data Analysis (EDA)

Conducts systematic exploratory data analysis to uncover hidden patterns, anomalies, and actionable insights in unfamiliar datasets.

Honcho Integration

Integrates Honcho persistent memory and social cognition into Python or TypeScript codebases to build stateful AI agents.

ReasoningBank Intelligence

Implements adaptive learning systems for AI agents to recognize patterns, optimize strategies, and improve autonomously over time.

Scientific Research Automation

Automates the end-to-end scientific research lifecycle from initial data analysis and hypothesis generation to the production of publication-ready LaTeX manuscripts.

System Prompt Architect

Transforms high-level requirements into production-ready system prompts for complex single and multi-agent AI systems.

Field Agent Visualization

Generates professional, executive-ready Plotly visualizations using Treasure Data's standardized branding and strict formatting requirements.