Data Science & ML Claude 技能

HAIPipe NN Pipeline Overview

Provides a foundational architecture map and decision guide for managing neural network pipelines within the HAIPipe research framework.

Multi-Model Council Synthesis

Synthesizes unified answers by orchestrating independent deliberations and adversarial debates between Claude, GPT-5 Codex, and Gemini Pro.

Whisper Audio Transcription

Transcribes audio files locally using whisper.cpp with CUDA acceleration for high-performance speech-to-text conversion.

Haipipe Model Instance Layer

Orchestrates model lifecycles and provides HuggingFace-style APIs for modular neural network research pipelines.

HAIPipe Source Data Processor

Standardizes raw academic and medical data files into structured SourceSet DataFrames for research pipelines.

Notebook Analysis Pipeline

Manages a robust four-stage pipeline that converts modular Python scripts into interactive Jupyter notebooks and comprehensive markdown documentation.

Haipipe NN Algorithm Layer

Standardizes the integration of external machine learning libraries and custom neural network modules within the Haipipe architecture.

Marketing Research & Insights

Provides expert guidance on marketing research methodology, survey design, and statistical data analysis frameworks.

Bayesian Time Series Modeling

Implements robust Bayesian time series models using Stan and JAGS for advanced statistical forecasting and analysis.

Causal Mediation Analysis in R

Performs advanced causal mediation analysis to decompose total effects into direct and indirect effects using industry-standard R packages.

Mediana Clinical Trial Simulation

Streamlines clinical trial design and simulation using the Mediana framework for Clinical Scenario Evaluation (CSE).

Network Meta-Analysis (NMA) Methodology

Provides comprehensive methodological guidance and R implementation patterns for conducting rigorous network meta-analyses.

R Diagnostic Accuracy Analysis

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

Clinical Trial Design Patterns

Implements and optimizes complex clinical trial designs including multi-arm, adaptive, and stratified patterns for biostatistical research.

Data Analysis Expert

Analyzes databases using SQL queries to generate actionable insights, trend reports, and data visualizations.

Pairwise Meta-Analysis Methodology

Provides expert methodological guidance and R code implementation for conducting rigorous pairwise meta-analyses following Cochrane and PRISMA standards.

Bayesian Regression Models

Implements advanced Bayesian regression models including linear, logistic, and robust variations using Stan and JAGS.

ML-NMR Statistical Methodology

Provides comprehensive methodological guidance for Multilevel Network Meta-Regression (ML-NMR) using the multinma package and NICE DSU standards.

Mendelian Randomization in R

Performs causal inference using genetic variants as instrumental variables through comprehensive R-based Mendelian Randomization workflows.

Bayesian Survival Analysis Models

Implements advanced Bayesian survival and time-to-event models with support for censoring and frailty effects.

Tidymodels Hyperparameter Tuning

Optimizes machine learning models using advanced hyperparameter tuning strategies within the R tidymodels ecosystem.

R Genomics & Bioinformatics Analysis

Performs comprehensive genomics and bioinformatics statistical analysis using Bioconductor and R tidy modeling workflows.

Clinical Trial Time-to-Event Analysis

Provides expert guidance and R implementation patterns for survival analysis methods and non-proportional hazards in clinical trials.

Clinical Trials Biostatistics

Implements industry-standard clinical trial design and statistical analysis workflows using regulatory-compliant R packages.

Bayesian Model Diagnostics

Performs comprehensive MCMC diagnostic checks and posterior predictive assessments for Bayesian models implemented in Stan or JAGS.

R Recipes Feature Engineering

Streamlines data preprocessing and feature engineering using R's Tidymodels recipes framework.

Tidymodels Code Review Patterns

Analyzes R machine learning code to detect data leakage, resampling violations, and workflow anti-patterns using tidymodels principles.

Bayesian Modeling in R

Performs comprehensive Bayesian statistical modeling and posterior analysis using Stan-based R packages like brms and rstanarm.

Bayesian Hierarchical Modeling

Implements hierarchical and multilevel Bayesian models with optimized parameterizations for robust statistical inference.

Power Optimization Patterns for Clinical Trials

Optimizes clinical trial designs through advanced sample size determination, event count tuning, and multi-objective tradeoff analysis.