Data Science & ML Claudeスキル

Hi-C Matrix Quality Control

Performs standardized quality control analysis on Hi-C contact matrices to evaluate genomic data depth, uniformity, and reproducibility.

Enzyme.jl Automatic Differentiation

Provides high-performance LLVM-level automatic differentiation for Julia code on CPU and GPU architectures.

Hi-C Compartment Shift Analysis

Performs A/B compartment shift analysis between Hi-C samples using PC1 eigenvector values and replicate-aware statistical methods.

Global Methylation Profiling

Performs genome-wide DNA methylation analysis to characterize patterns, genomic feature distributions, and sample similarities from sequencing data.

Differential TAD Analysis

Performs differential topologically associating domain (TAD) analysis to identify significant chromatin architecture changes between experimental conditions using HiCExplorer.

LLM Evaluation Framework

Implements rigorous evaluation strategies for LLM applications using automated metrics, human-in-the-loop feedback, and advanced benchmarking.

FreqAI ML Integration

Implements a self-adaptive machine learning retraining framework for automated trading signals and market regime detection.

Local Methylation Profiling

Generates and visualizes DNA methylation distribution patterns around specific genomic features such as promoters, enhancers, or transcription factor binding sites.

Multi-Agent Architecture Patterns

Guides the design and implementation of distributed agent systems to maximize context efficiency and task parallelization.

Hi-C TAD Calling & Visualization

Identifies topologically associating domains (TADs) from Hi-C data and generates high-resolution contact map visualizations with boundary overlays.

Scientific Critical Thinking

Evaluates research rigor and scientific claims by assessing methodology, statistical validity, and potential biases using standardized frameworks.

Alignment Quality Control

Evaluates technical mapping statistics for ChIP-seq and ATAC-seq BAM files to ensure data integrity and aligner performance before downstream analysis.

Genomic Feature Annotation & Visualization

Annotates genomic regions with biological features and generates visual distribution summaries using the Homer bioinformatics suite.

Replicates Incorporation

Manages genomic experimental reproducibility by pooling BAM files, generating pseudo-replicates, and performing IDR or consensus peak analysis.

Shadow Goblin

Integrates advanced topological graph theory and bicomodule structures into Claude for complex scientific computing and algebraic modeling.

Loop Annotation

Annotates chromatin loops with regulatory and structural information, including enhancer-promoter mappings and CTCF-peak overlap.

ML Pipeline Workflow Orchestrator

Orchestrates end-to-end MLOps pipelines from data preparation and model training to production deployment and monitoring.

RAG Implementation Expert

Builds Retrieval-Augmented Generation (RAG) systems to ground LLM applications with vector databases and semantic search capabilities.

NeuroKit2 Biosignal Analysis

Processes and analyzes complex physiological signals including ECG, EEG, and EDA for psychophysiology research and medical data science.

Vector Index Tuner

Optimizes vector index performance for production-grade latency, recall, and memory efficiency in AI applications.

Prompt Engineering Patterns

Optimizes LLM performance and reliability through advanced prompting techniques like chain-of-thought and few-shot learning.

Book SFT Pipeline

Converts literary works into high-quality supervised fine-tuning (SFT) datasets for training distinctive author-voice and style-transfer models.

LangChain Architecture Design

Architects sophisticated LLM applications using LangChain patterns for autonomous agents, stateful memory management, and modular chains.

Hybrid Search Implementation

Combines vector similarity and keyword-based search to enhance retrieval accuracy in RAG systems and search engines.

ML Pipeline Workflow

Orchestrates end-to-end MLOps pipelines from data preparation through production deployment and monitoring.

Möbius Inversion Engine

Performs advanced Möbius inversion on partially ordered sets and lattices to solve complex combinatorial, topological, and graph-theoretic problems.

HoloViz Parameterization Expert

Implements type-safe, declarative configuration and reactive logic using the Param library for Python applications.

RAG System Implementation

Builds sophisticated Retrieval-Augmented Generation systems using vector databases, semantic search, and advanced document processing patterns.

Networked System Dynamics

Models and analyzes dynamical systems on graph structures to understand complex flow behaviors and stability.

Differential Methylation Analysis

Identifies differential DNA methylation regions and cytosines between experimental conditions using WGBS methylation tracks.