Data Science & ML Claude 스킬

SHAP Model Interpretability

16

Explains machine learning model predictions and feature importance using Shapley values to provide transparent and actionable AI insights.

DiffDock Molecular Docking

16

Predicts high-accuracy 3D binding poses for protein-ligand complexes using diffusion-based deep learning models.

MCMC Sampling with Stan

16

Implements Bayesian statistical models and runs MCMC sampling using Stan with comprehensive diagnostic validation.

PyHealth

16

Develops, tests, and deploys healthcare-specific machine learning models using electronic health records, clinical prediction tasks, and medical coding systems.

DNA Assembly

16

Designs and validates DNA assembly strategies, including Golden Gate and Gibson assembly, with precise requirements for Type IIS restriction enzyme primers.

PubChem Database Explorer

16

Accesses the world's largest chemical database to retrieve compound properties, structures, and bioactivity data for cheminformatics workflows.

MTEB Text Retrieval

16

Executes text embedding retrieval and semantic ranking tasks using sentence transformers and cosine similarity metrics.

Distribution Search

16

Optimizes probability distributions to satisfy complex statistical constraints like KL divergence, entropy, and moment conditions through systematic mathematical analysis and numerical search.

ESM Protein Modeling

16

Provides advanced protein language models for generating novel sequences, predicting structures, and creating high-quality embeddings for protein engineering and scientific research.

DNA Insert Primer Design

16

Designs and validates specialized primers for DNA sequence insertion into plasmids using site-directed mutagenesis protocols.

PyTorch Model CLI Implementation

16

Implements standalone command-line inference tools in C, C++, and Rust by extracting weights and logic from PyTorch models without Python dependencies.

Scikit-learn Machine Learning Toolkit

16

Implements comprehensive machine learning workflows including classification, regression, and data preprocessing using the industry-standard Scikit-learn library.

Pydicom

16

Reads, writes, and manipulates DICOM medical imaging data, including pixel arrays, metadata extraction, and file anonymization.

GPT-2 Code Golf

16

Implements minimal GPT-2 inference and transformer architectures within strict code size constraints.

Letta Agent Designer

16

Provides architectural guidance and best practices for designing memory-intensive AI agents using the Letta framework.

Count Dataset Tokens

16

Calculates precise token counts for datasets by systematically identifying relevant text fields and applying correct domain filtering logic.

Scientific Context Initialization

16

Configures workspace environments to automatically prioritize established scientific research patterns, database access protocols, and package usage guidelines.

Metabolomics Workbench Database

16

Accesses the NIH Metabolomics Workbench to query metabolite data, study metadata, and standardized nomenclature for biomarker discovery.

MuJoCo MJCF Tuning

16

Optimizes MuJoCo MJCF simulation files to improve computational performance while maintaining high physics accuracy and stability.

LatchBio Integration

16

Builds and deploys serverless bioinformatics workflows using the Latch Python SDK and cloud infrastructure.

Transformers

16

Integrates state-of-the-art machine learning models for NLP, computer vision, and audio tasks using the Hugging Face ecosystem.

AnnData Genomics Toolkit

16

Manipulates and manages AnnData objects for single-cell genomics workflows, including scRNA-seq data processing and file management.

Gemini CLI Integration

16

Integrates Google Gemini CLI to provide Claude with real-time web search, deep codebase analysis, and multi-model code generation capabilities.

Arboreto GRN Inference

16

Infers gene regulatory networks from expression data using high-performance machine learning algorithms like GRNBoost2 and GENIE3.

Portfolio Optimization

16

Optimizes financial computations and portfolio risk metrics by implementing high-performance Python C extensions for large-scale numerical data.

Multi Source Data Merger

16

Merges heterogeneous data sources into unified datasets using field mappings and priority-based conflict resolution.

ENA Database Access

16

Accesses the European Nucleotide Archive to retrieve genomic sequences, raw reads, and metadata for bioinformatics pipelines.

Build Cython Extensions

16

Provides comprehensive guidance for compiling Cython extensions and resolving version-specific NumPy compatibility issues.

Pymatgen Materials Science

16

Automates materials science workflows including crystal structure analysis, phase diagrams, and Materials Project integration.

COBRApy Metabolic Modeling

16

Facilitates constraint-based reconstruction and analysis (COBRA) of metabolic models for systems biology and metabolic engineering.