Data Science & ML Claudeスキル

Scientific Hypothesis Generator

16

Generates testable, evidence-based scientific hypotheses and experimental designs from observations or literature.

Bayesian Network Recovery and Modification

16

Guides the recovery of Directed Acyclic Graph structures from observational data, parameter estimation, and the implementation of causal interventions.

Political Science Analyst

16

Analyzes global events, policy changes, and power dynamics using established political science frameworks and international relations theories.

Prompt Engineering Patterns

16

Implements advanced prompting strategies like Chain-of-Thought and few-shot learning to optimize LLM performance and output reliability.

Excel Analysis & Automation

16

Automates complex Excel data processing, visualization, and formatting using powerful Python libraries like Pandas and OpenPyXL.

UMAP Dimensionality Reduction

16

Performs fast, scalable non-linear dimensionality reduction and manifold learning for high-dimensional data visualization and clustering.

Seaborn Statistical Visualization

16

Generates publication-quality statistical graphics and complex multi-panel data visualizations using the Seaborn Python library.

CSV Data Summarizer

16

Automatically analyzes CSV files to generate comprehensive statistical summaries and tailored visualizations without requiring user prompts.

LLM Inference Batching Scheduler

16

Optimizes LLM inference workloads on compilation-based accelerators by balancing request batching, shape selection, and padding overhead to minimize costs while meeting latency requirements.

Scientific Peer Review Toolkit

16

Provides a systematic framework for evaluating the methodology, statistics, and integrity of scientific manuscripts and grant proposals.

Histolab Digital Pathology

16

Processes whole slide images (WSI) for digital pathology by automating tissue detection, tile extraction, and preprocessing for computational pipelines.

Portfolio Optimization

16

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

Statsmodels Statistical Analysis

16

Performs rigorous statistical modeling, econometric analysis, and hypothesis testing using Python's statsmodels library.

Video Processing

16

Guides frame-level analysis and event detection in videos using OpenCV to ensure accurate motion tracking and algorithm validation.

Adaptive Rejection Sampler

16

Implements efficient adaptive rejection sampling algorithms for generating random samples from log-concave probability distributions.

Count Dataset Tokens

16

Calculates token counts in large-scale datasets using specific tokenizers and precise filtering criteria.

Bayesian Network Fitting and Modification

16

Streamlines Bayesian Network workflows by guiding structure learning, parameter estimation, causal interventions, and network sampling using industry-standard libraries.

Physicist Analyst

16

Analyzes systems and technological feasibility using fundamental laws of physics and quantitative modeling.

Epidemiologist Analyst

16

Analyzes disease patterns, health events, and transmission dynamics using established epidemiological frameworks and mathematical modeling.

Chemist Analyst

16

Analyzes complex chemical processes and molecular structures using rigorous scientific principles and analytical techniques.

Caffe Framework & CIFAR-10 Training

16

Guides the compilation of the legacy Caffe deep learning framework and the training of convolutional neural networks on the CIFAR-10 dataset.

Model Evaluation Benchmark

16

Automates comprehensive AI model benchmarking and performance comparison using the Benchmark Suite V3 framework.

Environmentalist Analyst

16

Provides expert ecological analysis and sustainability assessments using systems thinking and conservation biology principles.

Caffe CIFAR-10 Build and Training

16

Guides the compilation of the Caffe deep learning framework from source and the execution of CIFAR-10 image classification training workflows.

Small Matrix Eigenvalue Computation

16

Optimizes dominant eigenvalue calculations for small dense matrices by reducing Python wrapper overhead through direct LAPACK integration.

Raman Spectroscopy Peak Fitting

16

Analyzes and fits peaks in Raman spectroscopy data using physically-constrained models like Lorentzian, Gaussian, and Voigt functions.

Train FastText

16

Optimizes FastText text classification models by balancing hyperparameter tuning with strict file size and accuracy constraints.

Modern R Data Science

16

Accelerates R 4.4+ development by providing expert guidance on tidyverse patterns, ggplot2 visualizations, and Shiny application architecture.

CZ CELLxGENE Census

16

Facilitates programmatic access and analysis of the CZ CELLxGENE Census database containing over 61 million single-cell genomics records.

Historian Analyst

16

Applies rigorous historical methodologies and temporal frameworks to analyze events, identify long-term patterns, and contextualize contemporary trends.