Data Science & ML Claudeスキル

Computational Text Analyst

Guides systematic computational text analysis for social science research using R or Python to produce publication-ready results.

Modelica Simulation & Modeling

Enables acausal, multi-domain modeling and simulation of complex physical systems using Modelica and Wolfram Language.

Critical Opalescence Physics

Analyzes and simulates critical opalescence signatures and phase transition dynamics in physical and biological systems.

Waddington Landscape Modeling

Models developmental biology cell fate transitions through gradient flow, potential surfaces, and fractional diffusion dynamics.

Levity-Levin Algorithmic Play

Orchestrates playful multi-agent exploration anchored by Leonid Levin's algorithmic complexity and optimality guarantees.

Gay-Julia: Deterministic Color Sampling

Generates deterministic, wide-gamut color palettes and GF(3) trit assignments for scientific visualization and UI theming in Julia.

RAG Chunking Strategies

Implements optimized document splitting and processing workflows for Retrieval-Augmented Generation (RAG) systems.

Acquisition System Setup

Configures and verifies scientific data acquisition systems by automating hardware discovery and parameter management.

ADK Advanced

Facilitates visual agent design and advanced reasoning configuration for building sophisticated, multi-step AI workflows.

Technical Chart Analyst

Performs objective technical analysis on weekly price charts to identify trends, support levels, and probabilistic price scenarios.

LangChain Architecture Master

Designs and implements sophisticated LLM applications using the LangChain framework for agents, memory management, and complex task workflows.

LLM Project Architect

Architects and implements robust LLM-powered projects from initial ideation through deployment using agentic methodologies.

LLM Application Evaluation

Implements robust evaluation frameworks for AI applications using automated metrics, human feedback, and LLM-as-judge patterns.

LLM Prompt Engineering Patterns

Implements advanced prompt engineering techniques like few-shot learning and chain-of-thought to maximize LLM performance and reliability.

Turing Chemputer

Automates programmable chemical synthesis by treating chemical procedures as executable XDL code on modular robotic hardware.

LLM Evaluation Framework

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

Vector Index Tuner

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

Book SFT Pipeline

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

RAG Implementation Expert

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

HoloViz Parameterization Expert

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

Prompt Engineering Patterns

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

HoloViz Colormaps & Styling

Applies perceptually uniform colormaps and accessible visual styling to data visualizations using Colorcet and the HoloViz ecosystem.

LangChain Architecture Design

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

HoloViz Plotting Fundamentals

Simplifies the creation of interactive, publication-quality visualizations using hvPlot and HoloViews within the HoloViz ecosystem.

ML Pipeline Workflow

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

Multi-Agent Orchestration

Architects complex multi-agent systems and workflows using standardized patterns across major AI frameworks.

ChIP-seq Biological Quality Control

Performs specialized biological validation for ChIP-seq data by calculating cross-correlation metrics and fraction of reads in peaks.

Functional Enrichment Analysis

Performs Gene Ontology and KEGG pathway enrichment analysis from genomic regions or gene lists with automated R-based visualizations.

Regulatory Community Analysis for ChIA-PET

Analyzes protein-mediated chromatin interactions to identify and visualize regulatory communities from ChIA-PET datasets.

ReasoningBank with AgentDB

Implements high-performance adaptive learning and memory distillation for AI agents using the AgentDB vector backend.