Data Science & ML Claudeスキル

Context Optimization

Optimizes LLM context windows through strategic compaction, masking, and caching to improve model performance and reduce costs.

Context Optimization for AI Agents

Optimizes LLM context windows through compaction, masking, and caching strategies to maximize performance and minimize token costs.

LangChain Architecture & Agent Design

Architects sophisticated LLM applications using LangChain patterns for agents, memory management, and complex tool integration.

Python Practice Tutor

Generates customized Jupyter notebook practice challenges for Python algorithms and pandas data manipulation.

Miles RL Training Framework

Provides expert guidance and implementation patterns for training large-scale Mixture-of-Experts (MoE) models using enterprise-grade Reinforcement Learning.

xAI Stock Sentiment Analysis

Analyzes real-time stock sentiment on X (Twitter) using Grok to provide actionable market insights and retail investor mood.

GraphPad Prism Automation

Automates scientific data analysis and graphing workflows using GraphPad Prism scripting and XML manipulation.

Veo 3.1 Consistent Video Generation

Generates high-quality videos with consistent subject appearance using Google’s Veo 3.1 model and reference images.

Data Visualization Expert

Implements high-performance, accessible, and perceptually accurate data visualizations using industry-standard algorithms and best practices.

Excel Analysis

Analyzes, cleans, and visualizes Excel spreadsheet data using Python libraries like pandas and openpyxl.

Dimensions Academic Search

Queries the Dimensions database to find and analyze academic publications, grants, patents, and clinical trials for evidence-based research.

Veo 3.1 Image-to-Video Prompting

Generates high-fidelity video prompts for Google's Veo 3.1 model by analyzing images and applying professional cinematic formulas.

Prompting Patterns

Implements standardized prompt engineering patterns to ensure reliable, secure, and high-performance LLM interactions.

Data Analyst

Transforms raw data into actionable insights through automated exploratory analysis and professional Python-based visualizations.

Scientific Figure Generator

Automates the creation of consistent, publication-quality scientific figures and diagrams directly from LaTeX placeholders.

Media Ingest & Semantic Cataloger

Automates the ingestion, visual analysis, and semantic tagging of photo and video assets into a searchable SQLite database.

ESM Protein Design & Modeling

Accelerates protein engineering and research using state-of-the-art ESM3 and ESM C language models for sequence generation and structure prediction.

GeoMet Canadian Environmental Data

Accesses, queries, and visualizes Canadian weather, climate, and hydrometric data through the MSC GeoMet API.

Replicate API Integration

Integrates the Replicate API for seamless deployment and execution of generative AI models like Flux, SDXL, and custom LoRA weights.

RAG Implementation & Semantic Search

Implements Retrieval-Augmented Generation (RAG) systems to ground LLM responses in external knowledge bases and private documents.

Similarity Search Patterns

Implements efficient semantic search and vector database patterns for RAG and recommendation systems.

Prompt Engineering Patterns

Implements advanced prompt engineering techniques and structured reasoning patterns to optimize LLM performance and reliability in production environments.

Vector Index Performance Tuning

Optimizes vector database performance by tuning HNSW parameters, quantization strategies, and memory usage for efficient AI applications.

LLM Performance Evaluation

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking.

Embedding Strategies for RAG

Optimizes semantic search and RAG applications through advanced embedding model selection and document chunking strategies.

Market Sizing & Opportunity Analysis

Calculates TAM, SAM, and SOM using professional methodologies to quantify market opportunities for startups and new business ventures.

LangChain Application Architecture

Architects sophisticated LLM applications using LangChain's framework for agents, memory management, and complex tool integration.

Hybrid Search Implementation

Implements advanced search architectures by combining vector similarity and keyword-based retrieval for improved RAG system recall.

Data Storytelling Analytics

Transforms raw business data into compelling narratives and persuasive executive presentations using proven storytelling frameworks.

LLM Project Development Methodology

Guides the end-to-end lifecycle of LLM projects, from evaluating task-model fit to architecting resilient, agent-assisted data pipelines.