Data Science & ML Claudeスキル

FiftyOne Model Evaluation

Evaluates computer vision model predictions against ground truth using industry-standard protocols like COCO and Open Images.

FiftyOne Dataset Inference

Runs machine learning model inference, including detection, classification, and segmentation, directly on FiftyOne datasets.

FiftyOne Dataset Export

Exports FiftyOne computer vision datasets to industry-standard formats like COCO, YOLO, and VOC for machine learning training.

Clustering Algorithm Runner

Executes unsupervised machine learning algorithms to identify patterns, group data points, and perform cluster analysis on complex datasets.

Prompt Engineering Patterns

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

ML Pipeline Workflow

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

LangChain Architecture & LLM Orchestration

Architects sophisticated LLM applications using the LangChain framework with advanced patterns for agents, memory, and tool integration.

Flox CUDA Development

Streamlines NVIDIA CUDA setup and GPU computing environments using Flox for deep learning and high-performance development.

Prompt Engineering Toolkit

Systematically designs and optimizes Claude prompts using a multi-level methodology for maximum effectiveness and cost efficiency.

DNAnexus Integration

Integrates Claude with the DNAnexus cloud platform to develop, deploy, and manage genomics pipelines and biomedical data analyses.

Prompt Engineering Patterns

Enhances LLM performance and reliability through advanced techniques like Chain-of-Thought, structured outputs, and few-shot learning.

Geospatial Visualization with GeoViews

Simplifies the creation of interactive maps and geographic data visualizations using GeoViews and GeoPandas.

Pymatgen Materials Analysis

Automates materials science analysis and computational chemistry workflows using the Pymatgen library.

Embedding Strategies

Optimizes vector embedding selection and text chunking strategies for production-grade RAG and semantic search applications.

RAG System Implementation

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

Hybrid Search Implementation

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

LangGraph Workflow Patterns

Architects sophisticated AI agent workflows using standardized LangGraph design patterns for complex state management.

Extended Reasoning & Thinking

Enables deep, multi-step chain-of-thought reasoning for complex problem-solving and logic verification within Claude.

OpenAlgo Technical Indicators

Performs sophisticated technical analysis and generates trading signals using TA-Lib and OpenAlgo market data.

Patent Prior Art Search

Conducts systematic 7-step patent prior art searches and patentability assessments using BigQuery and CPC classifications.

Multi-Agent Architecture Patterns

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

Context Engineering for AI Agents

Provides structured patterns and guidance for building high-performance, production-grade AI agent systems through advanced context management.

Nushell Data Processing

Enables high-performance data manipulation and analysis in Nushell using Polars DataFrames and LazyFrames.

Data Storytelling Analyst

Transforms raw datasets into impactful visual narratives using advanced data visualization techniques and narrative design principles.

Research Synthesis

Synthesizes complex findings from multiple sources into coherent, actionable conclusions with uncertainty quantification.

Intelligent Research Orchestrator

Orchestrates specialized AI agents to conduct systematic, multi-disciplinary research and synthesis on complex topics.

Critical Analysis & Research

Conducts rigorous evaluations of claims, evidence, and logical arguments to detect bias and validate research methodologies.

Risk of Bias Assessment

Evaluates methodological quality and potential bias in research studies using standardized frameworks like RoB 2 and ROBINS-I.

Sensitivity Analysis

Evaluates the robustness of research findings by testing how results change under different analytical assumptions and data conditions.

Research Randomization Logic

Implements rigorous randomization procedures for experimental research and unbiased participant allocation.