Data Science & ML Claudeスキル

AI RAG Vectors & Semantic Search

Integrates a vector embedding layer into Next.js applications using pgvector and AI Gateway for high-performance semantic search and retrieval.

PyMC Bayesian Modeling

Builds, fits, and validates robust Bayesian statistical models using the PyMC probabilistic programming framework.

PyDESeq2 Gene Expression Analysis

Performs differential gene expression analysis for bulk RNA-seq data using the Python implementation of DESeq2.

Excel & Spreadsheet Pro

Automates the creation, editing, and analysis of professional spreadsheets with support for complex formulas and financial modeling standards.

AI RAG Chat

Implements a complete Retrieval-Augmented Generation (RAG) chat interface with vector search and document citations.

Catenary Riser Analysis

Analyzes and designs offshore catenary and lazy wave riser configurations for static shape, tension, and OrcaFlex model generation.

AI Reasoning

Integrates Anthropic's extended thinking capabilities into chat interfaces with a collapsible chain-of-thought UI.

FiftyOne Dataset Import

Automates the detection and ingestion of computer vision datasets into FiftyOne with support for multimodal data and complex label formats.

FiftyOne Model Evaluation

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

LLM Evaluation Framework

Implements systematic evaluation strategies for LLM applications using automated metrics, human feedback, and comparative benchmarking.

FiftyOne Dataset Inference

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

AI Audio Transcription

Transcribes audio and video files into structured text and timestamped segments using the OpenAI Whisper API.

FiftyOne Dataset Export

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

Vercel AI SDK Assistant

Streamlines the development of AI-powered applications by providing real-time documentation, best practices, and implementation patterns for the Vercel AI SDK.

Clustering Algorithm Runner

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

Voice Retell Integration

Integrates real-time Retell AI voice calling and WebRTC capabilities into Next.js chat interfaces.

Owlex AI Council

Orchestrates multi-agent deliberations and structured critiques across multiple LLMs to provide optimized architectural and coding recommendations.

Experiment Design Methodology

Standardizes the creation, execution, and analysis of A/B tests and product experiments to ensure statistical significance and actionable insights.

Prompt Engineering Patterns

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

Flox CUDA Development

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

ML Pipeline Workflow

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

Prompt Engineering Toolkit

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

LangChain Architecture & LLM Orchestration

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

Roundtable AI Delegation

Orchestrates specialized AI sub-agents to solve complex engineering problems through parallel task delegation.

DNAnexus Integration

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

Oneiros Agent Continuity

Provides a persistent cognitive architecture for AI agents to maintain long-term memory, context, and identity across multiple sessions.

BAML Code Generation

Generates production-ready BAML applications and structured output configurations from natural language requirements.

BAML Code Generation

Generates production-ready BAML applications for structured data extraction, classification, and AI agent workflows using real-time patterns from official BoundaryML documentation.

LLM Provider Management

Manages multi-provider patterns and raw SDK access for OpenAI, Anthropic, Google Gemini, and Ollama.

Data Visualization Techniques

Transforms complex datasets into clear, actionable visual narratives through optimized chart selection, dashboard design principles, and modern React charting libraries.