Data Science & ML Claude 技能

LangChain Architecture

Builds sophisticated LLM applications and autonomous agents using the LangChain framework's core patterns and integrations.

OpenRouter Multi-Model Gateway

Integrates 300+ AI models into Claude Code for specialized tasks, high-fidelity image generation, and cross-model reasoning.

DuckDB & MotherDuck Analytics

Streamlines building high-performance OLAP applications using DuckDB, MotherDuck, and Parquet in Node.js and TypeScript.

Multimodal Media Analysis

Analyzes and extracts deep insights from images, videos, and audio files using advanced AI models.

Airflow DAG Patterns

Builds production-ready Apache Airflow DAGs using industry-standard patterns for orchestration and data engineering.

LLM Evaluation Framework

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

Data Storytelling

Transforms complex datasets into persuasive narratives and executive-ready presentations using proven storytelling frameworks.

Embedding Strategies for RAG

Optimizes embedding model selection and chunking strategies to improve semantic search and RAG application accuracy.

MLOps Pipeline Orchestrator

Builds and automates end-to-end MLOps pipelines from data ingestion and preparation through model training, validation, and production deployment.

RAG Implementation Expert

Builds production-grade Retrieval-Augmented Generation (RAG) systems using vector databases and semantic search for LLM applications.

Vector Index Optimization

Optimizes vector database indexes for production performance by balancing search latency, recall accuracy, and memory consumption.

LangChain Architecture Design

Builds sophisticated LLM applications using the LangChain framework to implement autonomous agents, complex workflows, and persistent memory.

Quantitative Backtesting Frameworks

Builds production-grade backtesting systems for trading strategies while mitigating common biases and accounting for realistic market costs.

PyHealth Healthcare AI

Builds and deploys healthcare machine learning models using specialized tools for EHR data, clinical tasks, and medical coding systems.

Risk Metrics Calculation

Calculates comprehensive portfolio risk metrics and performance indicators for quantitative trading strategies and investment management.

Prompt Engineering Patterns

Optimizes Large Language Model performance through advanced reasoning patterns, few-shot learning, and structured prompt templates.

ML Streaming Inference Pattern

Implements real-time machine learning prediction patterns for high-throughput data streams with sub-second latency.

Scientific Critical Thinking

Evaluates research rigor by assessing methodology, statistical validity, and evidence quality using industry-standard frameworks like GRADE and Cochrane.

Gambler's Fallacy Recognition

Identifies and mitigates the gambler's fallacy to improve decision-making in probabilistic and high-risk scenarios.

RAG Thinking Patterns

Implements sophisticated Retrieval-Augmented Generation architectures to ground AI responses in real-time external knowledge and eliminate hallucinations.

Supply and Demand Analysis

Predicts market price and quantity changes by analyzing the interaction between producer supply and consumer demand at equilibrium.

Online Learning System Design

Implements continuous model updates and incremental learning patterns to handle evolving data streams without full retraining.

Stock and Flow System Dynamics

Models complex system dynamics using stocks, flows, and feedback loops to quantitatively predict behavior and test policy interventions.

Experiment Log

Tracks experiment parameters, results, and environment snapshots to ensure full reproducibility and systematic iteration.

Data Network Effects

Leverages the data flywheel mental model to build compounding competitive advantages through automated machine learning and user-generated signals.

AI Development Research Agent

Conducts deep technical research and provides implementation guidance for AI-enabled software development including RAG, agentic workflows, and LLM architectures.

Ask OpenCode

Delegates coding tasks and cross-model feedback to multiple AI providers through the OpenCode CLI bridge.

Excel & Spreadsheet Management

Manages complex Excel workbooks with automated formula creation, financial modeling standards, and data analysis.

Base Rate Fallacy Logic

Corrects probability judgments by integrating statistical base rates with case-specific information to avoid common cognitive biases.

Normal Distribution Thinking Pattern

Analyzes and applies Gaussian statistical patterns to data for improved prediction, quality control, and anomaly detection.