Data Science & ML Claude 技能

LLM Model Selection & Provider Management

Optimizes LLM performance and reliability through automated model selection, cost estimation, and intelligent fallback strategies.

AI Multimodal Processing

Integrates Google Gemini's multimodal capabilities to process audio, video, images, and documents directly within the Claude Code environment.

GrepAI Workspace Manager

Manage GrepAI semantic search workspaces including creation, project management, and indexing status monitoring.

AgentDB Memory Patterns

Manages persistent AI agent memory and reasoning patterns using high-performance vector storage and learning algorithms.

NumPy String Operations

Performs high-performance, vectorized string manipulation and text cleaning using NumPy's specialized string modules.

GrepAI Embedder Config

Configures and troubleshoots embedding providers and models for the GrepAI semantic search tool.

Google Gemini AI & Multimodal Tools

Integrates Google Gemini's multimodal analysis, massive context processing, and image generation capabilities directly into Claude Code.

Excel & Spreadsheet Management

Automates the creation, editing, and analysis of professional Excel spreadsheets with advanced formula support and financial modeling standards.

LSEG Financial Data Access

Facilitates secure retrieval and rigorous validation of LSEG and Refinitiv financial data using the Python Data Library.

Gemini AI Integration

Delegates complex tasks and analysis to Google's Gemini models directly within your Claude Code environment.

Agent C3 Mixed Methods Consultant

Guides researchers through complex mixed methods study designs using systematic qualitative and quantitative integration patterns.

Quantitative Design Consultant

Architects optimized quantitative research designs, experimental methodologies, and sampling strategies using an enhanced three-phase validation process.

Gemini Batch Processor

Automates large-scale asynchronous document processing and bulk LLM tasks using the Google Gemini Batch API.

Qualitative Research Coding Specialist (E2)

Automates and guides systematic qualitative data coding, theme development, and rigorous research methodology implementation.

Scvitools

Analyzes single-cell omics data using deep probabilistic models for integration, batch correction, and differential expression.

I3 RAG Builder & Document Processor

Builds cost-free RAG systems using parallel document processing and local vector embeddings.

SpatialData

Manages, analyzes, and visualizes multi-modal spatial omics data using the SpatialData Python ecosystem and OME-NGFF standards.

PRISMA Systematic Review Orchestrator

Automates and manages the end-to-end 7-stage PRISMA 2020 systematic literature review pipeline from research question to RAG system.

Diverga: Social Science Research Suite

Orchestrates complex social science research and systematic reviews using 24 specialized agents and integrated academic database tools.

Data Science Review Specialist

Validates data analysis workflows by reviewing methodology, data quality, and statistical integrity with a high-confidence scoring system.

Market Research Help

Provides comprehensive guidance and command references for the Market Research plugin to streamline competitive analysis and trend reporting.

Data Visualization

Generates professional data visualizations and plots using industry-standard Python libraries like Matplotlib, Seaborn, and Plotly.

WRDS Research Data Access

Provides validated, high-integrity PostgreSQL query patterns and connection logic for Wharton Research Data Services (WRDS) datasets.

Mixed Methods Integration Specialist (E3)

Integrates qualitative and quantitative research data to generate rigorous meta-inferences and professional joint displays.

Prompt Engineering Patterns

Optimizes Large Language Model performance through advanced prompting techniques like few-shot learning and chain-of-thought reasoning.

Research Orchestrator

Manages complex academic research workflows through 24 specialized agents with mandatory human-in-the-loop checkpoints.

HEAD Framework Evaluation

Synthesizes established metrics into structured driver assessments and integrated analytical reports using the HEAD framework.

LangGraph 7-Layer Architect

Builds and manages complex LangGraph agent systems using a structured, 7-layer architectural pattern for scalable AI development.

Veo 3.1 Video Interpolation

Generates cinematic video transitions and morphing animations between two keyframe images using Google’s Veo 3.1 via fal.ai.

LangChain Application Architecture

Architects and implements sophisticated LLM applications using LangChain for agents, memory management, and complex workflows.