Data Science & ML Claude 스킬

Scientific Peer Reviewer

Evaluates scientific manuscripts and grant proposals using a systematic toolkit for methodology, statistics, and reporting standards.

Scientific Exploratory Data Analysis

Performs comprehensive exploratory data analysis and generates detailed reports for over 200 scientific file formats.

LabArchives Integration

Automates electronic lab notebook workflows by providing programmatic access to LabArchives for research data management and documentation.

SymPy Symbolic Mathematics

Performs exact symbolic mathematics in Python, including algebraic solving, calculus, and matrix manipulations.

PyTorch Lightning Scientist

Streamlines deep learning development by organizing PyTorch code into scalable, high-performance Lightning modules and data pipelines.

ENA Genomics Data Access

Access and retrieve comprehensive nucleotide sequence data and metadata from the European Nucleotide Archive (ENA).

Scientific Statistical Analysis

Performs advanced statistical hypothesis testing, regression analysis, and Bayesian modeling with automated assumption checking and APA-style reporting.

Research Information Lookup

Researches academic literature, technical documentation, and scientific data with automatic model selection and citation support.

Cost-Aware LLM Pipeline

Optimizes LLM API expenditures by implementing intelligent model routing, budget guardrails, and efficient prompt caching strategies.

Regex vs LLM Structured Text Parser

Optimizes structured text extraction using a hybrid decision framework that prioritizes Regular Expressions with LLM fallbacks for edge cases.

Scientific Tool Universe

Accesses and orchestrates over 600 scientific tools and databases for bioinformatics, drug discovery, and life sciences research workflows.

Ask Codex Expert

Consults an independent expert model to validate complex logic, brainstorm solutions, or execute high-reasoning tasks.

AI Agent Council

Aggregates and synthesizes perspectives from multiple AI agents to provide comprehensive, consensus-driven answers to complex queries.

Agent Council

Aggregates and synthesizes diverse perspectives from multiple AI agents to provide a consensus-driven answer to complex queries.

Senior Computer Vision

Implements production-grade computer vision systems including object detection, segmentation, and real-time video processing using industry-standard frameworks like PyTorch and OpenCV.

Senior Data Scientist

Provides expert guidance on statistical modeling, causal inference, and production-grade machine learning systems to drive data-driven decision-making.

Senior Prompt Engineer

Optimizes LLM performance and designs production-grade agentic systems using advanced prompt engineering patterns and evaluation frameworks.

Senior ML Engineer

Productionizes machine learning models and builds scalable MLOps systems using industry-leading frameworks and best practices.

Ark Agentic Framework Analysis

Analyzes the McKinsey Ark repository to help developers understand, implement, and extend provider-agnostic agentic resource patterns.

Tool Creator

Automates the generation of standardized Agent-as-a-Tool and function-based tools for the Strands SDK agent system.

System Prompt Writer

Optimizes and structures system prompts for AI agents using Anthropic's context engineering principles and mandatory Python template escaping rules.

MiniMax AI Voice & TTS

Integrates MiniMax's powerful text-to-speech engine to generate, clone, and design realistic voices directly within your development environment.

AI Product Canvas

Generates a comprehensive framework for defining, evaluating, and launching AI-powered features with technical and ethical rigor.

AI Product Canvas

Structures AI and ML product decisions through a rigorous framework covering problem definition, model selection, and evaluation.

Product Data Analysis Standard

Transforms raw product metrics into actionable business decisions using structured frameworks for funnel, cohort, and root-cause analysis.

Experiment Designer

Designs statistically rigorous A/B tests and interprets experiment results to drive data-driven product decisions.

NeMo Model Evaluator Launcher

Automates the execution, monitoring, and debugging of large-scale LLM evaluations using the NeMo Evaluator framework.

MLflow Evaluation Access

Queries and analyzes AI model evaluation results stored in MLflow through natural language.

NeMo Evaluator BYOB

Creates and deploys custom LLM evaluation benchmarks using the BYOB decorator framework for scalable model testing.

ScholarAIO Document Ingestion

Processes academic papers, patents, and technical documents from various formats into a structured, searchable research knowledge base.