Data Science & ML Claude 技能

Data Visualization & Charting

Generates professional, accessible, and insightful data visualizations using Python's leading charting libraries like Matplotlib and Seaborn.

Data Context Extractor

Generates tailored data analysis skills by capturing tribal knowledge, schema details, and business metrics from analysts.

Statistical Analysis

Applies advanced statistical methods to analyze data distributions, detect trends, and validate hypotheses with scientific rigor.

FRED Economic Data

Queries the FRED API for over 800,000 economic time series to support macroeconomic research and financial analysis.

Imaging Data Commons Access

Queries and downloads large-scale public cancer imaging datasets from the NCI Imaging Data Commons using Python and SQL.

Book SFT Pipeline

Automates the end-to-end process of converting literary works into high-quality datasets for fine-tuning AI models on specific authorial voices and writing styles.

Context Engineering Fundamentals

Provides foundational principles and implementation patterns for managing language model context windows and attention mechanics in AI agent systems.

Context Engineering & Optimization

Optimizes AI context window usage through strategic compression, observation masking, and partitioning to improve performance and reduce costs.

Memory Systems

Design and implement sophisticated agent memory architectures, from vector stores to temporal knowledge graphs, for cross-session persistence.

Context Compression Manager

Optimizes AI agent token usage through advanced context summarization and structured information preservation.

Advanced LLM Evaluation

Implements sophisticated LLM-as-a-judge frameworks and evaluation rubrics to ensure production-grade quality and bias mitigation.

BDI Mental State Modeling

Models autonomous agent behaviors using Belief-Desire-Intention (BDI) architecture and formal cognitive ontologies.

Context Degradation Diagnostics

Diagnoses and mitigates context-related failures in agent systems to ensure reliable performance across large context windows.

Multi-Agent Patterns

Designs and implements sophisticated multi-agent architectures for Claude Code by optimizing context isolation and coordination strategies.

Project Development Methodology

Guides the architectural design, evaluation, and implementation of LLM-powered applications and agent systems.

Kreuzberg Document Intelligence

Extracts structured text, metadata, and tables from over 75 document formats using a high-performance Rust core.

K-Dense Web Integration

Connects Claude to the K-Dense Web platform for advanced, end-to-end scientific research workflows and multi-agent AI collaboration.

MATLAB & Octave Scientific Computing

Performs advanced numerical computing, matrix operations, and scientific visualizations using MATLAB and GNU Octave syntax.

Rowan: Quantum Chemistry & Molecular Simulation

Automates advanced quantum chemistry workflows and protein-ligand modeling using a cloud-based Python API.

Creative Research Ideation

Applies cognitive science frameworks to generate novel research directions in computer science and artificial intelligence.

Research Idea Brainstorming

Facilitates structured research ideation using ten distinct cognitive frameworks to discover high-impact research directions.

Atomic Agents Configuration

Orchestrates and configures modular, structured AI agents using the Atomic Agents framework for robust LLM applications.

Atomic Prompt Design

Generates structured, effective system prompts for AI agents using a modular architecture of background identity, processing steps, and output instructions.

Atomic Agents Schema Designer

Defines robust, type-safe data contracts and Pydantic-based schemas for AI agents using the Atomic Agents framework.

Atomic Agents Context Providers

Injects dynamic, runtime data into AI agent system prompts to enable context-aware decision making and information sharing.

Atomic Agents Project Structure

Scaffolds and organizes modular AI agent projects using standardized directory layouts and configuration patterns.

Context Engineering Fundamentals

Master the core principles of AI context management to optimize agent performance and token efficiency.

LLM Project Methodology

Guides the end-to-end development of LLM-powered applications, from task evaluation and pipeline design to cost estimation and agent architecture.

Context Optimization Expert

Optimizes LLM context windows through strategic compaction, observation masking, and partitioning to reduce token costs and improve agent performance.

Advanced LLM Evaluation

Implements production-grade LLM-as-a-judge patterns to evaluate model outputs using structured rubrics, bias mitigation, and pairwise comparison techniques.