Data Science & ML Claudeスキル

AgentDB Memory Patterns

Implements persistent, high-performance memory and learning patterns for AI agents using AgentDB vector storage.

Machine Learning Model Developer

Automates the end-to-end machine learning lifecycle from data preprocessing and feature engineering to model training and deployment.

Agent PageRank Analyzer

Analyzes complex networks and calculates PageRank scores using sublinear algorithms to optimize graph structures and influence mapping.

SONA Learning Optimizer

Optimizes AI agent performance through SONA-powered self-learning, LoRA fine-tuning, and memory-safe pattern discovery.

D3.js Data Visualization

Creates sophisticated, interactive, and publication-quality data visualizations using the D3.js library.

Flow Nexus Neural Networks

Deploys and trains sophisticated neural networks across distributed E2B sandboxes with support for custom architectures and federated learning.

Agent Adaptive Coordinator

Orchestrates dynamic AI agent swarms by automatically switching between hierarchical, mesh, and ring topologies based on real-time performance metrics.

ReasoningBank Intelligence

Implements adaptive learning systems for AI agents to recognize patterns, optimize strategies, and improve autonomously through experience.

Financial Analyst

Performs production-ready financial analysis including DCF valuations, ratio calculations, and budget variance monitoring.

AgentDB Reinforcement Learning

Integrates nine advanced reinforcement learning algorithms into Claude to build self-optimizing autonomous agents that learn from experience.

Prompt Engineer

Optimizes LLM performance through structured system prompts, few-shot learning, and rigorous evaluation patterns.

D3.js Data Visualization

Creates sophisticated, interactive data visualizations and custom SVG charts using the D3.js library.

ReasoningBank with AgentDB

Implements high-performance adaptive learning and memory distillation for AI agents using AgentDB's optimized vector database.

AgentDB Reinforcement Learning

Trains autonomous agents using nine reinforcement learning algorithms to optimize decision-making and agent behavior through experience.

RAG Engineer

Architects high-performance Retrieval-Augmented Generation systems using advanced embedding, chunking, and search strategies.

Autonomous Agent Architect

Builds reliable, production-grade AI agents using structured patterns like ReAct and Plan-Execute to ensure task success and safety.

Context Window Management

Optimizes Large Language Model inputs through advanced context engineering, intelligent summarization, and token-saving strategies.

Autonomous Agent Architect

Architects reliable, production-ready AI agents by implementing structured loops, goal decomposition, and robust safety guardrails.

RAG Implementation Specialist

Implements sophisticated Retrieval-Augmented Generation patterns including semantic chunking, hybrid search, and vector store optimization.

Professional Excel & Financial Modeling

Creates, edits, and analyzes professional-grade Excel spreadsheets with advanced financial modeling standards and error-free formula calculation.

AI Product Development

Builds production-grade AI features using robust LLM integration patterns, RAG architecture, and cost-effective prompt engineering.

Voice AI Development

Builds high-performance, low-latency voice AI applications and real-time agents using industry-standard APIs and streaming infrastructure.

BayesFlow Packaging Specialist

Standardizes the creation and management of BayesFlow extension packages using best practices for Python structure and API exposure.

BayesFlow Keras Operations

Enforces backend-agnostic tensor mathematics using Keras 3 operations for BayesFlow extensions and custom neural network components.

BayesFlow Validation & Calibration

Validates and diagnoses BayesFlow neural posterior estimators using Simulation-Based Calibration (SBC) and coverage analysis.

BayesFlow Adapter

Streamlines the creation and debugging of data preprocessing pipelines for BayesFlow simulation-based inference models.

Keras 3 Multi-Backend Operations

Enforces backend-agnostic tensor math using Keras 3 to ensure code compatibility across PyTorch, JAX, and TensorFlow.

BayesFlow Validation & Calibration

Validates neural posterior estimators using Simulation-Based Calibration (SBC) and advanced diagnostic metrics.

Neural Pattern Training

Optimizes neural architectures and pattern learning using advanced SONA, MoE, and EWC++ frameworks.

AgentDB Vector Search

Accelerates semantic document retrieval and similarity matching with ultra-fast HNSW indexing and memory-efficient vector storage.