Data Science & ML Claudeスキル

BDI Mental State Modeling

Transforms external RDF context into formal Belief-Desire-Intention (BDI) mental states for advanced cognitive agent reasoning.

Scientific Experiment Design

Implements best practices for designing, documenting, and analyzing reproducible scientific experiments within data science workflows.

Experiment Design & Reproducibility

Implements best practices for designing reproducible, statistically valid scientific experiments and machine learning workflows.

Data Analysis & Statistics

Implements rigorous data exploration and statistical testing patterns for scientific research and analysis.

Data Analysis & Statistical Patterns

Implements rigorous data exploration, statistical testing, and scientific validation patterns using Python's data science stack.

ML Rigor

Enforces machine learning best practices including baseline comparisons, cross-validation, model interpretation, and data leakage prevention.

ML Rigor

Enforces scientific best practices in machine learning pipelines through baseline comparison, cross-validation, and model interpretation.

Google Gemini File Search

Implements fully managed Retrieval-Augmented Generation (RAG) using Google Gemini for searchable document knowledge bases.

AI SDK Core Integration

Builds advanced backend AI applications using the latest Vercel AI SDK features, including structured outputs, multi-modal capabilities, and performance optimizations.

GRPO Fine-Tuning for Vision Models

Implements Group Relative Policy Optimization (GRPO) to fine-tune vision-language models on small, specialized datasets.

ElevenLabs Voice Agents

Builds and manages production-ready conversational AI voice agents with integrated ASR, TTS, and custom RAG knowledge bases.

AI SDK React UI

Builds sophisticated React chat interfaces and AI-powered components using Vercel AI SDK v6 stable patterns.

OpenAI Agents SDK Integration

Build and deploy sophisticated AI agent workflows featuring multi-agent handoffs, realtime voice, and type-safe tool execution.

OpenAI Responses API Integration

Builds stateful, agentic AI applications using OpenAI's Responses API with preserved reasoning and server-side tool integration.

Google Gemini Embeddings

Implements high-performance text embeddings for RAG, semantic search, and document clustering using the Google Gemini API.

LLM Integration Patterns

Implements production-ready LLM patterns including tool use, streaming responses, local inference with Ollama, and parameter-efficient fine-tuning.

LangGraph Workflow Patterns

Provides production-ready LangGraph implementation patterns for state management, multi-agent orchestration, and human-in-the-loop workflows.

LLM Integration Patterns

Implements production-ready LLM patterns for function calling, streaming, local inference with Ollama, and model fine-tuning.

Golden Dataset Manager

Manages the complete lifecycle of high-quality evaluation datasets for AI and ML models through automated curation, validation, and versioning.

Golden Dataset Management

Manages the full lifecycle of high-quality AI evaluation datasets through automated curation, validation, and versioning patterns.

Multimodal LLM Integration

Integrates advanced vision, audio, and video generation capabilities using production-ready multimodal LLM patterns.

LangGraph Workflow Patterns

Architects robust AI agents and multi-agent systems using production-ready LangGraph orchestration patterns.

Agent Orchestration

Builds and coordinates sophisticated AI agent systems using industry-standard patterns like ReAct loops, multi-agent supervision, and framework-specific implementations.

Multimodal LLM Integration

Integrates advanced vision, audio, and video generation capabilities into AI applications using industry-leading multimodal models and production-ready patterns.

AgentDB Memory Patterns

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

BDI Mental State Modeling

Transforms RDF context into Belief-Desire-Intention (BDI) architectures to enable formal cognitive reasoning and rational agency in AI agents.

Biomni Biomedical Research Agent

Automates complex biomedical research tasks including genomics, drug discovery, and clinical analysis through autonomous multi-step reasoning.

DNAnexus Integration

Simplifies the development, deployment, and management of cloud-based genomics pipelines on the DNAnexus platform.

AgentDB Memory Patterns

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

PennyLane Quantum Computing

Builds and optimizes quantum circuits using automatic differentiation and seamless integration with PyTorch, JAX, and TensorFlow.