Data Science & ML Claudeスキル

LangChain Framework

Builds sophisticated LLM applications using LangChain for prompt management, model chaining, and structured output parsing.

LLM Project Development Methodology

Architects and optimizes LLM-powered applications using structured methodologies, pipeline design, and agent-assisted development patterns.

Model Quantization

Optimizes large language models for efficient inference and training by reducing memory footprint using advanced precision-shifting techniques like 4-bit and 8-bit quantization.

BDI Mental State Modeling

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

Finance DRIVER Project Initializer

Initializes a standardized project structure for financial underwriting and quant development using the DRIVER methodology.

Vision Model Fine-Tuning

Fine-tunes vision-language models like Pixtral and Ministral using Unsloth's FastVisionModel optimizations for faster training.

DPO Preference Optimization

Optimizes Large Language Models using Direct Preference Optimization to align behavior with preferred response pairs without explicit reward modeling.

PEFT & LoRA Fine-Tuning

Streamlines parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and Unsloth to optimize memory and training speed.

GRPO Alignment & RLHF

Implements Group Relative Policy Optimization for efficient LLM alignment and reinforcement learning from human feedback.

Scientific Exploratory Data Analysis

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

ML Pipeline Workflow

Orchestrates end-to-end MLOps pipelines from data preparation and model training to production deployment and monitoring.

Context Engineering Fundamentals

Provides foundational expertise in context engineering to optimize AI agent performance and manage token usage effectively.

Ollama Python Integration

Provides a clean, Pythonic interface for local LLM inference, chat completions, and model management using the official Ollama library.

Multi-Agent Architecture Patterns

Designs and implements sophisticated multi-agent systems using supervisor, swarm, and hierarchical patterns to solve complex context management challenges.

Context Degradation Diagnostics

Diagnoses and mitigates AI agent performance failures caused by long-context attention loss, poisoning, and informational clash.

Book SFT & Style Transfer Pipeline

Builds high-quality fine-tuning datasets from literary works to train AI models in specific authorial voices and writing styles.

QLoRA Experimentation & Optimization

Optimizes LLM fine-tuning via advanced QLoRA patterns, hyperparameter tuning, and memory-efficient implementation strategies.

Rust Machine Learning & AI

Guides the development of high-performance ML and AI applications in Rust using memory-efficient patterns and GPU acceleration.

Vector Index Tuning

Optimizes vector database performance by balancing search latency, recall accuracy, and memory footprint.

Finance DRIVER Methodology

Provides a comprehensive framework and guidance for building professional finance and quantitative analysis tools with AI assistance.

ComfyUI Stable Diffusion Manager

Manages ComfyUI instances for node-based Stable Diffusion image generation with automated GPU configuration and model management.

FiftyOne Dataset Manager

Manages FiftyOne dataset visualization and curation environments using Podman Quadlet containers with integrated MongoDB sidecars.

QIG Purity Guardian

Enforces E8 architecture standards and QIG purity protocols within the Pantheon development ecosystem.

Ollama OpenAI Bridge

Facilitates the use of local Ollama models with the official OpenAI Python library and compatible AI orchestration frameworks.

Jupyter ML Environment

Manages multi-instance JupyterLab environments with hardware-accelerated GPU support via Podman Quadlet.

LangChain Architecture

Builds sophisticated LLM-powered applications using autonomous agents, complex chains, and context-aware memory systems.

Tidymodels Workflow Patterns

Implements end-to-end machine learning pipelines in R using the modern tidymodels ecosystem.

Agri Hedge Fund Positioning Tracker

Quantifies hedge fund capital flows in agricultural commodity markets using CFTC COT data and macro sentiment indicators.

Ollama Local LLM Management

Manages local LLM inference using Ollama and Podman Quadlet with full GPU acceleration support.

Biopython Molecular Biology

Streamlines computational molecular biology tasks including sequence analysis, biological file parsing, and genomic database integration.