Data Science & ML Claude 스킬

Math Tools for Claude Code

Provides deterministic, symbolic mathematical computation using SymPy to ensure absolute accuracy in complex calculations.

Math Tools

Executes deterministic mathematical computations using SymPy to ensure exact symbolic results across algebra, calculus, linear algebra, and statistics.

ArXiv & Academic Paper Search Setup

Configures a Docker-based MCP server for searching and downloading academic papers from arXiv, PubMed, and other scholarly sources.

Business Analyst

Transforms complex business data into actionable insights through advanced analytics, predictive modeling, and strategic KPI frameworks.

LangChain Architecture

Architects sophisticated LLM applications using the LangChain framework for agents, memory management, and complex workflow orchestration.

Codex AI Model Routing

Optimizes development efficiency by routing complex Rust architecture tasks to Sonnet 4.5 and routine utility work to Haiku 4.5.

Vector Index Optimizer

Optimizes vector index performance by tuning HNSW parameters, quantization strategies, and memory usage for high-scale search.

Prompt Engineer

Optimizes LLM performance through advanced prompting techniques, constitutional AI, and production-ready prompt system design.

OpenAI Whisper Transcription

Transcribes audio files into text or JSON format using OpenAI's state-of-the-art Whisper API.

Scientific Hypothesis Generation

Generates testable, evidence-based scientific hypotheses and structured experimental designs from observations or literature.

Data Scientist Expert

Provides expert-level data analysis, machine learning modeling, and statistical insights to drive data-driven decision-making.

LLM Evaluation Suite

Implements comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking frameworks.

MLOps Engineer

Builds and automates production-grade machine learning pipelines, experiment tracking systems, and scalable ML infrastructure across cloud platforms.

AI Engineer

Builds production-grade LLM applications, advanced RAG architectures, and autonomous agent systems with a focus on scalability and safety.

pyvene Causal Interventions

Performs declarative causal interventions and mechanistic interpretability experiments on PyTorch models.

Constitutional AI Safety Alignment

Implements Anthropic's Constitutional AI method to train harmless, helpful models through self-critique and automated AI feedback.

Megatron-Core LLM Training

Optimizes large-scale language model training using NVIDIA Megatron-Core with advanced 3D and expert parallelism strategies.

TensorRT-LLM Optimization

Accelerates Large Language Model inference on NVIDIA GPUs using state-of-the-art optimization techniques for maximum throughput and minimal latency.

NeMo Guardrails Safety

Implements programmable safety rails and validation for LLM applications to prevent jailbreaks, hallucinations, and PII leaks.

NanoGPT Model Training

Implements and trains minimalist GPT architectures for educational and research purposes using Andrej Karpathy's clean, hackable codebase.

LitGPT LLM Training & Implementation

Simplifies Large Language Model implementation, training, and fine-tuning using clean, production-ready LitGPT architectures.

LLaMA Factory Fine-Tuning

Streamlines the fine-tuning process for over 100 large language models using the LLaMA-Factory framework and QLoRA techniques.

SGLang Inference Serving

Optimizes LLM serving and structured generation using RadixAttention prefix caching for high-performance agentic workflows.

OpenRLHF Training Framework

Deploys high-performance Reinforcement Learning from Human Feedback (RLHF) workflows using Ray and vLLM acceleration for large-scale model alignment.

TransformerLens Mechanistic Interpretability

Facilitates mechanistic interpretability research by providing tools to inspect, cache, and manipulate transformer model activations via HookPoints.

SimPO LLM Alignment

Simplifies large language model alignment using reference-free preference optimization to improve model performance without the overhead of PPO or DPO.

HQQ LLM Quantization

Quantizes Large Language Models to 4/3/2-bit precision without calibration data for faster inference and reduced memory footprint.

PEFT Fine-Tuning

Fine-tunes large language models using LoRA, QLoRA, and other parameter-efficient methods to drastically reduce memory and compute requirements.

MoE Training (Mixture of Experts)

Implements and optimizes Mixture of Experts (MoE) architectures to scale model capacity while reducing training and inference costs.

Ray Train Distributed Computing

Orchestrates distributed machine learning training across clusters to scale PyTorch, TensorFlow, and Hugging Face models.