Data Science & ML Claude 스킬

Learning Agents Manager

Orchestrates self-improving AI sub-agents that automatically learn from past mistakes and session transcripts to enhance future performance.

AI Agent Performance Auditor

Analyzes AI agent session transcripts to identify performance issues, knowledge gaps, and incorrect outputs for continuous improvement.

Learning Agent Optimizer

Automates the continuous improvement of AI agents by analyzing session transcripts, identifying errors, and refining agent definitions.

JAXSR Symbolic Regression

Discovers interpretable algebraic equations from data using JAX-powered sparse optimization and Design of Experiments (DOE) workflows.

LangChain4j Vector Stores Configuration

Configures and optimizes LangChain4j vector stores for RAG applications, enabling seamless semantic search and embedding storage in Java environments.

Fal Platform Manager

Manages model deployments, tracks usage, and monitors pricing within the fal.ai ecosystem.

Knowledge Graph Construction

Designs and builds structured knowledge graphs from unstructured data to ground LLM reasoning and enhance RAG systems.

CocoIndex Data Pipelines

Builds ultra-performant real-time ETL pipelines for AI indexing, vector search, and incremental data processing.

Knowledge Graph Embedding Fusion

Designs sophisticated embedding strategies that fuse semantic and structural graph data for advanced knowledge representation.

Claude Agent SDK Architect

Architects and implements production-grade autonomous agents using Anthropic's official SDK for Python and TypeScript.

Claude Agent SDK

Builds production-ready AI agents with native support for tool orchestration, context management, and hierarchical subagent workflows.

Retrieval & Search Orchestration

Orchestrates sophisticated retrieval strategies for knowledge graphs in RAG systems to ensure accurate, traceable, and multi-hop reasoning.

GraphRAG Evaluation & Benchmarking

Evaluates GraphRAG system performance across knowledge graph quality, retrieval accuracy, multi-step reasoning, and hallucination prevention.

ML & Computer Vision Specialist

Provides specialized guidance for designing machine learning systems, computer vision pipelines, and production-ready AI architectures.

Deep Agents Implementation

Implements sophisticated AI agents using the Deep Agents framework and LangGraph for complex, multi-step workflows.

PydanticAI Agent Builder

Simplifies the creation of production-grade AI agents using PydanticAI with strict type-safety and structured data validation.

Prompt Analyzer

Analyzes generated AI prompts to provide structural insights, style comparisons, and data-driven optimization recommendations.

DSPy Model Distillation & Fine-tuning

Distills complex DSPy programs into optimized model weights to reduce inference costs and increase production performance.

DSPy SIMBA Optimizer

Optimizes DSPy programs using mini-batch Bayesian optimization and statistical analysis of rich feedback signals.

DSPy Output Refinement & Constraints

Enhances DSPy program reliability by enforcing custom constraints and reward functions through iterative refinement and best-of-N selection.

DSPy ReAct Agent Builder

Builds production-ready ReAct agents using the DSPy framework to solve complex multi-step tasks with integrated tool-calling and reasoning.

DSPy Bootstrap Few-Shot Optimizer

Automates the generation and selection of high-quality few-shot demonstrations for DSPy programs using teacher models.

DSPy MIPROv2 Optimizer

Optimizes DSPy programs by jointly tuning instructions and few-shot demonstrations using Bayesian search for maximum model performance.

DSPy Advanced Module Composition

Orchestrates complex DSPy programs using ensemble patterns, multi-chain reasoning synthesis, and robust sequential pipelines.

DSPy RAG Pipeline Builder

Builds and optimizes retrieval-augmented generation pipelines using the DSPy framework and ColBERTv2 for grounded, factual AI responses.

DSPy GEPA Reflective Optimizer

Optimizes complex AI agents and ReAct systems using LLM-driven reflection on execution trajectories and textual feedback.

DSPy Custom Module Designer

Architects production-grade custom DSPy modules with robust state management, serialization, and error handling.

DSPy Evaluation Suite

Systematically measures and evaluates DSPy program performance using built-in metrics and custom scoring functions.

DSPy Signature Designer

Designs type-safe, structured signatures for DSPy modules to define precise AI model inputs and outputs.

Excel Spreadsheet Management & Analysis

Automates the creation, editing, and analysis of professional Excel spreadsheets with advanced formula support and financial modeling standards.