Data Science & ML Claude 스킬

Biopython Bioinformatics Tools

Streamlines computational molecular biology tasks and bioinformatics workflows using the Biopython library.

GeoPandas Geospatial Analysis

Enables advanced geospatial vector data analysis, geometric operations, and spatial mapping within Python environments.

FluidSim CFD Framework

Executes high-performance computational fluid dynamics simulations and analysis using pseudospectral methods in Python.

AgentDB Memory Patterns

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

Neural Network Builder

Automates the design, configuration, and implementation of complex neural network architectures for various machine learning tasks.

Mobility Manager

Optimizes 5G RAN mobility and handover performance using cognitive AI and predictive trajectory modeling.

PyTDC Therapeutics Data Commons

Accesses and manages AI-ready drug discovery datasets, benchmarks, and molecular oracles for therapeutic machine learning.

ReasoningBank Intelligence

Implements adaptive learning and meta-cognitive systems to enable AI agents to recognize patterns and optimize strategies through experience.

Quantum Physics Simulation (QuTiP)

Simulates and analyzes quantum mechanical systems using the Quantum Toolbox in Python (QuTiP).

AgentDB Advanced Features

Enables high-performance distributed vector search and multi-agent coordination using QUIC synchronization and hybrid search.

Vercel AI SDK Assistant

Simplifies the development of AI-powered features and autonomous agents using the Vercel AI SDK.

AgentDB Reinforcement Learning Plugins

Empowers AI agents to learn and improve through experience using 9 specialized reinforcement learning algorithms and WASM-accelerated inference.

Scikit-Bio

Analyzes biological data including sequences, phylogenetic trees, and microbial diversity metrics using specialized Python tools.

Constraint Satisfaction Solver

Solves complex logic puzzles and scheduling problems using Peter Norvig's propagate-then-search algorithmic pattern.

Astropy Astronomy Toolkit

Provides comprehensive tools for astronomical data analysis, coordinate transformations, and cosmological calculations within Python environments.

Pysam Genomic Toolkit

Manipulates genomic datasets and processes Next-Generation Sequencing (NGS) files using a Pythonic interface to htslib.

Counter Frequency Patterns

Implements efficient counting and frequency analysis patterns using Python's collections.Counter for data processing and distribution analysis.

UMAP-Learn Dimensionality Reduction

Performs high-performance nonlinear dimensionality reduction for data visualization, clustering preprocessing, and supervised manifold learning.

Python Data Grouping Patterns

Optimizes Python data structures using defaultdict for efficient grouping, adjacency lists, and nested dictionary management.

AI Prompt Optimizer

Refines and compresses LLM prompts to minimize token usage and maximize response quality.

Prompt Engineering Expert

Provides expert guidance and implementation patterns for crafting highly effective LLM prompts using advanced techniques like chain-of-thought and few-shot learning.

DiffDock Molecular Docking

Predicts high-accuracy 3D protein-ligand binding poses using diffusion-based deep learning for structure-based drug design.

Frontier-Based Graph Exploration

Implements flexible graph and tree traversal patterns with configurable DFS, BFS, and randomized exploration strategies.

Graceful Failure Coding Pattern

Implements the Norvig pattern of returning sentinel values instead of exceptions for natural algorithmic failures.

Propagate-Then-Search Logic Pattern

Optimizes constraint satisfaction problem-solving by eliminating impossibilities through inference before initiating recursive search operations.

Local Search Optimizer

Solves NP-hard optimization problems using greedy construction and iterative local improvement patterns.

Stable Matching & Gale-Shapley

Implements the Gale-Shapley algorithm to solve stable matching problems for two-sided markets like residency and admissions.

State-Driven Class Patterns

Encapsulates complex state management into robust class structures to handle transitions, backtracking, and algorithmic branching.

Side-by-Side Comparison Patterns

Visualizes code changes, algorithm results, and data states by displaying multiple outputs in parallel columns.

Python Comprehension Chain Patterns

Implements elegant, idiomatic data transformations using Pythonic list, dictionary, and set comprehensions inspired by Peter Norvig.