Data Science & ML Claudeスキル

Marimo Reactive Notebooks

Develops and manages reactive Python notebooks that function as pure-code files, interactive data apps, and reproducible scripts.

Biopython Molecular Biology Toolkit

Streamlines computational molecular biology tasks including sequence analysis, biological file parsing, and programmatic NCBI database access.

LangChain Architecture & Agent Design

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

Neuropixels Data Analysis

Streamlines the analysis of high-density neural recordings from Neuropixels probes through automated preprocessing, spike sorting, and quality curation.

Unsloth Model Inference

Deploys and optimizes fine-tuned LLMs using native Unsloth kernels, vLLM, or SGLang for high-performance production serving.

D3.js Visualisation

Builds sophisticated, interactive data visualizations and custom SVG-based charts using the D3.js library.

PathML Computational Pathology

Processes and analyzes whole-slide pathology images using advanced machine learning, spatial graph construction, and multiparametric imaging workflows.

Modal Cloud Compute

Deploys and runs Python applications on serverless cloud infrastructure with automatic scaling and GPU acceleration.

LLM Evaluation Framework

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

Advanced Excel & Financial Modeling

Creates, edits, and analyzes professional Excel workbooks with dynamic formulas, automated recalculation, and industry-standard formatting.

GPU Memory Cleanup

Prevents Jupyter notebook hangs by explicitly managing CuPy GPU memory pools and Python garbage collection.

ENA Database Access

Retrieves nucleotide sequences, raw sequencing reads, and metadata from the European Nucleotide Archive for genomics research.

Rapid Quantitative Implementation

Accelerates the development of financial models and UI components by building and running functional code immediately for instant visual feedback.

Moodle AI Subsystem Integration

Streamlines the development of AI-powered features within the Moodle LMS using the official AI Subsystem for version 4.5 and above.

Stonk: Ethical Investment Intelligence

Analyzes global investments through the lens of power structures, ethical constraints, and geopolitical alignments.

AI Gateway Manager

Manages and routes requests across multiple AI providers including Anthropic, Ollama, and HuggingFace.

PyTDC (Therapeutics Data Commons)

Accesses AI-ready drug discovery datasets and benchmarks for therapeutic machine learning and pharmacological prediction.

Structural Biology Analysis

Analyzes protein and molecular structures through AlphaFold interpretation, quality validation metrics, and comparative structural techniques.

Adaptyv Protein Design & Validation

Automates protein testing and validation through a cloud-based laboratory platform for accelerated biotechnological research and sequence optimization.

LLM Embedding Strategies

Optimizes semantic search and RAG applications by selecting, implementing, and fine-tuning high-performance embedding models and chunking strategies.

Denario Scientific Research Assistant

Automates the end-to-end scientific research pipeline from hypothesis generation and data analysis to publication-ready LaTeX manuscripts.

HPC Development & Testing Workflow

Streamlines scientific development on HPC environments using multi-root workspaces and automated test data extraction.

GPU Parallel Scheduling & Memory Safety

Implements queue-based GPU allocation and memory cleanup patterns to prevent OOM crashes and ensure reliable progress tracking in parallel workflows.

Prompt Engineering Patterns

Implement advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production environments.

Data Ingestion Builder

Automates the creation of robust data ingestion providers using standardized patterns for registry mapping, storage abstraction, and metadata tracking.

Excel & Spreadsheet Expert

Creates, edits, and analyzes sophisticated Excel spreadsheets with advanced formula support and industry-standard financial formatting.

Gold Revaluation Stress Test

Calculates implied gold prices and sovereign backing ratios to stress-test currency stability in scenarios where the USD loses its reserve status.

Data Commons Client

Provides programmatic access to global statistical data for demographic, economic, and environmental research.

LLM Evaluation Framework

Implement comprehensive evaluation strategies for AI applications using automated metrics, LLM-as-judge patterns, and human feedback.

Cirq Quantum Computing

Designs, simulates, and executes quantum circuits using Google's Cirq framework for NISQ-era hardware and noise-aware algorithms.