Data Science & ML Claudeスキル

Trading Backtest & Colab Optimizer v4

Corrects multi-action trading logic bugs and optimizes backtesting notebooks for Google Colab environments.

KINTSUGI GPU-Only SLURM Scheduling

Optimizes KINTSUGI batch processing by enforcing GPU-only SLURM scheduling to achieve up to 25x speedups over CPU fallback.

Snakemake Per-Channel Resume Logic

Implements granular skip-existing checks in Snakemake wrapper scripts to resume interrupted HPC jobs without re-processing completed channels.

Globus Dataset Staging

Manages large-scale scientific dataset transfers between remote Globus endpoints and high-performance computing clusters.

Scientific Hypothesis Generator

Generates testable, evidence-based scientific hypotheses and experimental designs across multiple research domains.

Data Commons Client

Accesses and analyzes global public statistical data through the Data Commons knowledge graph and Python API.

Gemini CLI Integration

Integrates the Google Gemini CLI into Claude to provide large-context analysis, safe sandbox execution, and structured code modifications.

GWAS Database Explorer

Queries the NHGRI-EBI GWAS Catalog to retrieve genetic variant-trait associations and summary statistics.

Scientific Critical Thinking & Research Rigor

Evaluates scientific research rigor by assessing methodology, statistical validity, and bias through established frameworks like GRADE and Cochrane ROB.

Market Research Report Generator

Generates comprehensive, 50+ page professional market research reports with consulting-grade analysis and high-fidelity visualizations.

CZ CELLxGENE Census Analysis

Facilitates programmatic access to over 61 million standardized single-cell genomics data points for advanced querying and analysis.

HMDB Scientific Database Access

Access and interpret the Human Metabolome Database for metabolite identification, biomarker discovery, and clinical chemistry research.

Scanpy Single-Cell Analysis

Analyzes single-cell RNA-seq data with standardized workflows for quality control, clustering, and cell type annotation.

BRENDA Enzyme Database Integration

Accesses the BRENDA database via SOAP API to retrieve kinetic parameters, reaction equations, and organism-specific enzyme data for biochemical research.

Prompt Engineer

Architects high-performance system instructions and prompt patterns to optimize Large Language Model outputs and consistency.

Hybrid Search Implementation

Combines semantic vector similarity with keyword-based retrieval to maximize search recall and accuracy in AI applications.

Academic Research Engineer

Implements high-performance systems and complex algorithms with absolute scientific rigor and formal correctness.

Project Designer

Transforms initial software concepts into comprehensive, well-architected technical designs and implementation roadmaps.

Voice AI Development Architect

Builds low-latency, production-grade voice applications using real-time APIs, advanced synthesis, and streaming transcription services.

RDKit Cheminformatics

Performs advanced molecular analysis and manipulation using the RDKit toolkit for drug discovery and computational chemistry.

Scientific Schematics

Generates publication-quality scientific diagrams and technical schematics with automated AI quality review and smart iteration.

Reference Indexer

Indexes and manages external reference documents to power Retrieval-Augmented Generation (RAG) for domain-specific AI workflows.

PyTorch Docstring Writer

Generates and updates professional PyTorch-style docstrings using Sphinx and reStructuredText conventions.

LatchBio Integration

Builds and deploys bioinformatics workflows using the Latch SDK and serverless cloud infrastructure.

Math Intelligence Router

Orchestrates complex mathematical computations by deterministically routing natural language requests to specialized CLI tools for symbolic math, logic, and geometry.

DNAnexus Genomics Integration

Streamlines genomics pipeline development and data management on the DNAnexus cloud platform using the dxpy Python SDK.

Adaptyv Protein Lab

Connects Claude to cloud laboratory services for automated protein testing, sequence optimization, and wet-lab validation.

bioRxiv Research Database Search

Searches and retrieves life sciences preprints from the bioRxiv database with advanced filtering and PDF download capabilities.

PyTorch Geometric (PyG) Support

Enables development and training of Graph Neural Networks (GNNs) using the PyTorch Geometric library.

Research Question Refiner

Transforms vague research interests into concrete, actionable, and tractable research questions with a systematic feasibility analysis.