Data Science & ML Claude 技能

DocETL Pipeline Developer

Builds and executes LLM-powered data processing pipelines for unstructured document analysis using DocETL and Claude Haiku.

ERA5 Climate Data Downloader

Retrieves global atmospheric, land, and ocean climate reanalysis data from the Copernicus Climate Data Store using the CDS API.

Gemini Token Optimization

Optimizes token usage and reduces operational costs when delegating tasks to the Gemini CLI.

Running Readiness Check

Evaluates athlete health signals and training load to provide conservative pre-run activity recommendations.

Run-Smart AI Skill Registry

Manages the discovery, safety guardrails, and shared contracts for Run-Smart AI coaching skills.

Data & AI Engineering

Builds and deploys robust machine learning models, data pipelines, and intelligent LLM applications using Python and industry-standard frameworks.

Data, AI & Machine Learning Roadmap

Provides comprehensive guidance and implementation patterns for data science, machine learning engineering, and AI application development.

LayerChart Svelte Visualizations

Builds sophisticated, responsive, and interactive data visualizations in Svelte using unopinionated building blocks and motion primitives.

SHAP Model Interpretability

Explains machine learning model predictions and feature importance using mathematically grounded Shapley values and high-impact visualizations.

ESM Protein Design & Analysis

Empowers protein engineering and biological research through state-of-the-art ESM3 generative models and ESM C embeddings.

Advanced Excel & Spreadsheet Engineering

Creates, modifies, and analyzes professional Excel spreadsheets with automated formula recalculation and industry-standard financial formatting.

OpenAlex Academic Literature

Queries and analyzes the OpenAlex database to search scholarly literature, track citations, and perform bibliometric analysis.

Bioinformatics & Genomic Data (gget)

Provides a unified interface for rapid bioinformatics queries across 20+ genomic databases including Ensembl, AlphaFold, and NCBI.

Flow Nexus Neural Networks

Trains and deploys complex neural network architectures within distributed E2B sandbox environments using Flow Nexus.

AI Agents Architect

Designs and implements autonomous AI agents with sophisticated tool use, memory systems, and multi-agent orchestration.

AI Agents Architect

Architects and implements robust autonomous AI agents with sophisticated tool use, memory systems, and multi-agent orchestration.

Product Expert Design

Designs adaptive user-facing agent experts to create personalized product experiences and dynamic UX.

Globus Dataset Staging

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

Snakemake Per-Channel Resume Logic

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

Weighted Autofluorescence Subtraction

Enhances multiplex immunofluorescence images by applying range-specific weights to remove background noise while preserving delicate biological signals.

Denario AI Scientific Research Assistant

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

Trading Backtest & Colab Optimizer v4

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

Excel & Spreadsheet Master

Automates professional Excel spreadsheet creation, financial modeling, and data analysis with error-free formula verification.

Market Researcher

Conducts comprehensive market analysis, industry trend tracking, and market sizing calculations to drive data-informed business decisions.

Gemini CLI Integration

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

KINTSUGI GPU-Only SLURM Scheduling

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

PDF Document Automation

Enables programmatic PDF manipulation, data extraction, and document creation using professional Python and command-line tools.

Gtars Genomic Analysis

Performs high-performance genomic interval analysis, overlap detection, and machine learning tokenization using Rust-powered tools.

Scientific Hypothesis Generator

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

Scientific Critical Thinking & Research Rigor

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