AI/ML

An ambitious tool for distributed neural network training with innovative features like divergent patterns and decentralized autonomous agents, but suffers from incomplete documentation and unclear security implementation.

A comprehensive log analysis skill for MassGen experiments that provides structured workflows for running experiments, monitoring progress, and analyzing traces with detailed SQL queries.

Provides scikit-survival integration for survival analysis tasks including Cox models, random survival forests, and competing risks analysis. Includes practical guidance on model selection, data preprocessing, and performance evaluation with concrete code examples.

A sophisticated multi-agent orchestration skill with innovative topology patterns and comprehensive coordination features, though lacking concrete implementation details and security considerations.

Provides practical guidance for building LLM applications with LangChain, covering agents, chains, memory, and document processing. Includes working code examples for common patterns like RAG and multi-step workflows, plus testing and optimization tips.

Provides comprehensive guidance for using Hugging Face Transformers library across NLP, vision, and audio tasks. Covers installation, authentication, pipelines for quick inference, model loading, text generation, fine-tuning, and tokenization with practical code examples.

Provides detailed guidance for building AI agents with Google's Agent Development Kit, covering architecture patterns, deployment options, and MCP integration. Includes concrete code examples for different agent types and production deployment scenarios.

This skill provides step-by-step guidance for performing bulk RNA-seq differential expression analysis using the omicverse Python package. It covers the complete workflow from loading count matrices and gene ID mapping to statistical testing, visualization, and pathway enrichment analysis.

This skill provides guidance for running gene set enrichment analysis (GSEA) in OmicVerse. It focuses on the critical step of correctly loading pathway databases as dictionaries instead of file paths, which is a common error. Includes workflow examples, error solutions, and visualization methods.

Histolab provides Python tools for processing whole slide pathology images. It detects tissue regions, extracts tiles using random, grid, or scoring methods, and prepares datasets for computational pathology workflows. The skill includes sample datasets, multiple mask types, and detailed troubleshooting guides for common extraction issues.

Provides Claude access to the pymoo Python library for solving single and multi-objective optimization problems using evolutionary algorithms like NSGA-II, NSGA-III, and MOEA/D. Handles constraint optimization, benchmark problems (ZDT, DTLZ), and offers customizable genetic operators for engineering design and research applications.

This skill provides image generation and editing using Google's Gemini API. It supports text-to-image, image editing, style transfer, and multi-turn refinement. The documentation clearly explains resolution options, aspect ratios, and critical file format handling to avoid common errors.