Agent Skills Hub

markdown-converter

Convert various documents, media, and web content into Markdown using markitdown, ideal for LLM processing and text analysis.

agentdb-state-manager

Persistent state management and workflow analytics using DuckDB for task dependency tracking, historical metrics, and context checkpointing.

ffmpeg-skill

Universal media processing agent skill for converting, compressing, trimming, and editing audio/video files using FFmpeg.

spark-optimization

Optimize Apache Spark jobs with partitioning strategies, memory management, shuffle tuning, and data skew mitigation for high-performance data processing pipelines.

loading-insurance-data

Load, validate, and preprocess weekly insurance policy CSV data with intelligent period detection and standardization.

Data Analysis Helper

A versatile data analysis assistant for loading datasets, performing statistical calculations, visualizing trends, and generating professional summary reports.

mijia-control

Control and monitor Xiaomi Mijia smart home devices including status switching, device discovery, automation scenes, and environmental statistics.

scikit-learn

Classical machine learning with scikit-learn. Use for classification, regression, clustering, dimensionality reduction, preprocessing, model evaluation, and building robust ML pipelines in Python.

convoy

Manage batch work tracking and dispatch with Gas Town's convoy system for multi-agent orchestration.

template-skill

A flexible template for developing and integrating custom AI agent skills within the Mini-Agent framework.

connections

Lightweight MCP (Model Context Protocol) connection handler supporting stdio, SSE, and streamable HTTP transports for seamless server integration.

pytorch-lightning

PyTorch Lightning skill for scalable deep learning: automates model training, multi-GPU orchestration, data pipelines, and distributed training strategies like DDP, FSDP, and DeepSpeed.