Skill UI

Lightweight Google Drive integration with standalone OAuth authentication. No MCP server required. Supports full read/write operations: search, list, upload, download, move, copy, rename, trash files and folders. Requires Google Workspace account.

Provision, configure, and monitor NVIDIA GPU servers for AI inference and training workloads, including driver/CUDA installation, Docker GPU support, MIG partitioning, and health monitoring.

HasData is a comprehensive cloud platform designed for extracting structured public web data. It supports three core execution modes: Web Scraping API for arbitrary URLs (including JS rendering), pre-parsed Scraper APIs for known platforms (like Google or Amazon), and asynchronous Scraper Jobs for bulk or recursive crawling. Ideal for market research, e-commerce intelligence, job data collection, and local business lead generation.

Analyze health data trends and patterns over time, including weight, symptoms, medications, and lab results. Identify correlations and significant changes to provide data-driven insights. Supports multi-dimensional analysis and generates interactive HTML visualization reports using ECharts. Ideal for tracking health improvements and monitoring risks.

Automate routine HelpDesk tasks using the dedicated Rube MCP toolkit. This skill allows users to list, browse, and paginate through support tickets, manage predefined agent views, retrieve canned responses, and inspect custom field definitions, streamlining entire support workflows and improving operational efficiency.

Estimate the required memory for inference of Safetensors or GGUF models from the Hugging Face Hub using HTTP Range requests, without downloading weights. Supports optional KV cache estimation for LLMs and VLMs.

The Hugging Face Hub CLI (hf) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more. Supports authentication, cache management, and bucket operations.

Create, configure, and manage Hugging Face Hub datasets. Supports SQL querying, transformation, filtering, exporting, and pushing subsets or custom datasets to the Hub.

This skill enables users to add and manage structured evaluation results within Hugging Face model cards. It supports extracting evaluation tables from README files, importing benchmark scores via the Artificial Analysis API, and executing custom model evaluations using vLLM or lighteval backends. It ensures compatibility with the model-index metadata format for standardized model releases.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs infrastructure. Supports SFT, DPO, GRPO methods and GGUF conversion for local deployment. Requires Pro account and HF_TOKEN for Hub saving. Optimized for cloud GPU training without local setup.

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles. Ideal for AI engineers and researchers.

Create reusable command-line scripts and utilities for the Hugging Face API, enabling chaining, piping, and intermediate processing. Supports direct API access and the hf CLI tool, with examples for model search, metadata enrichment, and model card parsing.