Skill UI

This skill evaluates content for AI citability based on research from Princeton and Georgia Tech. It scores content on answer block quality, self-containment, and structural readability to optimize visibility in AI-generated responses. Ideal for SEO and GEO strategies to ensure AI models extract and cite your content effectively.

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.

Look up Hugging Face paper pages as markdown and query the papers API for structured metadata including authors, linked models, datasets, Spaces, GitHub repos, and project pages. Ideal for summarizing or analyzing AI research papers from hf.co or arXiv URLs and IDs.

This skill covers setting up infrastructure for fine-tuning Large Language Models (LLMs) using techniques like QLoRA, LoRA, and full fine-tuning. It includes configuring distributed training with DeepSpeed or FSDP, utilizing frameworks such as Hugging Face TRL and Axolotl, and implementing alignment methods like RLHF and DPO. Suitable for domain-specific model adaptation and production deployment.

Discover, find, compare, audit, repair, adapt, craft, run, debrief, and prepare repeatable AI-agent loops for publication. A comprehensive tool for managing bounded feedback loops in AI agent workflows.

A remote MCP server designed for AI agents to dynamically discover, inspect, and verify external tools, APIs, and services. It allows agents to search a curated index of AI-ready websites, check for machine-readable endpoints (like OpenAPI or MCP), and confirm if an endpoint responds correctly to JSON-RPC, enabling robust, dynamic agent workflow building.

This skill implements advanced 'Gatekeeper' logic to optimize AI agent performance in long-running workflows. It prevents context window bloat by sharding metadata, allocating token budgets, and enforcing Atomic Precision to deliver purely functional, filler-free responses. Ideal for complex coding, multi-step reasoning, and large document analysis where conciseness is critical.

Train and fine-tune transformer language models with Hugging Face TRL via CLI. Covers SFT, DPO, GRPO, RLOO, KTO and reward model training, plus LoRA adapters, YAML configs and distributed multi-GPU runs.