Skill UI

This skill manages and refines search results obtained from Exa's neural search API. It provides comprehensive control over content extraction scope, allowing users to selectively retrieve metadata, highlights, full text, or structured summaries. Key features include implementing result caching with TTL, deduplicating citations, and crucial token budget management, ensuring the retrieved context fits within LLM context window limits for robust RAG pipelines.

This skill provides comprehensive tools for documenting and managing model performance on Hugging Face. It supports multiple methods for adding structured evaluation data, including extracting tables from README content, importing benchmark scores via APIs (like Artificial Analysis), and executing high-performance custom evaluations using advanced backends such as vLLM or lighteval. It ensures that all metadata is structured and compatible with model leaderboards and industry standards.

An advanced role-playing agent simulating Yann LeCun, inventor of Convolutional Neural Networks (CNN) and Chief AI Scientist at Meta. This skill allows users to interact with an expert who maintains LeCun's rigorous, technical, and challenging intellectual tone. Use it to discuss deep learning, ML theory, AI history, or obtain detailed explanations tailored to the user's expertise level (from analogies for laymen to pseudocode for researchers).

This skill provides comprehensive analysis and structured data extraction for academic research papers hosted on Hugging Face and arXiv. It can read paper content in markdown format, retrieve key metadata (authors, abstracts, GitHub repos), and identify linked assets such as associated models, datasets, and Spaces. Use this when the user provides a Hugging Face or arXiv URL, or explicitly requests a summary or explanation of an AI research topic.

A comprehensive meta-skill template designed for developers to scaffold, structure, and define specialized Agent Skills for AI platforms like GitHub Copilot. It guides users through mandatory requirements, including folder naming conventions, YAML frontmatter best practices (name, description), and structuring the skill body with detailed workflows and documentation sections. Use this when building complex, specialized AI capabilities.

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.

This meta-skill automates the entire process of creating a professional, high-quality AI short drama video from a simple topic or prompt. It intelligently drafts a shot-by-shot shooting script, maintains character and scene consistency across all shots, generates comprehensive visual assets (identity reference, per-shot compositions), and compiles the final MP4 with burned subtitles and title cards. Suitable for content creators, marketers, and storytellers needing rapid, consistent visual narratives.

A generic entry point for delegating self-contained, multi-step tasks to specialized LLM agents (Codex, Claude Code, Pi). Utilizes background processing tools to manage the full lifecycle of AI-driven sub-tasks, such as policy review, complex report synthesis, document generation, or large-scale code refactoring. Ideal for meta-skill workflows requiring full agent agency.

This skill provides a comprehensive guide for building scalable Retrieval-Augmented Generation (RAG) pipelines and persistent agent memory using Pinecone as the vector database. It covers index setup, embedding large corpuses, implementing dense and hybrid semantic search, and advanced metadata filtering for real-world production systems. Use this for building searchable knowledge bases and context-aware AI agents.

A comprehensive guide and skill for deploying large language models (LLMs) locally using the llama.cpp framework and GGUF quantization format. It covers searching the Hugging Face Hub, selecting optimal quantizations (e.g., Q4_K_M), running local servers, and achieving OpenAI-compatible API endpoints. Supports various hardware backends including CPU, Mac Metal, CUDA, and ROCm. Ideal for developers needing offline, private LLM inference.