Skill UI

Uses the Gemini API to autonomously plan, search, read, and synthesize detailed research reports with streaming status updates, structured outputs, and the ability to continue previous investigations for market analysis, technical reviews, or due diligence.

This skill provides comprehensive tools for AI researchers and engineers to publish, index, and manage academic papers directly on the Hugging Face Hub. It supports automatic arXiv indexing, linking papers to specific models and datasets, verifying authorship, and generating professional, markdown-based research articles. It streamlines the entire scientific publication workflow from creation to professional publication.

A comprehensive tool and API wrapper for accessing, parsing, and analyzing research papers published on Hugging Face and arXiv. Users can input various URLs or IDs (e.g., arXiv ID) to retrieve structured metadata, full markdown content, and automatically link associated resources such as models, datasets, and application spaces. Ideal for researchers and developers needing structured access to cutting-edge AI knowledge.

Compresses natural language memory files (like notes, to-do lists, and preferences) into a highly condensed 'caveman-speak' format. The tool removes filler words, articles, and redundant phrasing while strictly preserving all technical elements, including code blocks, URLs, and Markdown structure. This process significantly reduces input tokens, optimizing memory storage and retrieval efficiency.

This utility compresses natural language documents (notes, preferences, memory files) into a highly condensed, 'caveman-speak' format. Its primary function is drastically reducing input tokens for efficiency while meticulously preserving all technical substance, including code blocks, URLs, file paths, and markdown structure. Ideal for optimizing memory consumption when interacting with AI models.

Interactive workflow that interrogates scope, deliverables, constraints, and success criteria while guiding users to refine task prompts; copies the final markdown with Joyride clipboard commands and never writes code.

Refines prompt files by analyzing prior successful patterns, improving structure, wording, and clarity while preserving the original intent and markdown front matter.

This skill provides instant, LLM-optimized summaries of single research papers sourced from arXiv/AlphaXiv. It utilizes a tiered fallback system (Overview → Markdown → LaTeX Source) to ensure deep understanding. It is ideal for quickly grasping the core findings, methodology, and key details of one specific paper without needing to perform broad literature searches or multi-paper surveys.

Master the complexities of building robust Retrieval Augmented Generation (RAG) pipelines using LangChain. This guide addresses common pitfalls in vector search, such as score semantics differences (L2 vs. Cosine), embedding dimension mismatches, and chunking issues for code/Markdown. Learn best practices for selecting between FAISS, Pinecone, Chroma, and PGVector, normalizing scores, and implementing hybrid keyword+vector search for maximum retrieval quality.