Skill UI

A comprehensive audio generation skill designed for professional multimedia content creation. It handles three types of audio output: music (jingles, beds), voiceovers (TTS), and sound effects (SFX). The skill intelligently routes requests to advanced models like Suno V5, Udio, MiniMax TTS, and ElevenLabs, producing a single, high-quality MP3 or WAV file ready for use in marketing, video, or podcast production.

A comprehensive guide detailing best practices for designing and auditing empirical evaluations of Large Language Models (LLMs). It addresses critical pitfalls such as data contamination, baseline unfairness, model version drift, and decoding parameter sensitivity, ensuring that published results are robust, reproducible, and scientifically sound for academic publication.

A rigorous framework for designing reproducible and scientifically sound experiments in robotics and AI, specifically for academic publication (e.g., RSS). It guides users to shift focus from simple system demonstration to testing a falsifiable scientific claim. Key areas covered include deriving conditions from a claim, establishing hardware trial protocols, managing simulation vs. real-world evidence splits, and performing detailed failure attribution analysis.