Skill UI

A comprehensive, model-agnostic toolkit for advanced LLM development. It enables iterative prompt optimization through static analysis (token usage, clarity), measures critical RAG metrics (relevance, faithfulness, coverage), and validates complex agent workflows and configurations. Essential for rigorous LLM quality assurance and cost management.

This skill provides comprehensive monitoring advisory services for data assets and AI agents. It helps users assess data coverage gaps, analyze use-case criticality, and automatically create data quality monitors (table, metric, validation). Furthermore, it enables monitoring of AI agent performance, latency, and observability, ensuring robust data governance across the entire ML lifecycle.

The /goal command converts standard agent prompts into persistent, self-correcting loops (plan → act → test → review → iterate). It is designed for long-running, complex engineering tasks like migrations, coverage lifts, or refactoring, ensuring progress is tracked against a verifiable stop condition and mandated documentation.

This comprehensive guide outlines best practices for designing, evaluating, and reporting experimental results in speech processing research (ASR, TTS, Speaker Verification, etc.). It details required metrics (WER, MOS, EER), establishing robust baselines, conducting significance testing (bootstrap, CI), and ensuring comprehensive condition coverage (speakers, noise, languages) to enhance the scientific rigor of academic submissions.