Skill UI

Provides comprehensive guidance on building robust evaluation frameworks for complex agent systems. It addresses the inherent challenges of non-determinism and multiple valid paths, enabling systematic performance testing, validating context engineering choices, and measuring continuous improvements across multiple quality dimensions (e.g., factual accuracy, tool efficiency).

Simulates a rigorous international journal peer review process using an expert team of 5 reviewers (EIC, 3 Peers, Devil's Advocate). It assesses papers from multiple, non-overlapping perspectives—including methodology, deep domain expertise, and core argument challenges—to generate a structured editorial decision and revision roadmap. Supports modes for initial review, re-review of revisions, and methodology focus.

This skill generates a comprehensive issue report on the current challenges, limitations, and open problems within Japanese Natural Language Processing (NLP) for a specified topic. By combining knowledge from a curated local dataset with real-time web search, it provides a deep dive into ongoing research gaps, evaluating the state-of-the-art and recommending areas for future work.