Originally published on AIPOCH As AI-powered medical research workflows become more common, agent skills are increasingly used to support disease mechanism analysis. However, even when two skills are designed for the same task, their quality can differ significantly depending on workflow structure, evidence handling, and execution design. To better understand these differences, I compared two disease mechanism agent skills using MedSkillAudit, a standardized framework for evaluating medical research agent skills. AIPOCH disease-mechanism-evidence-map The Agent Skill Description: Systematically maps mechanism evidence for a disease from molecules to pathways, cell types, tissues, biological consequences, and clinical phenotypes. Always use this skill when a user needs a layered mechanism evidence chain rather than a flat summary or immediate gap analysis. Formal literature citations must be real and verifiable.…