Diagnose product-page friction and turn observations into measurable test hypotheses.
Audit this independent-store product page from the buyer's decision sequence. Evaluate message clarity, offer, proof, objections, delivery, returns, mobile friction, and analytics coverage. Cite visible evidence, distinguish defects from hypotheses, and return no more than seven experiments with metric, effort, and risk.
A prioritized experiment backlog—not a redesign wishlist.
Recommendations such as “make the CTA bigger” are invalid without a documented friction point and a metric that could falsify the hypothesis.
If this prompt needs stable triggers, fixed tools, supporting files, and evaluation cases, validate it manually and then promote it to an Agent Skill.