Design a category-compliant Amazon main-image distinctiveness experiment based on shopper recognition and click-through evidence. Use when competing listings look interchangeable or a visual-similarity feature creates an unverified optimization hypothesis.
npx skills add https://github.com/xjli360/sealeap-amazon-skills --skill sealeap-jiuwei-amazon-main-image-distinctiveness-test
在主图政策和类目识别不变的前提下,用一个可解释的视觉变量测试点击差异,不声称能操纵视觉推荐池。
HOLD。缺少字段时明确标为 UNKNOWN 或 NEEDS_EVIDENCE,不要补造数据。
FACT、ESTIMATE、ASSUMPTION 或 UNKNOWN。结尾列出站点、数据窗口、口径、证据、关键假设、缺口、风险、下一步和所有待批准动作。证据不足时写 HOLD,不得包装成可直接执行。
执行表、指标和质量检查见 references/playbook.md。
Take xjli360/sealeap-jiuwei-amazon-main-image-distinctiveness-test from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.