Apply a simple Amazon Ads allocation model that separates discovery from exploitation, tests keyword and placement effects, and reallocates budget toward evidence-backed conversion pockets. Use when the user asks for a clear mental model for Amazon ads, how to find good traffic, how to compare placements, or how to reduce poor traffic. Draft only unless live changes are explicitly approved.
npx skills add https://github.com/xjli360/sealeap-amazon-skills --skill sealeap-amazon-ad-traffic-allocation
用“发现高转化组合”和“重分配预算”两个循环管理广告,避免同时改变关键词、位置和预算导致无法归因。
缺失的数据要明确列为缺口,并把结论标成事实、估算或假设;不要补造数字。
探索循环负责找词、商品目标和广告位;利用循环负责给已验证组合稳定预算。
先固定目标测试广告位,或固定广告位策略测试目标,避免多变量一起变化。
以相关性、CVR、CPA、贡献利润和样本强度联合判定,而不是只看订单或 ACoS。
小步增加赢家预算或竞价,减少低相关和持续亏损流量;每次保留前后对照。
保留受控探索预算,防止主力词老化或流量结构变化后失去新机会。
观察 TACoS、总贡献利润、自然订单、库存和广告间蚕食。
结尾列出数据窗口、关键假设、证据缺口、风险和下一步;如包含待执行动作,单独放在“待批准变更”中。
Take xjli360/sealeap-amazon-ad-traffic-allocation 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.