Rebuild an unprofitable Amazon ad account by replacing head-term dependence with a verified keyword universe, root-based broad tests, pre-emptive negatives, exact harvesting, and portfolio-level profit controls. Use when ACoS is extreme, lowering ads kills sales, or a product needs a structured turnaround. Do not promise a fixed turnaround period.
npx skills add https://github.com/xjli360/sealeap-amazon-skills --skill sealeap-amazon-ad-profit-turnaround
在不依赖高价大词硬扛的情况下,重新找到可盈利查询组合并恢复可控订单。
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。
只有在本任务确实需要外部市场、竞品、关键词或公开网页证据时,才读取 references/mcp-data-plan.md,并使用 scripts/mcp_research.py。
按查询、目标、广告位和活动找出亏损来源,计算关闭风险与可保留的订单。
合并自有查询和授权研究,按高相关词根、次级词根、不相关词根和核心词分类。
用紧密自动和词根级广泛测试,先加入经过复核的不相关词根否定,并设置组合预算帽。
预算有限时从最相关词根开始;比较 CVR、CPA、利润和样本,不追求一次覆盖全部词。
稳定出单词迁移到精准广告,单独管理预算;探索层用去重规则继续发现。
新结构达到订单与利润门槛后才逐步降低旧大词依赖,并监控总销量、TACoS 和库存。
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-profit-turnaround 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.