技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
sealeap-feilian-amazon-buyer-segment-price-calibration【数据与研究】Audit whether a reported shift toward value-driven, income-segmented buying behavior actually shows up in the account's own category conversion and price-band data before rebalancing keyword bidding, price bands, and the mix between high-consideration and everyday-replenishment items. Treats third-party consumer-sentiment findings as hypotheses to co…
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Audit whether a reported shift toward value-driven, income-segmented buying behavior actually shows up in the account's own category conversion and price-band data before rebalancing keyword bidding, price bands, and the mix between high-consideration and everyday-replenishment items. Treats third-party consumer-sentiment findings as hypotheses to confirm with the account's own data, not as facts to act on directly.
用户未指定时采用“诊断”。
缺失项必须标为 NEEDS_EVIDENCE;不得猜数字、补属性或把不同站点、ASIN、变体、币种和时间窗混在一起。
先读取 references/playbook.md,确认该方法适用于当前对象。按以下顺序执行:
最后做数据充分性检查,并把结论分成 FACT / ESTIMATE / HYPOTHESIS / UNKNOWN。若关键证据不足,状态写 HOLD。
仅在自有数据不足且当前任务确实需要外部证据时,读取 references/mcp-data-plan.md,再使用 scripts/mcp_research.py。本 Skill 的外部取数目的:补充同类目下不同价格带竞品的定价分布与相关关键词搜索量变化,作为消费分层假设是否适用于当前类目的交叉验证证据。
doctor,再 search-tools 和 describe;工具名及参数以实时 tools/list 与 inputSchema 为准。tools/call 或 Actor 可能计费;先展示 Provider、工具、无密钥业务参数、预计成本与输出位置,核对已有授权覆盖后才加 --allow-cost;该标志不是费用上限。方案状态使用 READY FOR REVIEW / DRAFT / HOLD / STOP;如已执行,另行记录实际结果及回读证据。未得到明确批准时,不得声称已修改线上对象。