executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
sealeap-dijiang-amazon-conversion-rate-keyword-filterFilter and prioritize keywords by historical conversion rate and market-concentration signals rather than raw search volume alone, manually verify each candidate phrase against live search results for genuine relevance, and split the surviving list into primary listing/PPC terms versus backend-only indexing terms. Use for 大词好还是长尾词好、关键词该放正文还是后台、怎么判断一个词值不值得砸广…
Independent GitHub snapshot · Automated classification · Original documentation governs
Filter and prioritize keywords by historical conversion rate and market-concentration signals rather than raw search volume alone, manually verify each candidate phrase against live search results for genuine relevance, and split the surviving list into primary listing/PPC terms versus backend-only indexing terms.
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:获取候选关键词的历史成交转化率与市场集中度等第三方估算指标,作为按搜索量排序之外的补充筛选证据。
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。