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-bifang-amazon-keyword-optimization-loopRun a five-stage keyword workflow for an Amazon listing: collect candidate terms from several comparable ASINs, screen them by product-fact relevance and observed performance, embed the shortlist into listing copy, raise weight on a few priority terms through controlled advertising, then monitor indexing and rank to decide what to add, cut or roll back. Use…
Independent GitHub snapshot · Automated classification · Original documentation governs
Run a five-stage keyword workflow for an Amazon listing: collect candidate terms from several comparable ASINs, screen them by product-fact relevance and observed performance, embed the shortlist into listing copy, raise weight on a few priority terms through controlled advertising, then monitor indexing and rank to decide what to add, cut or roll back.
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:获取可比 ASIN 的关键词反查、搜索量与相关词代理数据。
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。