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-bixie-amazon-unmet-demand-keyword-to-productIdentify keywords with rising search volume and click interest but below-benchmark conversion as unmet-demand signals, then run them through AI-assisted product-candidate generation and a market, competitive, and profitability validation gate. Rejects candidates that fail the profit or IP check before sourcing. Use for 找搜索量高转化低的词、选品没方向想从需求反推、AI拓品候选验证. Do no…
Independent GitHub snapshot · Automated classification · Original documentation governs
Identify keywords with rising search volume and click interest but below-benchmark conversion as unmet-demand signals, then run them through AI-assisted product-candidate generation and a market, competitive, and profitability validation gate. Rejects candidates that fail the profit or IP check before sourcing.
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:核实候选品类的市场趋势、竞品格局与评论声音作为需求验证阶段的第三方代理证据。
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。