算法艺术创作
algorithmic-art
通过代码和可调参数创作生成艺术与交互式视觉效果。
sealeap-taotie-amazon-third-party-tool-data-calibration【设计与创意】Calibrate third-party keyword and sales-estimate tools against each other: run the same keyword and the same high-volume ASIN through several tools, compare search volume, estimated monthly sales and trend shape, cross-check trend direction with a public search-trend source, note marketplace coverage gaps, and choose a tool set by store count and job…
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Calibrate third-party keyword and sales-estimate tools against each other: run the same keyword and the same high-volume ASIN through several tools, compare search volume, estimated monthly sales and trend shape, cross-check trend direction with a public search-trend source, note marketplace coverage gaps, and choose a tool set by store count and job to be done rather than by brand reputation.
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:对同一关键词与 ASIN 获取多来源搜索量、销量估算与趋势的第三方代理证据。
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。