writing-skills
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
sealeap-baxia-amazon-ai-agent-deployment-boundaryGate adoption of self-hosted open-source AI agent tooling for back-office Amazon operations behind a public-exposure security check and a task-complexity boundary that currently excludes advertising and product-selection decisions. Use for 自建AI智能体自动化前的安全自查、判断哪些环节适合当前交给智能体、智能体使用边界评审. Do not use to hand advertising bid changes, campaign creation, or product-s…
Independent GitHub snapshot · Automated classification · Original documentation governs
Gate adoption of self-hosted open-source AI agent tooling for back-office Amazon operations behind a public-exposure security check and a task-complexity boundary that currently excludes advertising and product-selection decisions.
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。
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。