daily-auditor

每日审计

准则

没人每天查看你的广告账户。代理机构不会（查看活动记录），Meta 不会（它的建议旨在优化 Meta 的收入），通常连你自己也不会。与此同时，社区里最好的建议是“别碰你的广告系列”，但只有在仍有人监看的情况下，这条建议才行得通。解决办法：每天查看，极少采取行动。只读审计能让你在不盲目行事的情况下按兵不动。

适用场景

• 每天早上在同一时间进行，不管情况看起来是否正常。悄无声息的故障代价最高。
• 另外：对由他人管理的任何账户进行问责检查。
• 需要 Meta Ads MCP，且仅需读取权限。

运行

Run a READ-ONLY audit of my ad account. Change nothing. Compare the last 7 complete days against the prior 7, at campaign, ad set, and ad level, and give me at most 5 findings, ranked by dollars at stake:

1. Wasted budget: spend with zero results, and where it is pooling.
2. Fading ads: flag ONLY if frequency > 4.0 AND CTR is down 30%+ vs the prior window. Name the ad.
3. Starved tests: ads that never got enough spend to be judged (Meta picked a favorite early and starved the rest). Tell me which ads never got a real test.
4. Pixel and conversion health: events that stopped firing, double-fires, or a mismatch that makes the numbers lie.
5. The one next test worth running, based on what the winners share.

For every finding: the numbers behind it, from the account. If a number is not in the account, say "no data", never estimate. If nothing is wrong in a category, say so in one line. End with: "No changes were made."

防护措施

• 只读是这项技能的核心。它提出建议；由人来决定是否采取行动。
• 最多 5 条发现。倾倒 50 行数据的仪表板不叫审计，那是作业。
• 仅比较完整的周同比数据：不完整的日期和生命周期视图都具有误导性。
• 疲劳规则（频次 > 4.0 且 CTR 下降 30%）是刻意设置的双条件启发式规则，用于避免误报。它可以被证伪；如果数据与之不符，就收紧或放宽规则，并写下原因。

理想输出

五条要点，喝咖啡前就能读完，每条都包含真实的账户数字，并以“未作任何更改。”结尾。