ads-optimize
Diagnose and draft or explicitly apply paid-ad optimizations using evidence, financial constraints, experiments, and capability-gated adapters. Use …
它会碰到什么
这一栏是扫描器报的事实，不是结论。命中多不等于有毒（安全工具、规则库、示例脚本本来就会包含危险写法），命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系，需要你自己看。
技能内容
Paid Media Optimization
Default to --draft.
- Load the latest normalized snapshot, prior decisions, monitoring results,
experiment state, conversion lag, economics, and platform capability manifest.
- Identify the decision and causal evidence; do not optimize a metric in isolation.
- Compare no-change, experiment, and mutation options, including learning, policy,
tracking, inventory, and opportunity-cost effects.
- Produce ranked recommendations with confidence and success measures.
- Convert approved recommendations into mutation plans only through the main
mutation gate.
- Apply, verify, audit, and retain rollback only when the exact operation is
enabled and remote state still matches the draft precondition.
Never use a fixed CPA multiple, budget ratio, benchmark, or novelty claim as sole
authorization to change an account.
Destructive-action boundary
Refuse permanent deletion of campaigns, ad groups, ads, audiences, conversions,
or other account objects. Permanent deletion is outside the supported mutation
contract and cannot be made safe by confirmation. Offer reversible alternatives:
leave objects paused, archive where supported, apply labels, export a backup, and
define a retention or later-review date. Do not create or apply a delete plan.
Search-term actions require a search terms report, business-relevance evidence,
and an overblocking review. Without them, request the missing evidence and do not
invent or illustrate specific negative keywords.
想直接用这个技能？
本站把开放许可（MIT / Apache 等）的技能按仓库打包整理到网盘，点一下转存到你自己的网盘，不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接，不打包。