Anthropic’s prompt suggestions are simple, but you can’t give an LLM an open-ended question like that and expect the results you want! You, the user, are likely subconsciously picky, and there are always functional requirements that the agent won’t magically apply because it cannot read minds and behaves as a literal genie. My approach to prompting is to write the potentially-very-large individual prompt in its own Markdown file (which can be tracked in git), then tag the agent with that prompt and tell it to implement that Markdown file. Once the work is completed and manually reviewed, I manually commit the work to git, with the message referencing the specific prompt file so I have good internal tracking.
ВСУ запустили «Фламинго» вглубь России. В Москве заявили, что это британские ракеты с украинскими шильдиками16:45
，推荐阅读Line官方版本下载获取更多信息
“I don’t want to minimize what happened to the officers, but I think the police department is using this because of their dislike or disdain for the mayor,” Vomvolakis said. “I think they’re taking it out on Mr. Coulibaly. They want to pick a fight with the mayor.”
const cur = temperatures[i]; // 当前天的温度，推荐阅读爱思助手下载最新版本获取更多信息
"includeCoAuthoredBy": false
“我做的品牌，目标是全球最高端、最顶级的。”。Line官方版本下载是该领域的重要参考