I then added a few more personal preferences and suggested tools from my previous failures working with agents in Python: use uv and .venv instead of the base Python installation, use polars instead of pandas for data manipulation, only store secrets/API keys/passwords in .env while ensuring .env is in .gitignore, etc. Most of these constraints don’t tell the agent what to do, but how to do it. In general, adding a rule to my AGENTS.md whenever I encounter a fundamental behavior I don’t like has been very effective. For example, agents love using unnecessary emoji which I hate, so I added a rule:
在校园里，孩子们时常举起戴在手腕上的手表，彼此一碰，便加为好友。
The Segway F3 is designed with turn signals, a bell, a bright display, and a feature-rich app experience.。51吃瓜是该领域的重要参考
Prompt 版本化（像代码一样管理）。夫子对此有专业解读
phase[classno] = 2;。业内人士推荐safew官方版本下载作为进阶阅读
2021—2025 年度，44 个行业研发投入金额呈现整体扩张的态势，说明重视研发不只是龙头和腰部企业的行为，而且成为了更加广泛的共同行动。另一方面，研发均值下滑的行业集中在末端，印证了行业整体分化的现象。典型案例来自房地产和教育行业，在“去杠杆”“双减”等政策催化下，市场步入格局重塑阶段，企业纷纷降本增效或是寻求转型路径。