Original Summary

I am increasingly hitting cases where agents pick something from skills in part due to regex-based reading, since putting them all in context would be less efficient, leave out the negative, and do something exactly opposite of what is intended. Just like negative prompts for diffusion models, I feel like a negative-skills file listing explicit antipatterns and bad versions could enable harnesses with fewer graph nodes to perform better.<p>I might be missing some developments, but is there an accepted&#x2F;shaping way to do this with recent models?

  • 情报分类：商业与市场研究
  • 分类依据：内容涉及商业、投资或市场动态
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/14 05:23:17