# Phil Schmid 在 aiDotEngineer 博览会上指出 vibe-checking agent 技能在生产中会失败，并介绍了构建可靠自动化评估的方法：添加负面测试、限制文件大小、使用正则断言和消融测试
- 来源：Philipp Schmid
- 发布时间：2026-07-20 22:00
- AIWatch 分数：67
- AIWatch 标记：当日精选
- AIWatch 链接：https://aiwatch.icu/events/evt_01ky0kec2fpyfax54sysb0tw0m
- 原文链接：https://x.com/_philschmid/status/2079204690160677308
## 精选理由
常规快讯，保留列表
## AI 摘要
Phil Schmid 在 aiDotEngineer 博览会上指出 vibe-checking agent 技能在生产中会失败，并介绍了构建可靠自动化评估的方法：添加负面测试、限制文件大小、使用正则断言和消融测试。
## 正文
At the @aiDotEngineer World's Fair, I gave a talk on why vibe-checking agent skills breaks in production and how to build reliable automated evals before your users find the bugs. I talked about:
🎯 Why vague descriptions cause skill failures and how adding negative test cases prevents keyword hijacking on unrelated prompts
✂️ Why skill files over 500 lines degrade model reasoning
⚡ How to validate outcomes using simple, millisecond regex assertions across 10 to 20 production prompts.
🗑️ How to run ablation tests (with vs. without skills) to know when models have caught up and you can retire skills.
Check out the full talk and resources below: