agentleFS
marblue939marblue939/ai-workflow-skills/skills/codex-rules-verify/SKILL.md

codex-rules-verify

Skill0 starsChanged 23 days agoMITView on GitHub

把一版规则(含截图规则)装进 agent 的全局配置并验证它真的被加载时使用,覆盖新会话验证、旧会话不生效的判断与回滚

The file

Files
SKILL.md

全局规则装载与验证

何时触发

  • 用户给出规则(文字或截图),要求「对所有会话 / 所有项目生效」
  • 装完规则后需要证明它真的被读取,而不是写到文件就结束

步骤

  1. 抽取规则原文:截图先 OCR,逐条转成可执行的表述;含糊的条款当场问清,不自己补。
  2. 写入全局配置(例如 AGENTS.md / 全局 instruction 文件),按「优先级最高」放在文件顶部,保留原有内容不覆盖。
  3. 备份原文件:写前复制一份 *.bak,记录改动 diff。
  4. 验证装载:
    • 新会话:开一个新会话,问一个只有规则里才有答案的问题,看是否命中。
    • 旧会话:说明旧会话不会自动重载,必须新开会话才生效——不要用旧会话的失败反推规则没装上。
  5. 回滚:验证不通过就还原 *.bak,并说明失败原因。

验收

  • 规则文件顶部可读到新增条款
  • 新会话实测命中(有明确问答证据)
  • 旧会话的行为差异已解释清楚
  • 原文件备份存在,可一键回滚

坑

  • 把规则写进项目级文件却以为全局生效——作用域要写清楚。
  • 截图里的示例与规则正文混在一起,OCR 后要人工区分「规则」与「举例」。
  • 规则太长时先拆成「必须 / 建议」两段,否则模型会忽略后半部分。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.