# 为Codex构建自动化分诊技能：指南与VISION.md集成

- 来源：Peter Steinberger 🦞 (@steipete)
- 发布时间：2026-05-24 01:36
- AIHOT 分数：48
- AIHOT 链接：https://aihot.virxact.com/items/cmpimsz3r0ydjsljw5ij1b4eq
- 原文链接：https://x.com/steipete/status/2058240758801420530

## AI 摘要

开发者为Codex创建了一套自动化分诊技能，通过预设指南并读取项目VISION.md文件，自动处理符合特定标准的issue和PR。这些标准包括契合项目愿景、代码可高置信度推断、修复方案明确且支持实时测试。Codex利用虚拟机与计算机视觉（通过Crabbox平台）验证修复结果，实现自主工作流，减少人工介入。开发者保留手动审核环节，并在repo.bar中集成了issue浏览器，方便点击处理常见剪贴板格式的问题。该系统旨在提升开发效率，让AI承担重复性代码审查与测试任务。

## 正文

I built an autotriage skill for codex that has a set of guidelines + reads VISION.md from my repos， so issues/prs that have a clear way of
- fit vision of the project
- being inferrable in code with high confidence
- clear fix
- can be live tested

Are now worked on autonomously. Codex can use a VM + computer vision （via https://crabbox.sh ， new parallels backend） to verify fixes， so it can work without interrupting me. I manually review suggestions. Since it was tedious to type in issues， I added an issue browser into http://repo.bar that parses common clipboard formats by codex so I can click through them conveniently.