AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻译准备中
个人 GitHub 账号下公开仓库的所有者可以登录并验证所有权,自行管理介绍,无需管理员批准。
登录并生成验证文件,在 30 分钟内将其提交到此仓库的默认分支。其他分支或分叉仓库中的文件无效。然后在下方检查文件,即可无需管理员批准直接管理项目。请保留文件以维持管理权限。
如需登录,将前往登录页面。登录后请回到此处,再次点击所选的验证按钮。
在项目文件夹中运行 /nomorevibe verify,即可验证所有权并自行管理介绍。
一分钟完成验证AI-powered task tracker: annotate elements in a running web page, capture screenshots, and export structured prompts for LLM implementation.
翻译准备中
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
Tell your AI agent exactly what to fix — by clicking on it.
Vibeflow eliminates the back-and-forth of describing UI bugs in words. Click any element on a page to create a task with its exact CSS selector, URL, and source location. Your agent gets precise, actionable context — no "the button in the top right" needed.
AI agents write code fast, but understanding what to change is slow. Describing a UI issue in prose wastes tokens and produces wrong fixes.
Vibeflow turns visual feedback into structured tasks:查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
Tell your AI agent exactly what to fix — by clicking on it.
Vibeflow eliminates the back-and-forth of describing UI bugs in words. Click any element on a page to create a task with its exact CSS selector, URL, and source location. Your agent gets precise, actionable context — no "the button in the top right" needed.
AI agents write code fast, but understanding what to change is slow. Describing a UI issue in prose wastes tokens and produces wrong fixes.
Vibeflow turns visual feedback into structured tasks:查看完整 README ↗