Building an AI TODO Manager Workflow

卡尔的AI沃茨 · wechat · 2026-07-15

Using Obsidian and a custom Skill named "Butler Afu," the author created an AI TODO workflow. The core mechanism converts inbox materials into Markdown, which the AI then automatically scans to identify actionable task cards. For incomplete materials like videos or links, it uses yt-dlp and local Whisper to extract content, helping determine if a task is worth pursuing.

For scheduling, the system supports batching task cards into a scheduling pool, dragging them to a weekly view, and syncing with Mac or Feishu Calendars. If multiple topics are similar, the AI can suggest grouping them to prevent redundant efforts. The author also integrated features like overdue reminders, archiving, and easy moving/deletion. The ultimate goal is to streamline the process of offloading ideas into a trusted external system, closely aligning with GTD principles.

Original post →

More from coding & agent

coding & agent channel →