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.
More from coding & agent
- Tenable and AWS launch a Black Hat build event for open-source security agents and MCP servers — Dave_Maynor · 2026-07-22
- Codex helps build Valdiluce, an open-world game with climbing, gliding and gondolas — Dimillian · 2026-07-22
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22