Proactive-Do

Proactive todo execution, heartbeat-driven review, and structured follow-up for a markdown todo system. Use when the agent needs to review `todo/todo.md`, pi...

This skill appears coherent: it will create and update local files (todo/todo.md and agent_work/*), pick and work on up to three [new] todos, keep per-task journals, and optionally send heartbeat emails. Before enabling it: (1) confirm you are comfortable with the agent editing todo/todo.md in-place (it promises not to delete lines automatically), (2) expect it to create files/folders under agent_work/, (3) if you want to allow email delivery, prepare a delivery_prefs file or be ready to provide CLI credentials for your email tool (the skill may prompt for them at runtime), and (4) if you do not want autonomous reviews, either disable autonomous invocation or limit scheduling (cron events) so work only runs when you explicitly invoke it.

Type: OpenClaw Skill Name: proactive-do Version: 0.1.1 The 'proactive-do' skill implements a structured workflow for an AI agent to manage and execute tasks from a markdown todo list. It includes features for task prioritization, journaling in 'agent_work/', and automated reporting via the 'gog' CLI for email notifications. The instructions in SKILL.md emphasize transparency, non-destructive file handling, and safety escalations, with no evidence of malicious intent, data exfiltration, or unauthorized execution.