Remind

Auto-learns when and how to bring things back to your human's attention. Adapts timing and style to their preferences.

This skill is instruction-only and appears coherent for a reminder assistant. Before installing, confirm two things with the skill author or your platform: (1) what data sources the skill will 'observe' to learn (conversation history, calendar, email, notifications, etc.), and whether you must grant any connectors; and (2) where learned preferences and reminders are stored and how you can review or delete them. If you are concerned about autonomous learning, run it with model invocation limited or in a restricted test environment until you verify its behavior. If you plan to integrate it with calendars or email, only grant the minimum connector access required.

Type: OpenClaw Skill Name: remind Version: 1.0.0 The OpenClaw skill 'Remind' is designed to help users remember commitments and events. Its core loop involves detecting remindable items, evaluating preferences, delivering reminders, observing user reactions, and storing learned preferences for timing and style. All instructions across `SKILL.md`, `timing.md`, and `triggers.md` are consistent with this stated purpose, focusing on adaptive reminder management. There is no evidence of prompt injection attempting to subvert the agent, exfiltrate data, execute unauthorized commands, or perform any other malicious actions. The learning mechanism is described in a way that aligns with a benign, adaptive assistant feature.