Smart Reminder Assistant
Paste the following prompt into your AI chat to install this skill:
Install @user_41b104fd/smart-reminder-pro by following https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Casual to-dos in chat are easy to lose: a user may say “remind me to call Mr. Li tomorrow,” but a plain chat model is unlikely to remember it reliably or surface it in the next session.
How It Works
smart-reminder-pro uses an AI strategy layer + code execution layer: the model decides whether the user expresses a reminder intent, while reminder_engine.py handles local persistence, time parsing, due-date checks, and failure fallbacks. The core loop is:
- At the start of each conversation, run python reminder_engine.py check; if reminders are due, weave them naturally into the opening reply rather than emitting a system alert.
- During the conversation, detect time words, action words, or task-like phrasing, then call detect and add to record reminders without asking for confirmation or announcing “saved.”
- When the user confirms completion or requests deletion, run done or remove, with data kept in local pending.json and history.json.
Boundaries
This skill fits lightweight, private to-do reminders, not real-time multi-device scheduling or workflow approvals. Avoid storing secrets such as passwords, ID numbers, or bank account numbers; keep reminders concise, and treat ambiguous time phrases as best-effort parsing.
Use Cases
- Say casually in chat, “remind me to call Mr. Li tomorrow,” and expect a natural reminder next session.
- After accumulating follow-ups, ask “what reminders do I have?” and delete an outdated item by description.
- Tell the AI “done” after completing a task so the matching reminder is marked complete without extra steps.
- Schedule follow-ups like “submit the plan next Monday” or “check the budget in 3 days” inside the conversation.
Best For
- Sales reps who need to remember client follow-up times without switching to a to-do app.
- Operations staff juggling project milestones and wanting to log next steps in natural language.
- Engineers who schedule work items inside chat and expect due reminders in the opening reply.
- Independent consultants who prefer local storage for temporary reminders instead of cloud services.
Related Skills
Turn vague requests into structured prompts with role, task, context, and constraints, outputting only usable prompts without executing the task.
A skill for game NPC and enemy AI that separates decision, steering, and pathfinding, covering FSMs, behavior trees, A*, path caching, and pitfalls.
Provides multi-turn emotional companion chat through a third-party Agent API and supports continuing sessions via session_id.
An evaluation-driven workflow for diagnosing, optimizing, validating, and logging Agent Skills based on design patterns and anti-patterns.