remind-me for Openclaw

A natural language reminder skill that automates cron job creation and maintains a local markdown-based history log.

julianengel
v2.1.0
Jan 6, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install remind-me

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install remind-me using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is remind-me?

The remind-me skill is a robust automation tool designed for AI agents to handle scheduling tasks through simple, conversational language. By integrating bash-based cron scheduling with local markdown logging, it provides a seamless bridge between natural language requests and system-level task execution. This Openclaw Skills component ensures you never miss a deadline by converting phrases like "remind me in 2 hours" into precise, actionable system events.\n\nBuilt for developers and power users, this skill emphasizes transparency and control. Every reminder created is tracked in a human-readable format, allowing for easy auditing and manual management via the command line. Whether you are managing personal habits or professional deadlines, this skill offers a reliable, low-overhead solution for time-based automation within your agent environment.

remind-me Use Cases

  • Setting one-time alerts for meetings, phone calls, or immediate errands.\n- Establishing recurring daily or weekly habits such as stretching, checking emails, or submitting reports.\n- Maintaining a centralized, searchable log of all scheduled and past notifications for personal accountability.\n- Offloading memory-intensive scheduling tasks to an automated system using Openclaw Skills.

How remind-me Works

  1. The AI agent parses natural language time expressions (e.g., "next Monday at 2pm") from the user input.\n2. The system executes a bash script to create a one-time cron job using the --at flag or a recurring job using cron syntax.\n3. Task details, including a unique job ID and status, are appended to a local markdown file at /home/julian/clawd/reminders.md for persistence.\n4. At the designated timestamp, the system triggers the scheduled message or notification to the user.

remind-me Setup

Ensure your environment has bash and date utilities installed. To integrate this into your environment, follow these steps:\n\nbash\n# Ensure execution permissions for the core scripts\nchmod +x /home/julian/clawd/skills/remind-me/create-reminder.sh\nchmod +x /home/julian/clawd/skills/remind-me/create-recurring.sh\n\n# Verify the log file path exists and is writable\ntouch /home/julian/clawd/reminders.md\n

remind-me Data Schema & Taxonomy

The skill maintains a structured log in markdown format to track the lifecycle of every reminder. This allows Openclaw Skills to maintain a historical record of all interactions.\n\n| Field | Description |\n| :--- | :--- |\n| Status | Current state: [scheduled], [recurring], or [sent] |\n| Schedule | ISO date-time, relative time, or cron-style frequency |\n| Description | The specific task or message to be delivered |\n| Job ID | A unique identifier used for manual job removal (e.g., abc123) |\n\nExample entry:\n- [scheduled] 2026-01-06 17:00 | Pay for Gumroad (id: abc123)

remind-me Advanced Features

  • Support for complex relative time parsing including "later today", "tonight", and "this afternoon".\n- Flexible interval scheduling for recurring tasks (e.g., "every 30 minutes" or "every 2 hours").\n- Manual job management via CLI commands such as cron list and cron rm <job-id>.\n- Persistent markdown-based logging for easy integration with other Openclaw Skills and note-taking tools.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*