scheduler-notification-runbook
Reliable runbook for scheduled reminders and notification workflows with OpenClaw cron. Use when creating or reviewing reminder skills, scheduling one-shot or recurring reminders, choosing between systemEvent and agentTurn payloads, selecting the correct sessionTarget, writing reminder text that will still read clearly when delivered later, validating whether a job actually fired, or troubleshooting why a scheduled notification did not deliver as expected. Especially useful for ClawHub-published skills that need production-safe reminder behavior instead of ad hoc cron setup.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/atomiccn/scheduler-notification-runbookWhat This Skill Does
The scheduler-notification-runbook provides a standardized framework for implementing time-based automation within OpenClaw. This skill serves as both a reference guide and an operational manual for developers and power users looking to build production-safe scheduled tasks. It addresses the critical architectural decisions required when moving from ad hoc cron expressions to managed, resilient notification workflows. The skill focuses on defining clear boundaries between simple system-level event notifications and complex, agent-driven background tasks that require reasoning, context access, or external tool execution. By following this runbook, you ensure that your reminders and scheduled agents fire reliably, deliver to the correct interface context, and maintain logical coherence throughout their execution lifecycle.
Installation
To integrate this skill into your environment, run the following command in your terminal or OpenClaw interface:
clawhub install openclaw/skills/skills/atomiccn/scheduler-notification-runbook
Use Cases
This skill is designed for scenarios ranging from personal productivity to backend task automation. Common use cases include:
- Creating one-shot reminders: Setting alerts for meetings or follow-ups that don't require agent reasoning upon firing.
- Managing recurring reminders: Scheduling daily or weekly notifications for recurring tasks.
- Background agent operations: Automating tasks that must perform web searches, data processing, or summarization at a specific future time.
- Context-aware follow-ups: Ensuring that scheduled agent responses occur within the specific thread where a project or conversation originated.
- Troubleshooting failed deliveries: Validating job persistence and payload delivery parameters when reminders do not appear as expected.
Example Prompts
- "Remind me in 30 minutes to review the architectural design docs; use a systemEvent payload since I just need a simple notification."
- "Schedule an agentTurn task every Monday at 9 AM in an isolated session that summarizes my pending calendar tasks and emails me a report."
- "Why did my scheduled notification fail to fire? Walk me through the troubleshooting steps in the scheduler-notification-runbook to check the session target and payload configuration."
Tips & Limitations
- Prefer systemEvent for simple, static text reminders to keep overhead low. Only leverage agentTurn when the agent must perform active reasoning or tool calls at the time of execution.
- Always define your sessionTarget explicitly. Using 'current' links the task to the session's memory, which is useful for continuity but dangerous if the session history is cleared.
- Test your scheduled tasks by setting shorter intervals initially to verify that the payload triggers and processes as intended before deploying for production-critical workflows.
- Remember that isolated sessions do not have access to the chat history of the main session unless explicitly passed via context, so design your payloads accordingly.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-atomiccn-scheduler-notification-runbook": {
"enabled": true,
"auto_update": true
}
}
}