A professional framework for creating and managing reliable, scheduled AI tasks and periodic workflows within OpenClaw.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install cron-setup
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install cron-setup using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Cron Job Setup skill provides a standardized methodology for implementing automated, recurring tasks using Openclaw Skills. It allows developers to define complex schedules using cron expressions, ensuring that AI agents can perform background operations like system monitoring, data aggregation, and status reporting without manual triggers.
By emphasizing isolated sessions and specific model selections like Claude Sonnet 4.5, this skill ensures high reliability for tool calls while maintaining cost-efficiency. It is designed to handle everything from simple 30-minute inbox checks to comprehensive daily workspace summaries, providing a robust backbone for autonomous agent operations.
To get started with scheduled tasks in Openclaw Skills, you can view your current configuration or add new jobs using the CLI. Use the following command to see active jobs:
cron list
When defining a new job, use the standardized JSON template. Ensure you specify the model as anthropic/claude-sonnet-4-5 for the best balance of reliability and speed:
# Example of a job registration payload
{
"name": "daily-cleanup",
"schedule": {
"kind": "cron",
"expr": "0 4 * * *",
"tz": "America/New_York"
},
"payload": {
"kind": "agentTurn",
"message": "Run cleanup scripts and report status",
"model": "anthropic/claude-sonnet-4-5"
}
}
The skill organizes cron jobs using a structured JSON schema to ensure compatibility across Openclaw Skills. Below is the primary metadata taxonomy:
| Property | Description | Expected Value |
|---|---|---|
name |
Unique identifier | Kebab-case string (e.g., inbox-check) |
schedule |
Timing configuration | Object containing kind, expr, and tz |
sessionTarget |
Execution environment | Usually isolated for background tasks |
payload |
Task details | Object containing message, model, and timeoutSeconds |
delivery |
Output handling | Object with mode (none/announce) and optional channel targets |
Loading
Automatically stage changes, generate AI-driven commit messages, and push code to your remote repository in one seamless workflow.

A specialized tool for managing Caddy-based reverse proxy routes with wildcard subdomain support and automated HTTPS for local services.

A browser automation skill for purchasing, reordering, and processing returns on Amazon using an AI agent.

Automate the entire Amazon shopping lifecycle, from reordering essentials to processing returns, using browser-based AI agents.

A specialized utility designed to identify and remove AI-generated code slop, redundant defensive logic, and inconsistent styling from git branches.

A command-line utility to instantly expose local development projects via Caddy-managed subdomains with automated tmux session management.








































