According to AlphaMoat, as of 2026-09, Casual Cron has 4,406 downloads and 1 stars — ranked #2,215 of 5,078 AI skills overall, and #420 of 969 in AI Agent.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 137 | 4.4K | 1 | - |
| SkillHub ↗ | 219 | 4.2K | 1 | — |
Platforms count differently and update at different times.
The flow detects scheduling intent (including /at and /every commands), parses time, frequency, channel, destination, and message, builds an openclaw cron add command, and confirms the parsed time, job name, and job id with the user before executing. One-shot jobs use --at (clock times convert to DST-safe ISO with the America/New_York offset for that date; near-term reminders prefer relative times like --at "20m") and must include --delete-after-run and --deliver --channel <channel> --to <destination>; repeating jobs use --every "<duration>" for intervals or --cron "<expr>" --tz "America/New_York" for clock times, both with --session isolated and --message "Output exactly: <task>". The run-guard hard rules: inside a cron job, do NOT troubleshoot, restart the gateway, or check the time; do NOT send acknowledgements or explanations; output ONLY the exact message payload and then stop. The default timezone is America/New_York (DST-aware), the default channel is telegram (overridable via CRON_DEFAULT_CHANNEL), and telegram, whatsapp, slack, discord, and signal are supported. Time formats map inputs like 8am, 8:45pm, noon, midnight, and 14:30; frequencies cover daily, weekdays (Mon-Fri), mondays, hourly, every 2 hours, weekly (defaulting to Monday), and monthly (1st of the month). It requires python3 and openclaw.
Profile published 2026-10-27
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 4.4K | — | 1 |
| 2026-08 | 4.2K | +5.5% | 1 |
| 2026-07 | 4.0K | +9.7% | 1 |
| 2026-06 | 3.7K | +5.4% | 1 |
| 2026-05 | 3.5K | — | 1 |
| 2026-03 | 2.8K | — | 1 |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
---
name: casual-cron
description: "Create Clawdbot cron jobs from natural language with strict run-guard rules. Use when: users ask to schedule reminders or messages (recurring or one-shot), especially via Telegram, or when they use /at or /every. Examples: 'Create a daily reminder at 8am', 'Remind me in 20 minutes', 'Send me a Telegram message at 3pm', '/every 2h'."
metadata: {"openclaw":{"emoji":"⏰","requires":{"bins":["python3","openclaw"],"env":["CRON_DEFAULT_CHANNEL"]}}}
---
# Casual Cron
Create Clawdbot cron jobs from natural language. Supports one-shot and repeating schedules with safe run-guard rules.
## Cron Run Guard (Hard Rules) - When running inside a cron job: do NOT troubleshoot, do NOT restart gateway, and do NOT check time. - Do NOT send acknowledgements or explanations. - Output ONLY the exact message payload and then stop. --- ## How It Works 1. Agent detects scheduling intent from user message (or `/at` / `/every` command) 2. Parses: time, frequency, channel, destination, message 3. Builds `openclaw cron add` command with correct flags 4. Confirms parsed time, job name, and job id with user before executing --- ## Scheduling Rules When a message starts with `/at` or `/every`, schedule via the CLI (NOT the cron tool API). Use: `openclaw cron add` ### /at (one-shot) - If user gives a clock time (e.g., "3pm"), convert to ISO with offset computed for America/New_York on that date (DST-safe). - Prefer relative times for near-term reminders (e.g., `--at "20m"`). - Use `--session isolated --message "Output exactly: <task>"`. - Always include `--delete-after-run`. - Always include `--deliver --channel <channel> --to <destination>`. ### /every (repeating) - If interval: use `--every "<duration>"` (no timezone needed). - If clock time: use `--cron "<expr>" --tz "America/New_York"`. - Use `--session isolated --message "Output exactly: <task>"`. - Always include `--deliver --channel <channel> --to <destination>`. ### Confirmation - Always confirm parsed time, job name, and job id with the user before finalizing. --- ## Command Reference One-shot (clock time, DST-aware): ``` openclaw cron add \ --name "Reminder example" \ --at "2026-01-28T15:00:00-05:00" \ --session isolated \ --message "Output exactly: <TASK>" \ --deliver --channel telegram --to <TELEGRAM_CHAT_ID> \ --delete-after-run ``` One-shot (relative time): ``` openclaw cron add \ --name "Reminder in 20m" \ --at "20m" \ --session isolated \ --message "Output exactly: <TASK>" \ --deliver --channel telegram --to <TELEGRAM_CHAT_ID> \ --delete-after-run ``` Repeating (clock time, DST-aware): ``` openclaw cron add \ --name "Daily 3pm reminder" \ --cron "0 15 * * *" --tz "America/New_York" \ --session isolated \ --message "Output exactly: <TASK>" \ --deliver --channel telegram --to <TELEGRAM_CHAT_ID> ``` Repeating (interval): ``` openclaw cron add \ --name "Every 2 hours" \ --every "2h" \ --session isolated \ --message "Output exactly: <TASK>" \ --deliver --channel telegram --to <TELEGRAM_CHAT_ID> ``` --- ## Configuration | Setting | Value | |---------|-------| | Default timezone | `America/New_York` (DST-aware) | | Default channel | `telegram` (override via `CRON_DEFAULT_CHANNEL` env var) | | Supported channels | telegram, whatsapp, slack, discord, signal | --- ## Supported Patterns ### Time Formats | Input | Cron | |-------|------| | `8am` | `0 8 * * *` | | `8:45pm` | `45 20 * * *` | | `noon` | `0 12 * * *` | | `midnight` | `0 0 * * *` | | `14:30` | `30 14 * * *` | ### Frequencies | Input | Behavior | |-------|----------| | `daily` / `every day` | Daily at specified time | | `weekdays` / `mon-fri` | Mon-Fri at specified time | | `mondays` / `every monday` | Weekly on Monday | | `hourly` / `every hour` | Every hour at :00 | | `every 2 hours` | `0 */2 * * *` | | `weekly` | Weekly (defaults to Monday) | | `monthly` | Monthly (1st of month) |
Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.
Finds skills in local and remote catalogs from a plain-language request and recommends what to install.
A browser-automation command line skill for AI agents.
Turns corrections and self-review into tiered memory and promotes or archives it by use.
Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.
Stores agent memory and cross-skill state as a typed, constraint-checked knowledge graph.
A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.
A guide to creating and updating effective Claude skills.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.