name: calendar-reminders description: Calendar reminders pipeline: config-driven wrapper around gcalcli (Google Calendar) plus optional CalDAV source via vdirsyncer+khal, and a reminder planner that outputs a JSON plan for one-shot OpenClaw reminders.
This skill provides:
- scripts/calendar — wrapper around gcalcli
- scripts/calendar_reminder_plan.py — produces a JSON plan for reminder scheduling
- references/openclaw-calendar.example.json — example config format
Copy the example config to a private location and edit it:
~/.config/openclaw/calendar.jsonOPENCLAW_CALENDAR_CONFIG=/path/to/calendar.json想要更强大的技能插件,就来小葱技能站7w4.net看看吧。
python3, gcalclivdirsyncer, khalThis skill invokes external binaries and is config-driven.
gcalcli/khal using subprocess.check_output([...], shell=False) (argument-list form; safe against shell injection from event titles).vdirsyncerSyncCommand, make sure you run it as an argv list (subprocess.run(cmd_list, shell=False)), not as a shell string.gcalcliPath / khalBin to trusted binaries (prefer absolute paths). Don’t run untrusted paths.gcalcli requires OAuth. On headless servers you may need SSH port-forwarding.
The wrapper uses --noauth_local_server to print instructions.
The planner outputs a JSON blob describing reminders to schedule. A separate cron job (or an agent turn) can read it and create one-shot OpenClaw reminders.
Defaults: - Ignore birthdays. - Timed events are considered important. - All-day events only trigger reminders if their title matches configured keywords.
Create a daily cron job (e.g. 00:05 local time) that:
1) If CalDAV is enabled in config, runs the configured vdirsyncer sync command.
2) Runs scripts/calendar_reminder_plan.py to get a JSON plan.
3) For each planned reminder, creates a one-shot OpenClaw systemEvent reminder at reminderAtUtc.
4) Writes a small state file so you don’t schedule duplicates.
(Our skill intentionally provides the wrapper + planner; scheduling is left to your cron/agent wiring.)
这是一个设计合理的日历提醒工具,支持 Google 和 iCloud 双日历源,配置灵活,可避免重复提醒。文档清晰、安全考虑充分。但目前只提供了提醒规划部分,功能不够完整;依赖较多外部工具设置复杂;缺少自动化测试。整体质量中上,功能完善度还有提升空间。