做什么
大师OpenClaw的计时系统. 用于安排可靠的提醒, 设置定期维护( janitor job) , 以及理解何时使用 Cron vs Heartbeat 执行时间敏感的任务 .
技能库 智客分类:其他 cron-mastery OpenClaw
大师OpenClaw的计时系统. 用于安排可靠的提醒, 设置定期维护( janitor job) , 以及理解何时使用 Cron vs Heartbeat 执行时间敏感的任务 .
官方网址:ClawHub
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
大师OpenClaw的计时系统. 用于安排可靠的提醒, 设置定期维护( janitor job) , 以及理解何时使用 Cron vs Heartbeat 执行时间敏感的任务 .
用于时间敏感任务的 Cron vs Heartbeat
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Cron Mastery、The Core Principle、1. Setting Reliable Reminders (2026.2.15+ Standard)、Precision & The "Scheduler Tick"、Modern One-Shot Reminder Pattern、Cron Concurrency Rule (Stabilized)。
文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。
Master OpenClaw's timing systems. Use for scheduling reliable reminders, setting up periodic maintenance (janitor jobs), and understanding when to use Cron vs Heartbeat for time-sensitive tasks.
Cron MasteryThe Core Principle1. Setting Reliable Reminders (2026.2.15+ Standard)Precision & The "Scheduler Tick"Modern One-Shot Reminder PatternCron Concurrency Rule (Stabilized)2. The Janitor (Auto-Cleanup) - LEGACYWhy use `sessionTarget: "main"`? (CRITICAL)3. Reference: Timezone Lock4. The Self-Wake Rule (Behavioral)5. Legacy Migration GuideTroubleshooting
来源分类:ClawHub Cron
市场来源:ClawHub
namecron-masterydescription具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「cron-mastery」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-f15dd6d8fa174482-%E5%85%8B%E9%BE%99%E5%A4%A7%E5%B8%88.html 请存为 .cursor/skills/cron-mastery/SKILL.md 或 .claude/skills/cron-mastery/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
当前没有明确的 GitHub 技能包地址,请按来源页面的安装器说明操作。
Rule #1: Heartbeats drift. Cron is precise.
This skill provides the definitive guide for managing time in OpenClaw 2026.2.15+. It solves the "I missed my reminder" problem by enforcing a strict separation between casual checks (heartbeat) and hard schedules (cron).
| System | Behavior | Best For | Risk | | :--- | :--- | :--- | :--- | | Heartbeat | "I'll check in when I can" (e.g., every 30-60m) | Email checks, casual news summaries, low-priority polling. | Drift: A "remind me in 10m" task will fail if the heartbeat is 30m. | | Cron | "I will run at exactly X time" | Reminders ("in 5 mins"), daily reports, system maintenance. | Clutter: Creates one-off jobs that need cleanup. |
Rule: Never use act:wait or internal loops for long delays (>1 min). Use cron:add with a one-shot at schedule.
While Cron is precise, execution depends on the Gateway Heartbeat (typically every 10-60s). A job set for :00 seconds will fire on the first "tick" after that time. Expect up to ~30s of variance depending on your gateway config.
Use this payload structure for "remind me in X minutes" tasks.
Key Features (v2026.2.15+):
nextRunAtMs corruption and "Add-then-Update" deadlocks are resolved.deleteAfterRun: true).CRITICAL: Push Notifications vs. Silent Logs
For push-notification reminders (Reliable):
{
"name": "Remind: Water",
"schedule": { "kind": "at", "at": "2026-02-06T01:30:00Z" },
"payload": {
"kind": "agentTurn",
"message": "DELIVER THIS EXACT MESSAGE TO THE USER WITHOUT MODIFICATION OR COMMENTARY:\n\n💧 Drink water, Momo!"
},
"sessionTarget": "isolated",
"delivery": { "mode": "announce", "channel": "telegram", "to": "1027899060" }
}
For background logs (Silent):
{
"name": "Log: System Pulse",
"schedule": { "kind": "every", "everyMs": 3600000 },
"payload": {
"kind": "systemEvent",
"text": "[PULSE] System healthy."
},
"sessionTarget": "main"
}
Pre-2026.2.15, the "Add-then-Update" pattern caused deadlocks. While this is now stabilized, it is still best practice to pass all parameters (including wakeMode: "now") directly in the initial cron.add call for maximum efficiency.
Note: As of v2026.2.14, OpenClaw includes maintenance recompute semantics. The gateway now automatically cleans up stuck jobs and repairs corrupted schedules.
Manual cleanup is only needed for:
deleteAfterRun: false.sessionTarget: "main"? (CRITICAL)Sub-agents (isolated) often have restricted tool policies and cannot call gateway or delete other cron jobs. For system maintenance like the Janitor, always target the main session via systemEvent so the primary agent (with full tool access) performs the cleanup.
For cron to work, the agent must know its time.
MEMORY.md.Timezone: Cairo (GMT+2)Problem: If you say "I'll wait 30 seconds" and end your turn, you go to sleep. You cannot wake up without an event. Solution: If you need to "wait" across turns, you MUST schedule a Cron job.
act:wait).wakeMode: "now".If you have old cron jobs using these patterns, update them:
| Legacy (Pre-2026.2.3) | Modern (2026.2.15+) |
| :--- | :--- |
| "schedule": {"kind": "at", "atMs": 1234567890} | "schedule": {"kind": "at", "at": "2026-02-06T01:30:00Z"} |
| "deliver": true in payload | Not needed - announce mode handles delivery |
| "sessionTarget": "main" | "sessionTarget": "isolated" (default behavior) |
| Manual ghost cleanup required | One-shots auto-delete (deleteAfterRun: true) |
| cron.update after cron.add | Single-step cron.add with all properties |
cron:list. Verify the at timestamp is in the future (ISO 8601 format). Ensure wakeMode: "now" is set.cron tool takes too long (huge job list or file lock).
~/.openclaw/state/cron/jobs.json and restart the gateway if it's corrupted.agentTurn + announce mode for proactive pings."DELIVER THIS EXACT MESSAGE TO THE USER WITHOUT MODIFICATION OR COMMENTARY:\n\n💧 Your message here"其他
掌握学习、错误和校正,以便不断改进。 使用时间:(1) 命令或操作意外失败, (2) 用户更正 Claude ('No, that's wrong...', 'Actually...'), (3)用户请求具备不存在的能力,(4)外部API或工具失败,(5)克洛德意识到其知识已经过…
其他
自我反省+自我批评+自我学习+自我组织记忆. 特工评估自己的工作,发现错误,并永久改进. 当 (1) 命令,工具, API, 或操作失败时使用; (2) 用户纠正或拒绝您的工作; (3) 您意识到您的知识已经过时或不正确; (4) 您发现更好的方法; (5) 用户明确安装或引用当…
其他
将AI代理人从任务跟踪者转变为预先预测需要并不断改进的主动伙伴. 现在WAL协议,工作缓冲,自主克龙, 和战斗测试模式。 哈尔·斯塔克的一部分
其他
多搜索引擎集成16个引擎(7个CN+9 Global). 支持高级搜索操作员,时间过滤器,站点搜索,隐私引擎,和WolframAlpha知识查询. 不需要 API 密钥 .