Token导航 LogoToken导航TokenDH.com
效率敏感数据clawhub未标认证来源可访问clear审计通过

ping-me告诉我

Agent Skill

ping-me 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

9,596

周安装

392

GitHub Stars

1

下载量

3,105
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ping-me(告诉我)
来源仓库:https://github.com/ethan-shen-individual-lab/ping-me
安装命令:
openclaw skills install ping-me
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install ping-me

简介

Ping-Me通过自然语言设置一次性提醒通知服务。

  • 适用于日程管理、会议提醒或任务截止日跟踪场景。
  • 自动识别时区与频道信息减少手动配置成本。ping-me 属于效率类 Skill,可作为该场景下的辅助能力补充。
  • 通知推送依赖第三方服务稳定性存在一定延迟可能。
  • 隐私敏感提醒建议使用端到端加密通信渠道传递消息。

SKILL.md

name
ping-me
description
One-shot reminders via natural language. Auto-detects channel and timezone. Say 'remind me...' in any language and get pinged when it's time. Works with every channel.
metadata
{"openclaw":{"emoji":"⏰","requires":{"bins":["openclaw","python3"]}}}

ping-me ⏰

Set one-shot reminders through natural language. The reminder fires once, delivers to the user's current chat channel, then auto-deletes.

Response flow: Call the script first, then confirm with one short sentence. Keep it concise — no preamble, no time calculations, just the confirmation.

How It Works

User says something like:

  • "Remind me in 30 minutes to take a break"
  • "提醒我明天下午3点交作业"
  • "3分後にお風呂に入ることを思い出させて"
  • "rappelle-moi dans 2 heures de rappeler Marie"

You parse the time and message, then call the script SILENTLY.

Channel & Delivery Target

The script auto-detects which channel the user is chatting from.

  • You do NOT need to pass --channel unless the user explicitly asks for a different channel
  • Only pass --channel when the user explicitly says "remind me on telegram" / "发到飞书" / etc.

Delivery target (--to)

Some channels (e.g. QQ Bot) require a full delivery target for announce mode. The script resolves --to automatically from:

  1. $OPENCLAW_TO environment variable (if gateway sets it)
  2. $OPENCLAW_SESSION_KEY (extracts target from session key format)
  3. config.json"to" field (user-configured)

If reminders fail with "requires target" error, the user needs to configure their target once:

bash {baseDir}/scripts/ping-me-config.sh --set to=qqbot:c2c:<openid>

You can also pass --to explicitly when calling the script.

Commands

Set a reminder

bash {baseDir}/scripts/ping-me.sh [options] <time> <message>

Time formats:

User saysYou pass as <time>
"3分钟后" / "in 3 minutes"3m
"30分钟后" / "in 30 minutes"30m
"2小时后" / "in 2 hours"2h
"明天" / "tomorrow"1d
"明天下午3点" / "tomorrow at 3pm"ISO 8601: 2026-03-11T15:00 (no tz offset needed, script uses configured tz)
"周五晚上8点" / "Friday 8pm"ISO 8601 with calculated date

IMPORTANT: For relative times (N分钟后, N小时后, in N minutes/hours), ALWAYS use the short form (3m, 2h, 1d). Do NOT convert to ISO timestamp.

Options:

  • --channel <ch> — override delivery channel (only when user explicitly requests)
  • --to <dest> — override delivery target (e.g. qqbot:c2c:<openid>)
  • --tz <tz> — override timezone for this reminder
  • --emoji <e> — custom emoji prefix

Examples:

bash {baseDir}/scripts/ping-me.sh 30m "Take a break"
bash {baseDir}/scripts/ping-me.sh 2h "Team meeting"
bash {baseDir}/scripts/ping-me.sh "2026-03-11T15:00" "Submit homework"
bash {baseDir}/scripts/ping-me.sh --channel telegram 1d "Renew subscription"

List active reminders

bash {baseDir}/scripts/ping-me-list.sh

Cancel a reminder

bash {baseDir}/scripts/ping-me-cancel.sh <job-id>

View / change settings

bash {baseDir}/scripts/ping-me-config.sh                        # Show settings
bash {baseDir}/scripts/ping-me-config.sh --set tz=Asia/Tokyo     # Change timezone
bash {baseDir}/scripts/ping-me-config.sh --set channel=qqbot     # Change default channel
bash {baseDir}/scripts/ping-me-config.sh --set to=qqbot:c2c:<openid>  # Set delivery target
bash {baseDir}/scripts/ping-me-config.sh --set emoji=🔔          # Change emoji
bash {baseDir}/scripts/ping-me-config.sh --set lang=zh           # Change language
bash {baseDir}/scripts/ping-me-config.sh --reset                 # Reset to defaults

Your Job (Agent Instructions)

Creating Reminders

  1. Detect reminder intent in any language
  2. Extract time and message
  3. For relative times → use short form (3m, 2h, 1d). For absolute times → ISO 8601 without tz offset
  4. Do NOT pass --channel or --to unless user explicitly requests a specific channel, or the script fails without it
  5. Call ping-me.sh with the parsed arguments
  6. After the script succeeds, confirm with one short sentence in the user's language

Response Style

Keep responses concise. Call the script first, then confirm briefly:

  • "⏰ Got it, pinging you in 30 minutes to take a break."
  • "⏰ 好的,3分钟后提醒你洗澡。"
  • "⏰ 已设置,明天下午3点提醒你交作业。"
  • "⏰ 3分後にリマインドします。"

No need to explain time conversion or timezone logic to the user — just confirm the reminder.

Listing & Cancelling

  • "what reminders do I have" / "我有哪些提醒" → run ping-me-list.sh
  • "cancel reminder X" / "取消提醒" → run ping-me-cancel.sh <id> (get ID from list first)

Changing Settings (Interactive)

When user wants to change settings, use ping-me-config.sh:

  • "change timezone to Tokyo" / "改时区到东京" → --set tz=Asia/Tokyo
  • "默认发到飞书" / "send reminders to feishu by default" → --set channel=feishu
  • "设置QQ投递目标" → --set to=qqbot:c2c:<openid>
  • "show my settings" / "看看设置" → run without args
  • "reset settings" / "重置设置" → --reset

After changing settings, confirm with ONE sentence.

First-Time Setup Hint

If the first reminder fails with a "requires target" or "multiple channels" error, guide the user to configure:

  1. Default channel: ping-me-config.sh --set channel=qqbot
  2. Delivery target: ping-me-config.sh --set to=qqbot:c2c:<openid>

The user's openid can be found in their QQ Bot session key or gateway logs.

Notes

  • Reminders auto-delete after firing (--delete-after-run)
  • Channel auto-detection: $OPENCLAW_CHANNEL → config → empty
  • Delivery target auto-detection: $OPENCLAW_TO → session key extraction → config → empty
  • Timezone auto-detection: config.tz → system tz → UTC
  • No API keys or external services needed
  • Settings stored in {baseDir}/config.json

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

92.73%
按下载量换算2,879

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills