Use Avibe
avibe-bot/avibe
Safely inspect and modify local Avibe configuration, routing, runtime settings, watches, scheduled tasks, Avibe Cloud remote access, and operational state.
Creates, lists and cancels one-time and recurring reminders for a QQ bot by calling its reminder and cron tools instead of promising in text.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add tencent-connect/openclaw-qqbot --skill qqbot-remind -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tencent-connect/openclaw-qqbot qqbot-remind --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tencent-connect/openclaw-qqbot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/qqbot-remind .claude/skills/qqbot-remind && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "qqbot-remind" agent skill from https://github.com/tencent-connect/openclaw-qqbot/tree/main/skills/qqbot-remind into .claude/skills/qqbot-remind/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qqbot-remind", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tencent-connect/openclaw-qqbot/tree/main/skills/qqbot-remindType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tencent-connect/openclaw-qqbot --skill qqbot-remind -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tencent-connect/openclaw-qqbot qqbot-remind --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tencent-connect/openclaw-qqbot.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/qqbot-remind .agents/skills/qqbot-remind && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "qqbot-remind" agent skill from https://github.com/tencent-connect/openclaw-qqbot/tree/main/skills/qqbot-remind into .agents/skills/qqbot-remind/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qqbot-remind", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tencent-connect/openclaw-qqbot --skill qqbot-remind -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tencent-connect/openclaw-qqbot qqbot-remind --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tencent-connect/openclaw-qqbot.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/qqbot-remind .cursor/skills/qqbot-remind && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "qqbot-remind" agent skill from https://github.com/tencent-connect/openclaw-qqbot/tree/main/skills/qqbot-remind into .cursor/skills/qqbot-remind/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qqbot-remind", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tencent-connect/openclaw-qqbot.git --path skills/qqbot-remind--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tencent-connect/openclaw-qqbot --skill qqbot-remind -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tencent-connect/openclaw-qqbot qqbot-remind --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tencent-connect/openclaw-qqbot.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/qqbot-remind .gemini/skills/qqbot-remind && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "qqbot-remind" agent skill from https://github.com/tencent-connect/openclaw-qqbot/tree/main/skills/qqbot-remind into .gemini/skills/qqbot-remind/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qqbot-remind", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tencent-connect/openclaw-qqbot qqbot-remindInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tencent-connect/openclaw-qqbot --skill qqbot-remind -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tencent-connect/openclaw-qqbot.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/qqbot-remind .github/skills/qqbot-remind && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "qqbot-remind" agent skill from https://github.com/tencent-connect/openclaw-qqbot/tree/main/skills/qqbot-remind into .github/skills/qqbot-remind/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qqbot-remind", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tencent-connect/openclaw-qqbot --skill qqbot-remind -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tencent-connect/openclaw-qqbot qqbot-remind --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tencent-connect/openclaw-qqbot.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/qqbot-remind .opencode/skills/qqbot-remind && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "qqbot-remind" agent skill from https://github.com/tencent-connect/openclaw-qqbot/tree/main/skills/qqbot-remind into .opencode/skills/qqbot-remind/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qqbot-remind", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
qqbot-remindCreates, lists and cancels one-time and recurring reminders for a QQ bot by calling its reminder and cron tools instead of promising in text.
This skill handles QQ bot reminders: creating one-time and recurring reminders, listing them and cancelling them. Its main rule is that any request involving a reminder, alarm or delay must trigger a tool call, because an agent that only replies that it will remind you has registered nothing. The skill file is in Chinese.
The preferred flow calls a qqbot_remind tool with an action, content and a time given as a relative value such as five minutes or as a cron expression. The tool returns parameters that must be passed unchanged to the cron tool, and the agent then confirms to the user. A fallback uses the cron tool directly with fixed fields that route the message through the QQ channel, absolute millisecond timestamps for one-time jobs and an Asia/Shanghai time zone for recurring ones. A cron cheat sheet and a decision table cover common phrasings, and the agent asks when the time is missing.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit b9ba494. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
QQ Bot Reminders loads about 958 tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 215 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from tencent-connect/openclaw-qqbot at commit b9ba494, republished under its MIT licence (© tencent-connect). 215 words, ~958 tokens.
.claude/skills/qqbot-remind/SKILL.md (or your agent's skills folder).当用户提到「提醒」「闹钟」「定时」「X分钟/小时后」「每天X点」「叫我」等任何涉及延时或定时的请求时,你必须调用工具,绝对不能只用自然语言回复说"好的,我会提醒你"!
你没有内存或后台线程,口头承诺"到时候提醒"是无效的——只有调用工具才能真正注册定时任务。
qqbot_remind 工具)第一步:调用 qqbot_remind 工具,传入简单参数:
| 参数 | 说明 | 示例 |
|---|---|---|
action | 操作类型 | "add" / "list" / "remove" |
content | 提醒内容 | "喝水" |
to | 目标地址(可选,系统自动获取,通常无需填写) | — |
time | 时间(相对时间或 cron 表达式) | "5m" / "1h30m" / "0 8 * * *" |
jobId | 任务 ID(仅 remove) | "xxx" |
第二步:qqbot_remind 会返回 cronParams,你必须立即将 cronParams 的值原样作为参数调用 cron 工具。禁止修改、省略或重组 cronParams 中的任何字段(尤其是 delivery 对象中的 accountId)。
第三步:根据 cron 工具的返回结果,回复用户。
用户说:"5分钟后提醒我喝水"
qqbot_remind:{ "action": "add", "content": "喝水", "time": "5m" }cronParams → 立即调用 cron 工具,参数为该 cronParams⏰ 好的,5分钟后提醒你喝水~cron 工具)仅当
qqbot_remind工具不可用时使用以下方式。
payload.kind 必须是
"agentTurn",绝对不能用"systemEvent"!systemEvent只在 AI 会话内部注入文本,用户收不到 QQ 消息。
5 个不可更改字段:
| 字段 | 固定值 | 原因 |
|---|---|---|
payload.kind | "agentTurn" | systemEvent 不会发 QQ 消息 |
delivery.mode | "announce" | 投递模式 |
delivery.channel | "qqbot" | QQ 通道标识 |
delivery.to | 用户 openid | 从 To 字段获取 |
sessionTarget | "isolated" | 隔离会话避免污染 |
delivery.accountId必须填写当前会话的账户 ID(如果已知),以确保多账户场景下消息通过正确的机器人账户发送。
schedule.atMs必须是绝对毫秒时间戳(如1770733800000),不支持"5m"等相对字符串。 计算方式:当前时间戳ms + 延迟毫秒。
{
"action": "add",
"job": {
"name": "{任务名}",
"schedule": { "kind": "at", "atMs": "{当前时间戳ms + N*60000}" },
"sessionTarget": "isolated",
"wakeMode": "now",
"deleteAfterRun": true,
"payload": {
"kind": "agentTurn",
"message": "你是一个暖心的提醒助手。请用温暖、有趣的方式提醒用户:{提醒内容}。要求:(1) 不要回复HEARTBEAT_OK (2) 不要解释你是谁 (3) 直接输出一条暖心的提醒消息 (4) 可以加一句简短的鸡汤或关怀的话 (5) 控制在2-3句话以内 (6) 用emoji点缀"
},
"delivery": {
"mode": "announce",
"channel": "qqbot",
"to": "{openid}",
"accountId": "{accountId}"
}
}
}{
"action": "add",
"job": {
"name": "{任务名}",
"schedule": { "kind": "cron", "expr": "0 8 * * *", "tz": "Asia/Shanghai" },
"sessionTarget": "isolated",
"wakeMode": "now",
"payload": {
"kind": "agentTurn",
"message": "你是一个暖心的提醒助手。请用温暖、有趣的方式提醒用户:{提醒内容}。要求:(1) 不要回复HEARTBEAT_OK (2) 不要解释你是谁 (3) 直接输出一条暖心的提醒消息 (4) 可以加一句简短的鸡汤或关怀的话 (5) 控制在2-3句话以内 (6) 用emoji点缀"
},
"delivery": {
"mode": "announce",
"channel": "qqbot",
"to": "{openid}",
"accountId": "{accountId}"
}
}
}周期任务不加
deleteAfterRun。群聊to格式为"qqbot:group:{group_openid}"。
| 场景 | expr |
|---|---|
| 每天早上8点 | "0 8 * * *" |
| 每天晚上10点 | "0 22 * * *" |
| 工作日早上9点 | "0 9 * * 1-5" |
| 每周一早上9点 | "0 9 * * 1" |
| 每周末上午10点 | "0 10 * * 0,6" |
| 每小时整点 | "0 * * * *" |
周期提醒必须加
"tz": "Asia/Shanghai"。
| 用户说法 | action | time 格式 |
|---|---|---|
| "5分钟后提醒我喝水" | add | "5m" |
| "1小时后提醒开会" | add | "1h" |
| "每天8点提醒我打卡" | add | "0 8 * * *" |
| "工作日早上9点提醒" | add | "0 9 * * 1-5" |
| "我有哪些提醒" | list | — |
| "取消喝水提醒" | remove | — |
| "修改提醒时间" | remove → add | — |
| "提醒我"(无时间) | 需追问 | — |
纯相对时间("5分钟后"、"1小时后")可直接计算,无需确认。时间模糊或缺失时需追问。
⏰ 好的,{时间}后提醒你{内容}~⏰ 收到,{周期}提醒你{内容}~📋 目前没有提醒哦~ 说"5分钟后提醒我xxx"试试?✅ 已取消"{名称}"openclaw cron add \ --name "下班提醒" \ --at "2026-03-26T21:42:31+08:00" \ --message "test" \ --to …``
© tencent-connect, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/qqbot-remind of tencent-connect/openclaw-qqbot.
Open the folder on GitHubat commit b9ba494
QQ Bot Reminders next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| QQ Bot Reminders this skilltencent-connect/openclaw-qqbot | 1.6k | — | ~958 | Automated safety check: Pass | MIT | |
| Use Avibeavibe-bot/avibe | 622 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Twitter Monitorkangarooking/kangarooking-skills | 662 | — | ~798 | Automated safety check: Pass | None | |
| Task Manager0xranx/golembot | 322 | — | ~694 | Automated safety check: Pass | MIT | |
| Slack Channel MonitorOpenHands/extensions | 163 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Feishu Cron Reminderzrt-ai-lab/opencode-skills | 287 | — | ~562 | Automated safety check: Pass | None |
avibe-bot/avibe
Safely inspect and modify local Avibe configuration, routing, runtime settings, watches, scheduled tasks, Avibe Cloud remote access, and operational state.
kangarooking/kangarooking-skills
Fetch recent posts from one or more X/Twitter accounts through twitterapi.io, output structured JSON/CSV records, optionally sync records to Feishu/Lark Bitable through feishu-cli, and optionally…
0xranx/golembot
Creates and manages scheduled tasks, cron jobs, recurring reminders, and timers via the Task HTTP API.
OpenHands/extensions
This skill should be used when the user asks to "monitor a Slack channel", "watch Slack for messages", "create a Slack bot that responds to mentions", "set up an OpenHands Slack integration"…
zrt-ai-lab/opencode-skills
Create cron jobs that reliably deliver reminders to Feishu (飞书) chats.
TencentCloudBase/CloudBase-AI-Toolkit
Fast path for a minimal CloudBase Web + database demo (最小前后端 / 最小可用 fullstack / Lovable-like BaaS).
tencent-connect/openclaw-qqbot
Manages QQ guilds and their sub-channels, members, posts, announcements and schedules through the qqbot_platform_api tool.
Categories
Creates, lists and cancels one-time and recurring reminders for a QQ bot by calling its reminder and cron tools instead of promising in text. This skill handles QQ bot reminders: creating one-time and recurring reminders, listing them and cancelling them. Its main rule is that any request involving a reminder, alarm or delay must trigger a tool call, because an agent that only replies that it will remind you has registered nothing.
QQ Bot Reminders fits situations like: setting a reminder that fires in a few minutes or hours; creating a daily or weekday recurring reminder over QQ; listing the reminders already scheduled; cancelling or changing an existing reminder.
Run `npx skills add tencent-connect/openclaw-qqbot --skill qqbot-remind -a claude-code`. Or copy the skill folder (skills/qqbot-remind in tencent-connect/openclaw-qqbot) into .claude/skills/qqbot-remind in your project. Claude Code loads it when a task matches its description.
Run `npx skills add tencent-connect/openclaw-qqbot --skill qqbot-remind -a codex`. Or copy the skill folder (skills/qqbot-remind in tencent-connect/openclaw-qqbot) into .agents/skills/qqbot-remind in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tencent-connect/openclaw-qqbot --skill qqbot-remind -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qqbot-remind, .gemini/skills/qqbot-remind, .github/skills/qqbot-remind and .opencode/skills/qqbot-remind in your project.
SKILL.md names no scripts, command-line tools or credentials: QQ Bot Reminders is instructions for the agent only. Our summary lists: A QQ bot channel with the qqbot_remind and cron tools available.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
QQ Bot Reminders is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 958 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with QQ Bot Reminders: Use Avibe (avibe-bot/avibe, 622 stars), Twitter Monitor (kangarooking/kangarooking-skills, 662 stars), Task Manager (0xranx/golembot, 322 stars) and Slack Channel Monitor (OpenHands/extensions, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
tencent-connect (a GitHub organization) maintains it in tencent-connect/openclaw-qqbot, which has 1,555 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.
Source: tencent-connect/openclaw-qqbot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.