Token导航 LogoToken导航

Agent Skill · 开发

meetingos(meetingos 开发)

meetingos 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。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。

meetingos 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 5,784。

总安装 5,691周安装 228GitHub Stars 公开资料未说明下载 1,842核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.9

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:meetingos(meetingos 开发)
来源仓库:https://github.com/dttnpole-commits/meetingos
安装命令:
openclaw skills install meetingos
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 meetingos

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

meetingos 自动循环处理会议记录、摘要与行动项执行。在提及会议相关内容时自动触发全流程管理。适合持续跟踪会议成果与任务进度的场景。meetingos 属于开发类 Skill,可作为该场景下的辅助能力补充。安装命令:openclaw skills install meetingos。

需确认任务状态存储方式与提醒机制实现。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install meetingos;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

meetingos 怎么安装?

在终端执行 openclaw skills install meetingos。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

meetingos 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

meetingos 需要什么权限?

权限级别是接触敏感数据。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。

meetingos 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

meetingos 用的人多吗?

公开数据是累计安装 5,691 次,近一周安装 228 次,下载 1,842 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

meetingos 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
meetingos

meetingos 开发 · 本页

5,691—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
meeting-os
description
Auto meeting notes and action item execution loop. Trigger this skill whenever the user mentions meeting notes, meeting summary, action items, follow-up, transcript, recording, Zoom summary, Teams meeting, Tencent Meeting, Feishu meeting, WeCom meeting, upload audio, upload video, meeting template, task creation.
license
MIT
user-invocable
true
argument-hint
Free: 10 meetings/month. Pro billing via SkillPay: skillpay.me

MeetingOS

Auto meeting notes and action item execution loop.

Required Environment Variables

This skill uses the following environment variables. You must set them yourself in a local .env file. Never upload your .env file to any website.

The following variables control basic behavior and have safe defaults:

  • MEETINGOS_PRIVACY_MODE: Set to local or cloud. Default is local. Local mode keeps all data on your computer.
  • WHISPER_LOCAL_MODEL: Set to base or medium or large-v3. Default is base.
  • MEETINGOS_DOWNLOAD_DIR: Folder for temporary recording files. Default is /tmp/meetingos.
  • MEETINGOS_MAX_FILE_MB: Maximum file size in MB. Default is 2048.

The following variables are needed only if you use Feishu integration:

  • FEISHU_APP_ID: Your Feishu App ID. Get from open.feishu.cn
  • FEISHU_APP_SECRET: Your Feishu App Secret. Get from open.feishu.cn
  • FEISHU_CHAT_ID: Your Feishu group chat ID. Get from Feishu group settings.
  • FEISHU_WEBHOOK_URL: Your Feishu robot Webhook URL. Get from Feishu group robot settings.
  • FEISHU_BITABLE_TOKEN: Your Feishu Bitable App Token. Get from the Bitable URL.
  • FEISHU_BITABLE_TABLE: Your Feishu Bitable Table ID. Get from the Bitable URL.

The following variables are needed only if you use WeCom integration:

  • WECOM_CORP_ID: Your WeCom Corp ID. Get from WeCom admin panel.
  • WECOM_AGENT_ID: Your WeCom Agent ID. Get from WeCom admin panel.
  • WECOM_AGENT_SECRET: Your WeCom Agent Secret. Get from WeCom admin panel.
  • WECOM_WEBHOOK_URL: Your WeCom robot Webhook URL. Get from WeCom group robot settings.

The following variables are needed only if you use Notion integration:

  • NOTION_API_KEY: Your Notion Integration Token. Get from notion.so/my-integrations
  • NOTION_DATABASE_ID: Your Notion Database ID. Get from the Notion database page URL.

The following variable is needed only if you want cloud transcription:

  • OPENAI_API_KEY: Your OpenAI API Key. Get from platform.openai.com/api-keys. Not needed if you use local mode.

The following variables are needed only if you use SkillPay billing:

  • SKILLPAY_API_KEY: Your SkillPay API Key. Get from skillpay.me/dashboard
  • SKILLPAY_SKILL_ID: Your SkillPay Skill ID. Get from skillpay.me/dashboard/skills

Installation

Install Python packages:

pip install -r requirements.txt

Install ffmpeg for audio processing:

  • Windows: download from ffmpeg.org then restart your computer
  • Mac: run brew install ffmpeg
  • Linux: run sudo apt install ffmpeg

When to Use

  • Help me organize this meeting
  • Extract action items from this transcript
  • Push action items to Notion or Feishu or WeCom
  • Generate meeting notes from this recording
  • Follow up on last meeting action items
  • Send summary to Feishu group
  • Batch process multiple meeting recordings

Privacy

When MEETINGOS_PRIVACY_MODE is set to local, audio stays on your computer. No data is sent anywhere. This is the default.

When set to cloud, audio is sent to OpenAI. Only use this if you are comfortable with that.

Security

  • All API keys must be stored in your own .env file
  • Never upload your .env file to any website
  • Never paste real key values into code or documentation files
  • Only configure the services you actually plan to use
  • Temporary recording files are deleted automatically after processing

File Structure

meeting-os/
├── SKILL.md
├── requirements.txt
├── scripts/
│   ├── transcribe.py
│   ├── push_notion.py
│   ├── feishu_helper.py
│   ├── wecom_helper.py
│   ├── meeting_fetcher.py
│   ├── skillpay_guard.py
│   └── main_processor.py
└── templates/
    ├── default.md
    └── sales_debrief.md

---

## 第二件事:在 GitHub 提交人工审核申请

因为我们已经修了很多版本,这次修完后同时提交人工审核,让 ClawHub 团队确认。

**操作:**
1. 在技能页面点击黄色警告框里的 **「在 GitHub 上提交交问题」** 链接
2. 跳转到 GitHub 后点击 **「New Issue」**
3. 标题填:

MeetingOS skill flagged as suspicious - all issues fixed, requesting manual review


4. 内容填:

Hello,

I have fixed all flagged issues in version 1.0.6. Here is what was fixed:

  1. Removed all real API key values from all files
  2. Added complete environment variable documentation to SKILL.md
  3. All environment variables used in code are now declared in SKILL.md
  4. Added requirements.txt with all Python dependencies
  5. All test code is inside if __name__ == "__main__" blocks
  6. No .env file is included in the upload

The skill is a meeting notes automation tool that:

  • Transcribes audio using local Whisper (no data sent anywhere by default)
  • Extracts action items from transcripts
  • Optionally pushes to Feishu, WeCom, Notion (only if user configures their own keys)
  • Optionally uses SkillPay billing (only if user configures their own keys)

All external service calls are optional and require the user to provide their own credentials.

Please review and remove the suspicious flag.

Account: DTTNpole-commits Skill: meetingos

Thank you.

平台分布

OpenClaw

90.84%
按下载量换算1,673

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills