← Back to Skills Marketplace
utopiabenben

Ai Meeting Helper

by utopiabenben · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
261
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install ai-meeting-helper
Description
会议纪要生成器 - 自动将会议录音转为结构化纪要
README (SKILL.md)

AI Meeting Helper - 会议纪要生成器

自动将会议录音转换为结构化会议纪要,包括行动项、决策点和待办事项。

功能

  • 🎙️ 语音转文字:使用 OpenAI Whisper API 将会议录音转为文本
  • 📋 自动总结:使用 LLM 分析对话内容,生成结构化纪要
  • 提取要点:自动识别行动项、决策点、待办事项
  • 📤 多格式输出:支持 Markdown、纯文本、JSON 格式
  • 🔄 批量处理:一次处理多个会议录音文件
  • 👀 预览模式:不实际生成文件,只显示预览
  • ↩️ 撤销功能:自动备份原始文件,可撤销操作

快速开始

1. 安装技能

clawhub install ai-meeting-helper
cd ~/.openclaw/workspace/skills/ai-meeting-helper
./install.sh

2. 配置 OpenAI API

export OPENAI_API_KEY="your-api-key"

3. 使用示例

# 单个文件处理
ai-meeting-helper process meeting_recording.mp3 --output meeting_notes.md

# 批量处理文件夹
ai-meeting-helper batch ./meetings/ --output ./notes/ --format markdown

# 预览模式(不生成文件)
ai-meeting-helper process meeting.mp3 --preview

# 启用撤销功能
ai-meeting-helper process meeting.mp3 --output notes.md --backup

参数

参数 类型 必需 描述
input 路径 输入音频文件或目录
--output 路径 输出纪要文件路径(默认:当前目录)
--format 选项 输出格式:markdown/text/json(默认:markdown)
--model 字符串 Whisper 模型:tiny/base/small/medium/large(默认:base)
--llm-model 字符串 总结使用的 LLM 模型:gpt-4o/gpt-4o-mini(默认:gpt-4o-mini)
--preview 布尔 预览模式,不生成文件
--backup 布尔 启用备份(原始文件保存到 .ai_meeting_backup/)
--help 布尔 显示帮助信息

输出格式

Markdown(默认)

# 会议纪要

**日期**:2026-03-15  
**时长**:45分钟  
**参会人数**:5人

## 讨论要点

1. 讨论了Q1产品发布计划
2. 确定了市场营销策略
3. 分配了开发任务

## 行动项

- [ ] @张三:完成用户文档(3月20日前)
- [ ] @李四:设计海报素材(3月18日前)

## 决策点

- 采用A方案作为最终设计
- 预算增加10%

## 待办事项

- 下周一下午2点开会复盘

JSON

{
  "date": "2026-03-15",
  "duration": "45分钟",
  "participants": 5,
  "summary": "讨论了Q1产品发布计划...",
  "action_items": [
    {"assignee": "张三", "task": "完成用户文档", "due": "2026-03-20"}
  ],
  "decisions": ["采用A方案", "预算增加10%"],
  "todo": ["下周一下午2点开会复盘"]
}

技术栈

  • 语音识别:openai-whisper-api(需 OPENAI_API_KEY)
  • 文本处理:Python 标准库 + 正则
  • LLM 总结:OpenAI GPT-4o-mini(默认)或 GPT-4o
  • 文件处理:glob, json, pathlib

依赖

pip install openai python-dotenv

注意事项

  • 需要有效的 OpenAI API key
  • 音频文件支持:MP3, WAV, M4A, FLAC, OGG
  • 较大文件处理时间较长(建议 \x3C 30 分钟音频)
  • 建议使用高质量录音以提高识别准确率

与其他技能配合

  • audio-note-taker:类似功能,但 ai-meeting-helper 专为会议场景优化,输出更结构化
  • wechat-formatter:生成的纪要可直接排版发布到公众号
  • social-publisher:纪要内容可一键分发到多平台

License

MIT

Usage Guidance
What to consider before installing: - Metadata mismatch: the skill.json and SKILL.md require OPENAI_API_KEY, but the top-level registry metadata claimed no required env vars. Treat that inconsistency as a red flag — confirm which metadata is authoritative before trusting automated installers. - Review code yourself (you have the files): the Python script uses only the OpenAI client and local file I/O; no hard-coded external endpoints or obfuscated code were found. If you don't review, install only in an isolated environment. - Install in a virtual environment or sandbox rather than system-wide (the install.sh runs pip3 install without a venv). This avoids contaminating global Python packages. - Backups: the tool will copy original audio into .ai_meeting_backup/. Those files can contain sensitive conversations — ensure you control that directory, or disable backup if not needed, and securely delete backups when appropriate. - API key scope and monitoring: provide an OpenAI key with appropriate usage controls; monitor usage and billing. If possible use an account with limited permissions or monitoring alerts. - Trust and provenance: owner is unknown and there's no homepage. If you need high assurance, request more provenance or prefer a skill from a known source. If you decide to proceed: run install.sh only after inspecting it, execute the tool inside a dedicated virtualenv or container, and consider auditing network traffic or logs during first runs. If you need help verifying specific lines of code or testing in a sandbox, provide the environment and I can help step through it.
Capability Analysis
Type: OpenClaw Skill Name: ai-meeting-helper Version: 1.0.0 The ai-meeting-helper skill is a legitimate utility designed to transcribe and summarize audio recordings using the OpenAI API. The code in source/meeting_helper.py and the installation scripts (install.sh) perform standard operations such as environment variable management via .env files, local file backups, and structured API calls without any evidence of malicious intent, data exfiltration, or suspicious execution patterns.
Capability Assessment
Purpose & Capability
The code, SKILL.md, and skill.json all implement a meeting-transcription-and-summary tool that uses OpenAI Whisper and an LLM — requesting an OPENAI_API_KEY is coherent with that purpose. However, the top-level registry metadata provided to you (which claimed no required env vars / no primary credential) contradicts the included skill.json and SKILL.md that require OPENAI_API_KEY. The mismatch is unexpected and should be resolved before trusting the package metadata.
Instruction Scope
Runtime instructions and the Python code stay within the declared purpose: they read local audio files, call OpenAI APIs for transcription and summarization, format results, optionally backup original audio to a local .ai_meeting_backup/ directory, and write outputs. The instructions do not reference unrelated system paths, other credentials, or external endpoints beyond the OpenAI client.
Install Mechanism
Installation is a local install.sh that runs pip3 install openai python-dotenv (no virtualenv) and creates a .env template and backup/log directories in the skill folder. This uses a public PyPI package (openai) — not high risk by itself — but the script installs packages system-wide (no venv) which may be undesirable. No downloads from arbitrary URLs or obfuscated installers were found.
Credentials
The code requires a single credential (OPENAI_API_KEY), which is proportionate to the stated functionality. However, the provided registry metadata (at the top of this report) claims no required env vars/primary credential while skill.json and SKILL.md declare OPENAI_API_KEY required — that inconsistency is suspicious and could indicate sloppy packaging or metadata manipulation.
Persistence & Privilege
The skill does not request 'always: true' or elevated agent privileges. It creates and writes files only within its own skill directory (.env, .ai_meeting_backup/, .ai_meeting_logs/) and does not modify other skills or global agent config. Uninstall.sh offers to remove these files.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ai-meeting-helper
  3. After installation, invoke the skill by name or use /ai-meeting-helper
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
AI Meeting Helper 1.0.0 初始版本发布 - 自动将会议录音转换为结构化会议纪要,包括行动项、决策点和待办事项 - 支持语音转文字(基于 OpenAI Whisper API)和 LLM 自动总结 - 多格式导出:Markdown、纯文本、JSON - 提供批量处理、预览与撤销功能 - 命令行参数灵活,便于集成和扩展 - 兼容多种主流音频格式,依赖简洁易安装
Metadata
Slug ai-meeting-helper
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Ai Meeting Helper?

会议纪要生成器 - 自动将会议录音转为结构化纪要. It is an AI Agent Skill for Claude Code / OpenClaw, with 261 downloads so far.

How do I install Ai Meeting Helper?

Run "/install ai-meeting-helper" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ai Meeting Helper free?

Yes, Ai Meeting Helper is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Ai Meeting Helper support?

Ai Meeting Helper is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ai Meeting Helper?

It is built and maintained by utopiabenben (@utopiabenben); the current version is v1.0.0.

💬 Comments