← Back to Skills Marketplace
kylinr

Feishu BGM

by Rong · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
83
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install feishu-bgm
Description
飞书场景化背景音乐生成器。通过 MiniMax Music API 生成纯音乐 BGM,以音频消息发送到飞书群。 触发词:"来点BGM"、"开会背景音"、"加班音乐"、"头脑风暴BGM"、"会议音乐"、"工作BGM"、 "放点音乐"、"背景音乐"、"需要BGM"。当用户在飞书群中描述场景并希望获得背景音乐时激活。
README (SKILL.md)

飞书 BGM — 场景化背景音乐生成器

根据工作场景生成纯音乐 BGM,通过飞书音频消息即时送达群聊。

依赖:MiniMax CLI(mmx-cli)+ Token Plan


快速配置(首次使用)

1. 安装 MiniMax CLI

npm install -g mmx-cli

需要 Node.js 18+。完整文档:https://github.com/MiniMax-AI/cli

2. 订阅 Token Plan

前往 MiniMax 平台订阅 Token Plan(音乐生成需要额度):

  • 🇨🇳 国内:https://platform.minimaxi.com/subscribe/token-plan
  • 🌍 海外:https://platform.minimax.io/subscribe/token-plan

3. 登录认证

# 方式一:API Key 登录(推荐,从平台「接口密钥」页获取)
mmx auth login --api-key sk-xxxxx

# 方式二:浏览器 OAuth 登录
mmx auth login

4. 验证

# 检查登录状态
mmx auth status

# 检查剩余额度
mmx quota

# 测试生成一首 BGM
mmx music generate --prompt "calm piano, ambient" --instrumental --out /tmp/test_bgm.mp3

全部通过即可使用本 Skill。


场景预设表

用户描述模糊时,从预设匹配最近场景;描述具体时,直接用用户描述构建 prompt。

场景关键词 风格 BPM 情绪关键词
开会/会议/讨论 Ambient, Minimal 70-90 calm, professional, subtle
头脑风暴/创意 Electronic, IDM 100-120 creative, energetic, playful
加班/赶工/冲刺 Lo-fi, Chillhop 85-95 focused, determined, warm
放松/休息/午休 Bossa Nova, Jazz 90-110 relaxed, smooth, cozy café
庆祝/发布/上线 Funk, Disco 115-125 celebratory, groovy, uplifting
复盘/总结/回顾 Piano, Classical 60-80 reflective, thoughtful, gentle
面试/1on1 Acoustic, Folk 80-100 warm, comfortable, welcoming
站会/日会 Pop, Indie 110-120 light, breezy, efficient

工作流

Step 1: 解析用户意图

从用户消息中提取:

  • 场景:匹配上表或自由描述
  • 时长偏好:默认不指定(API 生成约 2 分钟)
  • 特殊要求:如"不要鼓点"、"要有钢琴"

Step 2: 构建 Prompt 并生成

优先使用 CLI(无需管理 API Key),回退到 Python 脚本:

# 方式一:MiniMax CLI(推荐)
mmx music generate \
  --prompt "\x3Cconstructed prompt>" \
  --instrumental \
  --out /tmp/openclaw/bgm_\x3Cscene>.mp3

# 方式二:Python 脚本(需要 MINIMAX_API_KEY 环境变量)
python3 scripts/generate_bgm.py \
  --prompt "\x3Cconstructed prompt>" \
  --output /tmp/openclaw/bgm_\x3Cscene>.mp3

Prompt 构建规则

\x3Cstyle>, instrumental, \x3Cmood keywords>, \x3Cinstrument hints>, \x3CBPM> BPM, 
background music for \x3Cscene description>, no vocals, professional and clean mix

示例:

Ambient, Minimal, instrumental, calm, professional, subtle, 
soft piano, warm pads, gentle strings, 80 BPM, 
background music for a team meeting, no vocals, professional and clean mix

Step 3: 发送到飞书

生成完成后,使用 message 工具发送音频文件到当前群聊:

message(action="send", filePath="/tmp/openclaw/bgm_\x3Cscene>.mp3", 
        message="🎵 \x3C场景名> BGM 已就绪")

Step 4: 响应格式

发送后回复:

🎵 BGM 已送达!
场景:\x3C场景描述>
风格:\x3C风格>
适合:\x3C使用建议>

💡 不满意可以说「换一首」或描述你想要的风格

快捷指令

用户说 动作
"换一首" / "再来一首" 同场景重新生成
"要欢快一点的" 调整情绪关键词重新生成
"不要鼓" / "加点吉他" 修改乐器提示重新生成
"停" / "够了" 结束,不再生成

生成方式

方式一:MiniMax CLI(推荐,零代码)

CLI 自动管理认证和 region,无需手动传 API Key:

mmx music generate \
  --prompt "\x3Cprompt>" \
  --instrumental \
  --out /tmp/openclaw/bgm_\x3Cscene>.mp3

方式二:Python 脚本(需要 API Key)

scripts/generate_bgm.py 直接调用 MiniMax Music API:

  • 读取 API Key:从环境变量 MINIMAX_API_KEY 获取
  • 模型:music-2.5+
  • 固定参数:is_instrumental: trueoutput_format: url
  • 音频设置:44100 Hz,256kbps,MP3
  • 超时:300 秒

错误处理

错误 处理
API 超时 告知用户生成较慢,自动重试一次
生成失败 提示用户换个描述试试
余额不足 告知用户 API 额度用完

注意事项

  • 只生成纯音乐(instrumental),避免人声歌曲作为 BGM
  • 默认不加水印(aigc_watermark: false
  • 单次生成约 2 分钟音频,适合单曲循环
  • 生成耗时约 60-120 秒,需提前告知用户等待
Usage Guidance
This skill appears to do what it says (generate BGM via MiniMax and send it to Feishu), but the registry metadata incorrectly omits the required MiniMax credential. Before installing: (1) verify you are comfortable giving an API key to the MiniMax service (api.minimaxi.com) and ensure the key has limited scope/quotas; (2) confirm how the 'message' tool sends files (that it posts only to the Feishu group and not to other endpoints); (3) inspect the mmx-cli project and the included scripts/generate_bgm.py (already bundled) to ensure no additional network endpoints or unexpected behavior; (4) ask the skill author to update the registry metadata to declare MINIMAX_API_KEY (or equivalent) so permissions are explicit. If you cannot verify those points or do not trust the MiniMax service/author, do not install or provide your API key.
Capability Tags
requires-oauth-token
Capability Assessment
Purpose & Capability
The skill's stated purpose (generate BGM for Feishu groups via MiniMax) matches the instructions and the bundled Python script. However, registry metadata reports no required environment variables or primary credential while the SKILL.md and scripts clearly require MiniMax authentication (CLI login or MINIMAX_API_KEY). That mismatch is unexpected and should be corrected by the author.
Instruction Scope
Runtime instructions are narrowly scoped to: install/use the MiniMax CLI, or call the provided Python script to request audio from MiniMax, then send the resulting MP3 to the Feishu chat via a 'message' tool. The instructions do not request unrelated system files or other external services beyond MiniMax and Feishu messaging.
Install Mechanism
There is no automated install spec; the SKILL.md instructs the user to install a public npm package (mmx-cli) and optionally run the included Python script. The npm package referenced points to a GitHub repo in the doc link; no obscure download URLs or archive extraction are used in the skill itself.
Credentials
The Python script requires a MINIMAX_API_KEY environment variable and the SKILL.md documents CLI authentication (API key or OAuth). Yet the registry metadata lists no required env vars or primary credential. The API key request is proportional to the stated purpose, but the failure to declare it in metadata is a security/process concern. Confirm where and how the API key will be stored and used, and whether the key must have limited scope/quotas.
Persistence & Privilege
The skill does not request always:true and has no install-time behavior that modifies other skills or system-wide configs. It operates on-demand and writes only its generated audio to /tmp/openclaw or other provided paths.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install feishu-bgm
  3. After installation, invoke the skill by name or use /feishu-bgm
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
Add MiniMax CLI + Token Plan quick-start setup; CLI as primary generation method
v1.0.0
Initial release: scene-based instrumental BGM generator for Feishu groups
Metadata
Slug feishu-bgm
Version 1.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Feishu BGM?

飞书场景化背景音乐生成器。通过 MiniMax Music API 生成纯音乐 BGM,以音频消息发送到飞书群。 触发词:"来点BGM"、"开会背景音"、"加班音乐"、"头脑风暴BGM"、"会议音乐"、"工作BGM"、 "放点音乐"、"背景音乐"、"需要BGM"。当用户在飞书群中描述场景并希望获得背景音乐时激活。 It is an AI Agent Skill for Claude Code / OpenClaw, with 83 downloads so far.

How do I install Feishu BGM?

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

Is Feishu BGM free?

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

Which platforms does Feishu BGM support?

Feishu BGM is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Feishu BGM?

It is built and maintained by Rong (@kylinr); the current version is v1.1.0.

💬 Comments