Automate the full QuarkPanTool → mswnlz GitHub content publishing pipeline. Use when the user provides Quark share URLs and wants: (1) create a batch folder in Quark Drive, (2) save/copy resources into that folder, (3) copy promotional files INTO each shared resource folder, (4) generate permanent encrypted share links with random passcodes, (5) auto-classify items into mswnlz repos (book/movies/etc.) by repo descriptions, (6) append/update the target repo's YYYYMM.md and README month index, (7) git commit+push, (8) send unified Telegram notifications, and (9) force-trigger mswnlz.github.io site rebuild and return the final site URLs.
Track YouTube channels for new uploads. Supports both RSS mode (no API key needed, unlimited quota) and API mode. Use when: add/remove/list tracked YouTube channels, check for new videos, or run scheduled YouTube channel monitoring.
文本转语音工具 - 支持 Edge TTS 和 Kokoro TTS (v1.1-zh) 双引擎，102 个中文音色
Convert YouTube videos to SEO-optimized blog posts. Extract video title, description, and content, then generate a search-engine-friendly blog post with embedded video, cover images, optimized metadata, structured Markdown sections, clean resource blocks, and canonical 5-8 keywords. Auto-generates English filenames and saves to the configured Hexo blog posts directory. Includes tag management rules to maintain a clean, consistent tag taxonomy.
视频变声处理工具 - 从视频提取音频，调用 voice-changer skill 变声后合并回视频。用户要求视频变声、给视频换声音、视频音色转换或处理视频音频时使用。
Upload and publish videos to YouTube with title, description, tags, thumbnail and subtitles. Use for: youtube upload, publish video, share on youtube.
| name | voice-changer |
| description | 音频变声处理工具 - 使用 RVC AI 模型进行真实的声音转换，支持视频直接输入 |
| version | 1.6.0 |
| author | M. |
voice-changer 是一个音频/视频变声处理 skill，支持直接处理视频文件或音频文件进行变声处理。
优点:
原理: 使用 HuBERT 特征提取 + RVC 模型推理：
适用场景:
voice-changer/
├── SKILL.md # 本文档
├── README.md # 使用说明
├── scripts/
│ └── voice_change.py # 核心变声脚本
├── config/
│ └── voice_config.json # 声音配置文件
└── models/ # RVC 模型目录
├── rvc_env_310/ # Python 3.10 环境
├── rvc_core/ # RVC 核心代码
└── rvc_models/ # RVC 模型文件
{
"method": "rvc",
"rvc_model_path": "models/rvc_models/trained_models/kohane.pth",
"default_voice": "female_3",
"voices": {
"female_3": {
"name": "女声（甜美）",
"method": "rvc",
"model_path": "...kohane.pth",
"index_path": "...kohane.index",
"f0up_key": -1,
"f0_method": "harvest"
}
}
}
method: 处理方法（rvc 或 pedalboard）f0up_key: 音高调整（半音）
f0_method: F0 提取方法（harvest、crepe、pm 等）# 基本用法（使用默认女声）
python3 ~/.claude/skills/voice-changer/scripts/voice_change.py input.mp3
# 直接处理视频文件（自动提取音频→变声→合成视频）
python3 ~/.claude/skills/voice-changer/scripts/voice_change.py input.mp4 -o output.mp4
# 指定声音类型
python3 ~/.claude/skills/voice-changer/scripts/voice_change.py input.mp3 -v female_2
# 指定输出文件
python3 ~/.claude/skills/voice-changer/scripts/voice_change.py input.mp3 -o output.mp3
# 自定义音高
python3 ~/.claude/skills/voice-changer/scripts/voice_change.py input.mp3 -p 7
# 查看帮助
python3 ~/.claude/skills/voice-changer/scripts/voice_change.py --help
处理视频时会自动：
import subprocess
def change_voice(input_audio, voice_type='female_1'):
"""调用 voice-changer skill"""
script_path = os.path.expanduser(
'~/.claude/skills/voice-changer/scripts/voice_change.py'
)
output_audio = input_audio.replace('.mp3', '_voice_changed.mp3')
cmd = [
'python3', script_path,
input_audio,
'-v', voice_type,
'-o', output_audio
]
result = subprocess.run(cmd, capture_output=True, text=True)
if result.returncode == 0:
return output_audio
else:
print(f"变声失败: {result.stderr}")
return input_audio
| 预设名称 | 音高 | 描述 | 适用场景 |
|---|---|---|---|
| female_1 | 0 | 女声（轻柔） | 基础女声 |
| female_2 | +2 | 女声（明亮） | 更高的女声 |
| female_3 | -1 | 女声（甜美）⭐ | 默认，自然女声 |
| child | +8 | 童声 | 儿童效果 |
| rvc_female | +4 | AI 女声（高音高） | 高质量女声 |
| rvc_male | -12 | AI 男声（低音高） | 高质量男声 |
| male_normal | -8 | 男声（正常） | 自然男声 |
| male_deep | -12 | 男声（低沉） | 低沉男声 |
# 先过滤关键字，再变声
python3 ~/.claude/skills/audiocut-keyword/scripts/audiocut_keyword.py input.mp3 --change-voice female_1
# YouTube 下载 + 过滤 + 变声 + 发布
python3 ~/.claude/skills/youtube-to-xiaoyuzhou/youtube_to_xiaoyuzhou.py \
https://youtu.be/xxxxx \
--filter-keywords \
--change-voice female_1 \
--schedule "2026-01-20 18:00"
# macOS
brew install ffmpeg
# Ubuntu/Debian
sudo apt-get install ffmpeg