Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add L-LesterYu/OpenClaw-hot-skills-zh --skill youtube-watcher-zhgit clone --depth 1 https://github.com/L-LesterYu/OpenClaw-hot-skills-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/youtube-watcher-zh)<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/youtube-watcher-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/youtube-watcher-zh/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/youtube-watcher-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/youtube-watcher-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01711 |
| Opus 5 | $0.00016 | $0.00856 |
| Sonnet 5 | $0.00007 | $0.00342 |
| Haiku 4.5 | $0.00003 | $0.00171 |
Grade B, and why
youtube-watcher-zh scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install yt-dlp How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube 字幕提取器
通过 yt-dlp 提取 YouTube 视频字幕并进行内容分析
🎯 功能特性
- 📝 字幕提取 - 从 YouTube 视频中提取带时间戳的字幕
- 🎬 内容分析 - 基于字幕进行视频内容摘要
- ❓ 问答支持 - 根据字幕内容回答问题
- 🔍 内容搜索 - 在字幕内容中搜索特定信息
- 📊 统计分析 - 分析字幕的词汇、主题等统计信息
🚀 快速开始
1. 安装依赖
确保安装了 yt-dlp：
# Ubuntu/Debian
sudo apt install yt-dlp
# macOS (使用 Homebrew)
brew install yt-dlp
# 或通过 pip 安装
pip install yt-dlp
2. 基本使用
提取视频字幕：
# 提取单个视频字幕
yt-dlp --write-subs --sub-format "srt" "https://www.youtube.com/watch?v=VIDEO_ID"
📝 使用方法
提取字幕
# 提取字幕并保存为 SRT 格式
yt-dlp --write-subs --sub-format "srt" --sub-lang "en,zh" "YOUTUBE_URL"
# 提取字幕并包含自动生成的字幕
yt-dlp --write-subs --sub-format "srt" --sub-lang "en,zh,en-auto" "YOUTUBE_URL"
字幕格式支持
- SRT - 标准字幕格式
- VTT - WebVTT 字幕格式
- ASS/SSA - 高级字幕格式
- JSON - 原始 JSON 数据
🔍 内容分析
视频摘要
基于字幕内容生成视频摘要：
# 提取关键字和主题
# 通过文本分析工具处理字幕内容
内容问答
根据字幕内容回答问题：
# 示例问题
"这个视频主要讲了什么？"
"视频中提到了哪些关键概念？"
"视频的主要内容分为哪几个部分？"
内容搜索
在字幕中搜索特定内容：
# 搜索关键词
grep "关键词" video.srt
# 使用文本搜索工具
find "搜索词" in video.srt
⚙️ 配置选项
yt-dlp 参数
| 参数 | 描述 |
|---|---|
--write-subs |
写入字幕文件 |
--sub-format "srt" |
字幕格式 |
--sub-lang "en,zh" |
字幕语言 |
--sub-lang "en-auto" |
自动生成的英文字幕 |
--no-playlist |
不提取播放列表 |
--no-mtime |
不修改文件时间戳 |
输出格式
# 输出文件命名规则
视频标题.语言.srt
视频标题.语言.vtt
视频标题.语言.json
📊 字幕处理
字幕清理
- 去除重复条目
- 时间戳标准化
- 文本格式化
- 语言检测
内容分析
- 词汇统计 - 计算词频、关键词
- 主题提取 - 识别主要讨论话题
- 情感分析 - 分析内容的情感倾向
- 结构分析 - 识别内容结构和逻辑
🎬 实际应用
1. 视频研究
# 提取教育视频的主要观点
# 分析演讲者的主要论点
# 识别技术视频的关键步骤
2. 内容创作
# 基于字幕创建文章摘要
# 生成视频内容的文字版本
# 创建视频内容的索引目录
3. 学习辅助
# 将视频内容转换为文字笔记
# 创建视频内容的问答集
# 生成视频内容的思维导图
📁 文件管理
存储结构
workspace/
├── videos/
│ ├── [视频ID]/
│ │ ├── video.srt # 字幕文件
│ │ ├── video.vtt # WebVTT 格式
│ │ ├── video.json # 原始数据
│ │ └── summary.txt # 内容摘要
└── processed/
├── transcripts/ # 处理后的字幕
├── summaries/ # 视频摘要
└── analysis/ # 内容分析
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 276 lines · 33 tokens per session scan B 12565c76196a
youtube-watcher-zh is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (54 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 1,711 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
youtube-transcribe
A tool that downloads YouTube videos or subtitles, turns speech into text, and can translate English into Chinese in a bilingual Markdown file.
youtube-summarizer
Automatically fetch YouTube video transcripts, generate structured summaries, and send full transcripts to messaging platforms. Detects YouTube URLs and provides metadata, key insights, and downloadable transcripts.
youtube-summarizer
Automatically fetch YouTube video transcripts, generate structured summaries, and send full transcripts to messaging platforms. Detects YouTube URLs and provides metadata, key insights, and downloadable transcripts.
youtube-transcribe
Transcribe YouTube videos and playlists. Extract audio to text with visual context, generate summaries and detailed notes.
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.
tiktok-transcribe
A workflow that downloads TikTok videos, turns their audio into text with speech-recognition software, and saves the result as a Markdown file.