Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/garroshub/MixCut-Skillnpx agentmods add skills/garroshub/mixcut-skill/youtube-clipper-skillWrote 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/garroshub/mixcut-skill/youtube-clipper-skill)<a href="https://agentmods.dev/skills/garroshub/mixcut-skill/youtube-clipper-skill"><img src="https://agentmods.dev/badge/skills/garroshub/mixcut-skill/youtube-clipper-skill/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/garroshub/mixcut-skill/youtube-clipper-skill"><img src="https://agentmods.dev/badge/skills/garroshub/mixcut-skill/youtube-clipper-skill.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 | $0.00110 | $0.03283 |
| Opus 5 | $0.00055 | $0.01641 |
| Sonnet 5 | $0.00022 | $0.00657 |
| Haiku 4.5 | $0.00011 | $0.00328 |
Grade A, and why
youtube-clipper scanned grade A with 0 findings 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to youtube-clipper — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube 视频智能剪辑工具
Installation: If you're installing this skill from GitHub, please refer to README.md for installation instructions. The recommended method is
npx skills add https://github.com/op7418/Youtube-clipper-skill.
工作流程
你将按照以下 6 个阶段执行 YouTube 视频剪辑任务：
阶段 1: 环境检测
目标: 确保所有必需工具和依赖都已安装
-
检测 yt-dlp 是否可用
yt-dlp --version -
检测 FFmpeg 版本和 libass 支持
# 优先检查 ffmpeg-full（macOS） /opt/homebrew/opt/ffmpeg-full/bin/ffmpeg -version # 检查标准 FFmpeg ffmpeg -version # 验证 libass 支持（字幕烧录必需） ffmpeg -filters 2>&1 | grep subtitles -
检测 Python 依赖
python3 -c "import yt_dlp; print('✅ yt-dlp available')" python3 -c "import pysrt; print('✅ pysrt available')"
如果环境检测失败:
- yt-dlp 未安装: 提示
brew install yt-dlp或pip install yt-dlp - FFmpeg 无 libass: 提示安装 ffmpeg-full
brew install ffmpeg-full # macOS - Python 依赖缺失: 提示
pip install pysrt python-dotenv
注意:
- 标准 Homebrew FFmpeg 不包含 libass，无法烧录字幕
- ffmpeg-full 路径:
/opt/homebrew/opt/ffmpeg-full/bin/ffmpeg(Apple Silicon) - 必须先通过环境检测才能继续
阶段 2: 下载视频
目标: 下载 YouTube 视频和英文字幕
-
询问用户 YouTube URL
-
调用 download_video.py 脚本
cd ~/.claude/skills/youtube-clipper python3 scripts/download_video.py <youtube_url> -
脚本会：
- 下载视频（最高 1080p，mp4 格式）
- 下载英文字幕（VTT 格式，自动字幕作为备选）
- 输出文件路径和视频信息
-
向用户展示：
- 视频标题
- 视频时长
- 文件大小
- 下载路径
输出:
- 视频文件:
<id>.mp4（使用视频 ID 命名，避免特殊字符问题） - 字幕文件:
<id>.en.vtt
阶段 3: 分析章节（核心差异化功能）
目标: 使用 Claude AI 分析字幕内容，生成精细章节（2-5 分钟级别）
-
调用 analyze_subtitles.py 解析 VTT 字幕
python3 scripts/analyze_subtitles.py <subtitle_path> -
脚本会输出结构化字幕数据：
- 完整字幕文本（带时间戳）
- 总时长
- 字幕条数
-
你需要执行 AI 分析（这是最关键的步骤）：
- 阅读完整字幕内容
- 理解内容语义和主题转换点
- 识别自然的话题切换位置
- 生成 2-5 分钟粒度的章节（避免半小时粗粒度切分）
-
为每个章节生成：
- 标题: 精炼的主题概括（10-20 字）
- 时间范围: 起始和结束时间（格式: MM:SS 或 HH:MM:SS）
- 核心摘要: 1-2 句话说明这段讲了什么（50-100 字）
- 关键词: 3-5 个核心概念词
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .env.example 2.8 KB
- .github/REPOSITORY_SETTINGS.md 1.4 KB
- .gitignore 372 B
- FIXES_AND_IMPROVEMENTS.md 8.0 KB
- install_as_skill.sh 6.8 KB runs code
- LICENSE 1.0 KB
- README.md 8.4 KB
- README.zh-CN.md 7.8 KB
- references/ffmpeg-guide.md 3.4 KB
- references/subtitle-formatting.md 7.7 KB
- references/yt-dlp-guide.md 6.3 KB
- scripts/__init__.py 128 B runs code
- scripts/analyze_subtitles.py 8.2 KB runs code
- scripts/burn_subtitles.py 8.5 KB runs code
- scripts/clip_video.py 7.4 KB runs code
- scripts/download_video.py 6.6 KB runs code
- scripts/extract_subtitle_clip.py 3.6 KB runs code
- scripts/generate_summary.py 6.1 KB runs code
- scripts/merge_bilingual_subtitles.py 2.2 KB runs code
- scripts/translate_subtitles.py 6.9 KB runs code
- scripts/utils.py 8.0 KB runs code
- TECHNICAL_NOTES.md 11 KB
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.
- 11d ago First seen · 374 lines · 110 tokens per session scan A 1039e3c3ac30
youtube-clipper is a skill published in the GitHub repository garroshub/MixCut-Skill (7 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 3,283 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to youtube-clipper, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
dubbing
Dub audio and video into other languages using the ElevenLabs Dubbing API (dubbingv2), preserving the original speakers' voices. Use when translating videos, podcasts, or recordings into other languages, localizing media content, reviewing or correcting dubbing transcripts and translations, or regenerating a dub after…
iflytek-video-translate
A tool that translates a video’s speech into another language and creates dubbed audio. Video localization means adapting video content for viewers who speak a different language.
scenario-caption-studio
Use when a video needs its spoken words on screen through Scenario via MCP: burned-in styled captions for a TikTok, Reels, or Shorts cut, ad captions for sound-off feeds, YouTube subtitles, an SRT sidecar, transcription of a clip's audio, captions translated into another language, karaoke or word-by-word styles, or…
video-bilingual-subtitle-delivery
Create, repair, audit, and deliver bilingual video subtitles with English speech timing and Chinese aligned on the same subtitle event. Use when asked to add English/Chinese subtitles to a video, fix subtitle sync, fill missing Chinese lines, produce softsub or hardcode MP4 deliverables, or turn a messy subtitle…
precise-bilingual-subtitle
Produce bilingual (EN+ZH) hardcoded-subtitle videos with Whisper word-level timing accuracy, customizable font/color/size, and the full pipeline from raw YouTube video to yellow-subtitle MP4. Use when YouTube auto-captions drift, when the user wants specific subtitle styling (color, size, font), or when subtitle…
youtube-bilingual-subtitle-delivery
Download a YouTube video, convert to MP4 if needed, build bilingual English/Chinese subtitles, audit completeness, and export softsub + hardcode MP4 deliverables. Includes fallback paths when YouTube auto-captions are partial or Chinese caption download is rate-limited, and notes a hardcode duration drift fix.