youtube-clipper
YouTube 视频智能剪辑工具。下载视频和字幕,AI 分析生成精细章节(几分钟级别), 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频,并生成总结文案。 使用场景:当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。…
Skill by op7418
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/op7418-youtube-clipper
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/youtube-clipper
What's inside
- Skill name
youtube-clipper- Description
- YouTube 视频智能剪辑工具。下载视频和字幕,AI 分析生成精细章节(几分钟级别), 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频,并生成总结文案。 使用场景:当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词:视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video
- License
- MIT
- Instructions
- 359 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- name: "youtube-clipper" does not match folder "Youtube-clipper-skill"
- allowed-tools: must be a space-separated string
Files (24)
- .env.example
- REPOSITORY_SETTINGS.md · .github/
- .gitignore
- FIXES_AND_IMPROVEMENTS.md
- LICENSE
- README.md
- README.zh-CN.md
- SKILL.md
- TECHNICAL_NOTES.md
- install_as_skill.sh
- ffmpeg-guide.md · references/
- subtitle-formatting.md · references/
- yt-dlp-guide.md · references/
- __init__.py · scripts/
- analyze_subtitles.py · scripts/
- burn_subtitles.py · scripts/
- clip_video.py · scripts/
- download_video.py · scripts/
- extract_subtitle_clip.py · scripts/
- generate_summary.py · scripts/
- merge_bilingual_subtitles.py · scripts/
- translate_subtitles.py · scripts/
- utils.py · scripts/
- summary-template.md · templates/
SKILL.md (first lines)
# YouTube 视频智能剪辑工具
> **Installation**: If you're installing this skill from GitHub, please refer to [README.md](README.md#installation) 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
1. 检测 yt-dlp 是否可用
```bash
yt-dlp --version
```
2. 检测 FFmpeg 版本和 libass 支持
```bash
# 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
```
3. 检测 Python 依赖
```bash
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
```bash
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
1. 询问用户 YouTube URL
2. 调用 download_video.py 脚本
```bash
cd ~/.claude/skills/youtube-clipper
python3 scripts/download_video.py <youtube_url>
```
3. 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
4. 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)
1. 调用 analyze_subtitles.py 解析 VTT 字幕
```bash
python3 scripts/analyze_subtitles.py <subtitle_path>
```
2. 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
3. **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)
4. 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
5. **章节生成原则**:
- 粒度:每个章节 2-5 分钟(避免太短或太长)
- 完整性:确保所有视频内容都被覆盖,无遗漏
- 有意义:每个章节是一个相对独立的话题
- 自然切分:在主题转换点切分,不要机械地按时间切
6. 向用户展示章节列表:
```
📊 分析完成,生成 X 个章节:
1. [00:00 - 03:15] AGI 不是时间点,是指数曲线
核心: AI 模型能力每 4-12 月翻倍,工程师已用 Claude 写代码
关键词: AGI、指数增长、Claude CodeFrom op7418/Youtube-clipper-skill, MIT.
Signals
- Stars
- 2,255
- Forks
- 322
- Open issues
- 8
- Last commit
- Jan 22, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/op7418/Youtube-clipper-skill
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from op7418
Cite this page
youtube-clipper skill. Agent Mart. https://agentmart.dev/skills/op7418-youtube-clipper (last updated 2026-10-24)