Skip to content
Back to search

youtube-clipper

SkillWorks with Claude CodeGitHub

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

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/op7418-youtube-clipper-skill/badge.svg)](/listings/op7418-youtube-clipper-skill)

HTML

<a href="/listings/op7418-youtube-clipper-skill"><img src="/api/listings/op7418-youtube-clipper-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Option 1: npx skills (Recommended)

npx skills add https://github.com/op7418/Youtube-clipper-skill

This command will automatically install the skill to `~/.claude/skills/youtube-clipper/`.

Option 2: Manual Installation

git clone https://github.com/op7418/Youtube-clipper-skill.git
cd Youtube-clipper-skill
bash install_as_skill.sh

The install script will: - Copy files to `~/.claude/skills/youtube-clipper/` - Install Python dependencies (yt-dlp, pysrt, python-dotenv) - Check system dependencies (Python, yt-dlp, FFmpeg) - Create `.env` configuration file

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 373 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. ---
  2. name: youtube-clipper
  3. description: >
  4. 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),
  5. 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。
  6. 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。
  7. 关键词:视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video
  8. allowed-tools:
  9. - Read
  10. - Write
  11. - Bash
  12. - Glob
  13. - AskUserQuestion
  14. model: claude-sonnet-4-5-20250514
  15. ---
  16. # YouTube 视频智能剪辑工具
  17. > **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`.
  18. ## 工作流程
  19. 你将按照以下 6 个阶段执行 YouTube 视频剪辑任务:
  20. ### 阶段 1: 环境检测
  21. **目标**: 确保所有必需工具和依赖都已安装
  22. 1. 检测 yt-dlp 是否可用
  23. ```bash
  24. yt-dlp --version
  25. ```
  26. 2. 检测 FFmpeg 版本和 libass 支持
  27. ```bash
  28. # 优先检查 ffmpeg-full(macOS)
  29. /opt/homebrew/opt/ffmpeg-full/bin/ffmpeg -version
  30. # 检查标准 FFmpeg
  31. ffmpeg -version
  32. # 验证 libass 支持(字幕烧录必需)
  33. ffmpeg -filters 2>&1 | grep subtitles
  34. ```
  35. 3. 检测 Python 依赖
  36. ```bash
  37. python3 -c "import yt_dlp; print('✅ yt-dlp available')"
  38. python3 -c "import pysrt; print('✅ pysrt available')"
  39. ```
  40. **如果环境检测失败**:
  41. - yt-dlp 未安装: 提示 `brew install yt-dlp` 或 `pip install yt-dlp`
  42. - FFmpeg 无 libass: 提示安装 ffmpeg-full
  43. ```bash
  44. brew install ffmpeg-full # macOS
  45. ```
  46. - Python 依赖缺失: 提示 `pip install pysrt python-dotenv`
  47. **注意**:
  48. - 标准 Homebrew FFmpeg 不包含 libass,无法烧录字幕
  49. - ffmpeg-full 路径: `/opt/homebrew/opt/ffmpeg-full/bin/ffmpeg` (Apple Silicon)
  50. - 必须先通过环境检测才能继续
  51. ---
  52. ### 阶段 2: 下载视频
  53. **目标**: 下载 YouTube 视频和英文字幕
  54. 1. 询问用户 YouTube URL
  55. 2. 调用 download_video.py 脚本
  56. ```bash
  57. cd ~/.claude/skills/youtube-clipper
  58. python3 scripts/download_video.py <youtube_url>
  59. ```
  60. 3. 脚本会:
  61. - 下载视频(最高 1080p,mp4 格式)
  62. - 下载英文字幕(VTT 格式,自动字幕作为备选)
  63. - 输出文件路径和视频信息
  64. 4. 向用户展示:
  65. - 视频标题
  66. - 视频时长
  67. - 文件大小
  68. - 下载路径
  69. **输出**:
  70. - 视频文件: `<id>.mp4`(使用视频 ID 命名,避免特殊字符问题)
  71. - 字幕文件: `<id>.en.vtt`
  72. ---
  73. ### 阶段 3: 分析章节(核心差异化功能)
  74. **目标**: 使用 Claude AI 分析字幕内容,生成精细章节(2-5 分钟级别)
  75. 1. 调用 analyze_subtitles.py 解析 VTT 字幕
  76. ```bash
  77. python3 scripts/analyze_subtitles.py <subtitle_path>
  78. ```
  79. 2. 脚本会输出结构化字幕数据:
  80. - 完整字幕文本(带时间戳)
  81. - 总时长
  82. - 字幕条数
  83. 3. **你需要执行 AI 分析**(这是最关键的步骤):
  84. - 阅读完整字幕内容
  85. - 理解内容语义和主题转换点
  86. - 识别自然的话题切换位置
  87. - 生成 2-5 分钟粒度的章节(避免半小时粗粒度切分)
  88. 4. 为每个章节生成:
  89. - **标题**: 精炼的主题概括(10-20 字)
  90. - **时间范围**: 起始和结束时间(格式: MM:SS 或 HH:MM:SS)
  91. - **核心摘要**: 1-2 句话说明这段讲了什么(50-100 字)
  92. - **关键词**: 3-5 个核心概念词
  93. 5. **章节生成原则**:
  94. - 粒度:每个章节 2-5 分钟(避免太短或太长)
  95. - 完整性:确保所有视频内容都被覆盖,无遗漏
  96. - 有意义:每个章节是一个相对独立的话题
  97. - 自然切分:在主题转换点切分,不要机械地按时间切
  98. 6. 向用户展示章节列表:
  99. ```
  100. 📊 分析完成,生成 X 个章节:
  101. 1. [00:00 - 03:15] AGI 不是时间点,是指数曲线
  102. 核心: AI 模型能力每 4-12 月翻倍,工程师已用 Claude 写代码
  103. 关键词: AGI、指数增长、Claude Code
  104. 2. [03:15 - 06:30] 中国在 AI 上的差距
  105. 核心: 芯片禁运卡住中国,DeepSeek benchmark 优化不代表实力
  106. 关键词: 中国、芯片禁运、DeepSeek
  107. ... (所有章节)
  108. ✓ 所有内容已覆盖,无遗漏
  109. ```
  110. ---
  111. ### 阶段 4: 用户选择
  112. **目标**: 让用户选择要剪辑的章节和处理选项
  113. 1. 使用 AskUserQuestion 工具让用户选择章节
  114. - 提供章节编号供用户选择
  115. - 支持多选(可以选择多个章节)
  116. 2. 询问处理选项:
  117. - 是否生成双语字幕?(英文 + 中文)
  118. - 是否烧录字幕到视频?(硬字幕)
  119. - 是否生成总结文案?
  120. 3. 确认用户选择并展示处理计划
  121. ---
  122. ### 阶段 5: 剪辑处理(核心执行阶段)
  123. **目标**: 并行执行多个处理任务
  124. 对于每个用户选择的章节,执行以下步骤:
  125. #### 5.1 剪辑视频片段
  126. ```bash
  127. python3 scripts/clip_video.py <video_path> <start_time> <end_time> <output_path>
  128. ```
  129. - 使用 FFmpeg 精确剪辑
  130. - 保持原始视频质量
  131. - 输出: `<章节标题>_clip.mp4`
  132. #### 5.2 提取字幕片段
  133. - 从完整字幕中过滤出该时间段的字幕
  134. - 调整时间戳(减去起始时间,从 00:00:00 开始)
  135. - 转换为 SRT 格式
  136. - 输出: `<章节标题>_original.srt`
  137. #### 5.3 翻译字幕(如果用户选择)
  138. ```bash
  139. python3 scripts/translate_subtitles.py <subtitle_path>
  140. ```
  141. - **批量翻译优化**: 每批 20 条字幕一起翻译(节省 95% API 调用)
  142. - 翻译策略:
  143. - 保持技术术语的准确性
  144. - 口语化表达(适合短视频)
  145. - 简洁流畅(避免冗长)
  146. - 输出: `<章节标题>_translated.srt`
  147. #### 5.4 生成双语字幕文件(如果用户选择)
  148. - 合并英文和中文字幕
  149. - 格式: SRT 双语(每条字幕包含英文和中文)
  150. - 样式: 英文在上,中文在下
  151. - 输出: `<章节标题>_bilingual.srt`
  152. #### 5.5 烧录字幕到视频(如果用户选择)
  153. ```bash
  154. python3 scripts/burn_subtitles.py <video_path> <subtitle_path> <output_path>
  155. ```
  156. - 使用 ffmpeg-full(libass 支持)
  157. - **使用临时目录解决路径空格问题**(关键!)
  158. - 字幕样式:
  159. - 字体大小: 24
  160. - 底部边距: 30
  161. - 颜色: 白色文字 + 黑色描边
  162. - 输出: `<章节标题>_with_subtitles.mp4`
  163. #### 5.6 生成总结文案(如果用户选择)
  164. ```bash
  165. python3 scripts/generate_summary.py <chapter_info>
  166. ```
  167. - 基于章节标题、摘要和关键词
  168. - 生成适合社交媒体的文案
  169. - 包含: 标题、核心观点、适合平台(小红书、抖音等)
  170. - 输出: `<章节标题>_summary.md`
  171. **进度展示**:
  172. ```
  173. 🎬 开始处理章节 1/3: AGI 不是时间点,是指数曲线
  174. 1/6 剪辑视频片段... ✅
  175. 2/6 提取字幕片段... ✅
  176. 3/6 翻译字幕为中文... [=====> ] 50% (26/52)
  177. 4/6 生成双语字幕文件... ✅
  178. 5/6 烧录字幕到视频... ✅
  179. 6/6 生成总结文案... ✅
  180. ✨ 章节 1 处理完成
  181. ```
  182. ---
  183. ### 阶段 6: 输出结果
  184. **目标**: 组织输出文件并展示给用户
  185. 1. 创建输出目录
  186. ```
  187. ./youtube-clips/<日期时间>/
  188. ```
  189. 输出目录位于当前工作目录下
  190. 2. 组织文件结构:
  191. ```
  192. <章节标题>/
  193. ├── <章节标题>_clip.mp4 # 原始剪辑(无字幕)
  194. ├── <章节标题>_with_subtitles.mp4 # 烧录字幕版本
  195. ├── <章节标题>_bilingual.srt # 双语字幕文件
  196. └── <章节标题>_summary.md # 总结文案
  197. ```
  198. 3. 向用户展示:
  199. - 输出目录路径
  200. - 文件列表(带文件大小)
  201. - 快速预览命令
  202. ```
  203. ✨ 处理完成!
  204. 📁 输出目录: ./youtube-clips/20260121_143022/
  205. 文件列表:
  206. 🎬 AGI_指数曲线_双语硬字幕.mp4 (14 MB)
  207. 📄 AGI_指数曲线_双语字幕.srt (2.3 KB)
  208. 📝 AGI_指数曲线_总结.md (3.2 KB)
  209. 快速预览:
  210. open ./youtube-clips/20260121_143022/AGI_指数曲线_双语硬字幕.mp4
  211. ```
  212. 4. 询问是否继续剪辑其他章节
  213. - 如果是,返回阶段 4(用户选择)
  214. - 如果否,结束 Skill
  215. ---
  216. ## 关键技术点
  217. ### 1. FFmpeg 路径空格问题
  218. **问题**: FFmpeg subtitles 滤镜无法正确解析包含空格的路径
  219. **解决方案**: burn_subtitles.py 使用临时目录
  220. - 创建无空格临时目录
  221. - 复制文件到临时目录
  222. - 执行 FFmpeg
  223. - 移动输出文件回目标位置
  224. ### 2. 批量翻译优化
  225. **问题**: 逐条翻译会产生大量 API 调用
  226. **解决方案**: 每批 20 条字幕一起翻译
  227. - 节省 95% API 调用
  228. - 提高翻译速度
  229. - 保持翻译一致性
  230. ### 3. 章节分析精细度
  231. **目标**: 生成 2-5 分钟粒度的章节,避免半小时粗粒度
  232. **方法**:
  233. - 理解字幕语义,识别主题转换
  234. - 寻找自然的话题切换点
  235. - 确保每个章节有完整的论述
  236. - 避免机械按时间切分
  237. ### 4. FFmpeg vs ffmpeg-full
  238. **区别**:
  239. - 标准 FFmpeg: 无 libass 支持,无法烧录字幕
  240. - ffmpeg-full: 包含 libass,支持字幕烧录
  241. **路径**:
  242. - 标准: `/opt/homebrew/bin/ffmpeg`
  243. - ffmpeg-full: `/opt/homebrew/opt/ffmpeg-full/bin/ffmpeg` (Apple Silicon)
  244. ---
  245. ## 错误处理
  246. ### 环境问题
  247. - 缺少工具 → 提示安装命令
  248. - FFmpeg 无 libass → 引导安装 ffmpeg-full
  249. - Python 依赖缺失 → 提示 pip install
  250. ### 下载问题
  251. - 无效 URL → 提示检查 URL 格式
  252. - 字幕缺失 → 尝试自动字幕
  253. - 网络错误 → 提示重试
  254. ### 处理问题
  255. - FFmpeg 执行失败 → 显示详细错误信息
  256. - 翻译失败 → 重试机制(最多 3 次)
  257. - 磁盘空间不足 → 提示清理空间
  258. ---
  259. ## 输出文件命名规范
  260. - 视频片段: `<章节标题>_clip.mp4`
  261. - 字幕文件: `<章节标题>_bilingual.srt`
  262. - 烧录版本: `<章节标题>_with_subtitles.mp4`
  263. - 总结文案: `<章节标题>_summary.md`
  264. **文件名处理**:
  265. - 移除特殊字符(`/`, `\`, `:`, `*`, `?`, `"`, `<`, `>`, `|`)
  266. - 空格替换为下划线
  267. - 限制长度(最多 100 字符)
  268. ---
  269. ## 用户体验要点
  270. 1. **进度可见**: 每个步骤都展示进度和状态
  271. 2. **错误友好**: 清晰的错误信息和解决方案
  272. 3. **可控性**: 用户选择要剪辑的章节和处理选项
  273. 4. **高质量**: 章节分析有意义,翻译准确流畅
  274. 5. **完整性**: 提供原始和处理后的多个版本
  275. ---
  276. ## 开始执行
  277. 当用户触发这个 Skill 时:
  278. 1. 立即开始阶段 1(环境检测)
  279. 2. 按照 6 个阶段顺序执行
  280. 3. 每个阶段完成后自动进入下一阶段
  281. 4. 遇到问题时提供清晰的解决方案
  282. 5. 最后展示完整的输出结果
  283. 记住:这个 Skill 的核心价值在于 **AI 精细章节分析** 和 **无缝的技术处理**,让用户能快速从长视频中提取高质量的短视频片段。
README.md · README · 319 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # YouTube Clipper Skill
  2. > AI-powered YouTube video clipper for Claude Code. Download videos, generate semantic chapters, clip segments, translate subtitles to bilingual format, and burn subtitles into videos.
  3. [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
  4. [![Python](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
  5. English | [简体中文](README.zh-CN.md)
  6. [Features](#features) • [Installation](#installation) • [Usage](#usage) • [Requirements](#requirements) • [Configuration](#configuration) • [Troubleshooting](#troubleshooting)
  7. ---
  8. ## Features
  9. - **AI Semantic Analysis** - Generate fine-grained chapters (2-5 minutes each) by understanding video content, not just mechanical time splitting
  10. - **Precise Clipping** - Use FFmpeg to extract video segments with frame-accurate timing
  11. - **Bilingual Subtitles** - Batch translate subtitles to Chinese/English with 95% API call reduction
  12. - **Subtitle Burning** - Hardcode bilingual subtitles into videos with customizable styling
  13. - **Content Summarization** - Auto-generate social media content (Xiaohongshu, Douyin, WeChat)
  14. ---
  15. ## Installation
  16. ### Option 1: npx skills (Recommended)
  17. ```bash
  18. npx skills add https://github.com/op7418/Youtube-clipper-skill
  19. ```
  20. This command will automatically install the skill to `~/.claude/skills/youtube-clipper/`.
  21. ### Option 2: Manual Installation
  22. ```bash
  23. git clone https://github.com/op7418/Youtube-clipper-skill.git
  24. cd Youtube-clipper-skill
  25. bash install_as_skill.sh
  26. ```
  27. The install script will:
  28. - Copy files to `~/.claude/skills/youtube-clipper/`
  29. - Install Python dependencies (yt-dlp, pysrt, python-dotenv)
  30. - Check system dependencies (Python, yt-dlp, FFmpeg)
  31. - Create `.env` configuration file
  32. ---
  33. ## Requirements
  34. ### System Dependencies
  35. | Dependency | Version | Purpose | Installation |
  36. |------------|---------|---------|--------------|
  37. | **Python** | 3.8+ | Script execution | [python.org](https://www.python.org/downloads/) |
  38. | **yt-dlp** | Latest | YouTube download | `brew install yt-dlp` (macOS)<br>`sudo apt install yt-dlp` (Ubuntu)<br>`pip install yt-dlp` (pip) |
  39. | **FFmpeg with libass** | Latest | Video processing & subtitle burning | `brew install ffmpeg-full` (macOS)<br>`sudo apt install ffmpeg libass-dev` (Ubuntu) |
  40. ### Python Packages
  41. These are automatically installed by the install script:
  42. - `yt-dlp` - YouTube downloader
  43. - `pysrt` - SRT subtitle parser
  44. - `python-dotenv` - Environment variable management
  45. ### Important: FFmpeg libass Support
  46. **macOS users**: The standard `ffmpeg` package from Homebrew does NOT include libass support (required for subtitle burning). You must install `ffmpeg-full`:
  47. ```bash
  48. # Remove standard ffmpeg (if installed)
  49. brew uninstall ffmpeg
  50. # Install ffmpeg-full (includes libass)
  51. brew install ffmpeg-full
  52. ```
  53. **Verify libass support**:
  54. ```bash
  55. ffmpeg -filters 2>&1 | grep subtitles
  56. # Should output: subtitles V->V (...)
  57. ```
  58. ---
  59. ## Usage
  60. ### In Claude Code
  61. Simply tell Claude to clip a YouTube video:
  62. ```
  63. Clip this YouTube video: https://youtube.com/watch?v=VIDEO_ID
  64. ```
  65. or
  66. ```
  67. 剪辑这个 YouTube 视频:https://youtube.com/watch?v=VIDEO_ID
  68. ```
  69. ### Workflow
  70. 1. **Environment Check** - Verifies yt-dlp, FFmpeg, and Python dependencies
  71. 2. **Video Download** - Downloads video (up to 1080p) and English subtitles
  72. 3. **AI Chapter Analysis** - Claude analyzes subtitles to generate semantic chapters (2-5 min each)
  73. 4. **User Selection** - Choose which chapters to clip and processing options
  74. 5. **Processing** - Clips video, translates subtitles, burns subtitles (if requested)
  75. 6. **Output** - Organized files in `./youtube-clips/<timestamp>/`
  76. ### Output Files
  77. For each clipped chapter:
  78. ```
  79. ./youtube-clips/20260122_143022/
  80. └── Chapter_Title/
  81. ├── Chapter_Title_clip.mp4 # Original clip (no subtitles)
  82. ├── Chapter_Title_with_subtitles.mp4 # With burned subtitles
  83. ├── Chapter_Title_bilingual.srt # Bilingual subtitle file
  84. └── Chapter_Title_summary.md # Social media content
  85. ```
  86. ---
  87. ## Configuration
  88. The skill uses environment variables for customization. Edit `~/.claude/skills/youtube-clipper/.env`:
  89. ### Key Settings
  90. ```bash
  91. # FFmpeg path (auto-detected if empty)
  92. FFMPEG_PATH=
  93. # Output directory (default: current working directory)
  94. OUTPUT_DIR=./youtube-clips
  95. # Video quality limit (720, 1080, 1440, 2160)
  96. MAX_VIDEO_HEIGHT=1080
  97. # Translation batch size (20-25 recommended)
  98. TRANSLATION_BATCH_SIZE=20
  99. # Target language for translation
  100. TARGET_LANGUAGE=中文
  101. # Target chapter duration in seconds (180-300 recommended)
  102. TARGET_CHAPTER_DURATION=180
  103. ```
  104. For full configuration options, see [.env.example](.env.example).
  105. ---
  106. ## Examples
  107. ### Example 1: Extract highlights from a tech interview
  108. **Input**:
  109. ```
  110. Clip this video: https://youtube.com/watch?v=Ckt1cj0xjRM
  111. ```
  112. **Output** (AI-generated chapters):
  113. ```
  114. 1. [00:00 - 03:15] AGI as an exponential curve, not a point in time
  115. 2. [03:15 - 06:30] China's gap in AI development
  116. 3. [06:30 - 09:45] The impact of chip bans
  117. ...
  118. ```
  119. **Result**: Select chapters → Get clipped videos with bilingual subtitles + social media content
  120. ### Example 2: Create short clips from a course
  121. **Input**:
  122. ```
  123. Clip this lecture video and create bilingual subtitles: https://youtube.com/watch?v=LECTURE_ID
  124. ```
  125. **Options**:
  126. - Generate bilingual subtitles: Yes
  127. - Burn subtitles into video: Yes
  128. - Generate summary: Yes
  129. **Result**: High-quality clips ready for sharing on social media platforms
  130. ---
  131. ## Key Differentiators
  132. ### AI Semantic Chapter Analysis
  133. Unlike mechanical time-based splitting, this skill uses Claude's AI to:
  134. - Understand content semantics
  135. - Identify natural topic transitions
  136. - Generate meaningful chapter titles and summaries
  137. - Ensure complete coverage with no gaps
  138. **Example**:
  139. ```
  140. ❌ Mechanical splitting: [0:00-30:00], [30:00-60:00]
  141. ✅ AI semantic analysis:
  142. - [00:00-03:15] AGI definition
  143. - [03:15-07:30] China's AI landscape
  144. - [07:30-12:00] Chip ban impacts
  145. ```
  146. ### Batch Translation Optimization
  147. Translates 20 subtitles at once instead of one-by-one:
  148. - 95% reduction in API calls
  149. - 10x faster translation
  150. - Better translation consistency
  151. ### Bilingual Subtitle Format
  152. Generated subtitle files contain both English and Chinese:
  153. ```srt
  154. 1
  155. 00:00:00,000 --> 00:00:03,500
  156. This is the English subtitle
  157. 这是中文字幕
  158. 2
  159. 00:00:03,500 --> 00:00:07,000
  160. Another English line
  161. 另一行中文
  162. ```
  163. ---
  164. ## Troubleshooting
  165. ### FFmpeg subtitle burning fails
  166. **Error**: `Option not found: subtitles` or `filter not found`
  167. **Solution**: Install `ffmpeg-full` (macOS) or ensure `libass-dev` is installed (Ubuntu):
  168. ```bash
  169. # macOS
  170. brew uninstall ffmpeg
  171. brew install ffmpeg-full
  172. # Ubuntu
  173. sudo apt install ffmpeg libass-dev
  174. ```
  175. ### Video download is slow
  176. **Solution**: Set a proxy in `.env`:
  177. ```bash
  178. YT_DLP_PROXY=http://proxy-server:port
  179. # or
  180. YT_DLP_PROXY=socks5://proxy-server:port
  181. ```
  182. ### Subtitle translation fails
  183. **Cause**: API rate limiting or network issues
  184. **Solution**: The skill automatically retries up to 3 times. If persistent, check:
  185. - Network connectivity
  186. - Claude API status
  187. - Reduce `TRANSLATION_BATCH_SIZE` in `.env`
  188. ### Special characters in filenames
  189. **Issue**: Filenames with `:`, `/`, `?`, etc. may cause errors
  190. **Solution**: The skill automatically sanitizes filenames by:
  191. - Removing special characters: `/ \ : * ? " < > |`
  192. - Replacing spaces with underscores
  193. - Limiting length to 100 characters
  194. ---
  195. ## Documentation
  196. - **[SKILL.md](SKILL.md)** - Complete workflow and technical details
  197. - **[TECHNICAL_NOTES.md](TECHNICAL_NOTES.md)** - Implementation notes and design decisions
  198. - **[FIXES_AND_IMPROVEMENTS.md](FIXES_AND_IMPROVEMENTS.md)** - Changelog and bug fixes
  199. - **[references/](references/)** - FFmpeg, yt-dlp, and subtitle formatting guides
  200. ---
  201. ## Contributing
  202. Contributions are welcome! Please:
  203. - Report bugs via [GitHub Issues](https://github.com/op7418/Youtube-clipper-skill/issues)
  204. - Submit feature requests
  205. - Open pull requests for improvements
  206. ---
  207. ## License
  208. This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
  209. ---
  210. ## Acknowledgements
  211. - **[Claude Code](https://claude.ai/claude-code)** - The AI-powered CLI tool
  212. - **[yt-dlp](https://github.com/yt-dlp/yt-dlp)** - YouTube download engine
  213. - **[FFmpeg](https://ffmpeg.org/)** - Video processing powerhouse
  214. ---
  215. <div align="center">
  216. **Made with ❤️ by [op7418](https://github.com/op7418)**
  217. If this skill helps you, please give it a ⭐️
  218. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.