youtube-transcript
Download and process YouTube video transcripts using yt-dlp. Use this when extracting subtitles, creating summaries from videos, or processing video content.
Best use case
youtube-transcript is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Download and process YouTube video transcripts using yt-dlp. Use this when extracting subtitles, creating summaries from videos, or processing video content.
Download and process YouTube video transcripts using yt-dlp. Use this when extracting subtitles, creating summaries from videos, or processing video content.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "youtube-transcript" skill to help with this workflow task. Context: Download and process YouTube video transcripts using yt-dlp. Use this when extracting subtitles, creating summaries from videos, or processing video content.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/youtube-transcript/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How youtube-transcript Compares
| Feature / Agent | youtube-transcript | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Download and process YouTube video transcripts using yt-dlp. Use this when extracting subtitles, creating summaries from videos, or processing video content.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# YouTube Transcript Downloader
유튜브 영상에서 자막을 추출하고 처리하는 스킬입니다.
## Priority Order
```
1. yt-dlp 설치 확인
2. 사용 가능한 자막 목록 확인
3. 수동 자막 우선 시도
4. 자동 생성 자막 폴백
5. 최후 수단: Whisper 변환
```
## Requirements
```bash
# macOS
brew install yt-dlp
# Linux
sudo apt install yt-dlp
# Universal
pip install yt-dlp
```
## Workflow
### Step 1: 자막 목록 확인
```bash
yt-dlp --list-subs "VIDEO_URL"
```
### Step 2: 수동 자막 다운로드 (권장)
```bash
# 한국어 자막
yt-dlp --write-sub --sub-lang ko --skip-download "VIDEO_URL"
# 영어 자막
yt-dlp --write-sub --sub-lang en --skip-download "VIDEO_URL"
```
### Step 3: 자동 생성 자막 (폴백)
```bash
yt-dlp --write-auto-sub --sub-lang ko --skip-download "VIDEO_URL"
```
### Step 4: VTT → 텍스트 변환
```bash
# VTT 파일에서 타임스탬프 제거
sed '/^[0-9]/d; /^$/d; /-->/d' subtitle.ko.vtt > transcript.txt
```
## Output Processing
### 중복 제거
자동 생성 자막은 progressive 캡션으로 인해 중복이 많음:
```python
# 중복 라인 제거
seen = set()
unique_lines = []
for line in lines:
if line not in seen:
seen.add(line)
unique_lines.append(line)
```
### 요약 생성
추출된 자막으로:
- 핵심 내용 요약
- 타임스탬프별 챕터 생성
- 주요 키워드 추출
## Examples
### Example 1: 강의 영상 요약
```
User: 이 유튜브 강의 요약해줘 - https://youtube.com/watch?v=xxx
Claude:
1. yt-dlp로 자막 다운로드
2. VTT → 텍스트 변환
3. 핵심 내용 요약 생성
4. 타임스탬프별 목차 제공
```
### Example 2: 다국어 자막 추출
```
User: 이 영상의 영어/한국어 자막 둘 다 추출해줘
Claude:
1. --list-subs로 가용 언어 확인
2. 각 언어별 자막 다운로드
3. 정리된 텍스트 파일 제공
```
## Error Handling
| 에러 | 원인 | 해결책 |
|------|------|--------|
| `yt-dlp not found` | 미설치 | brew/apt/pip 설치 |
| `No subtitles available` | 자막 없음 | Whisper 사용 제안 |
| `Invalid URL` | URL 오류 | URL 형식 확인 |
| `Video unavailable` | 비공개/삭제 | 사용자에게 알림 |
## Whisper Fallback
자막이 전혀 없는 경우 (사용자 확인 필요):
```bash
# 파일 크기 확인
yt-dlp --print filesize "VIDEO_URL"
# 사용자 승인 후 오디오 다운로드
yt-dlp -x --audio-format mp3 "VIDEO_URL"
# Whisper로 변환
whisper audio.mp3 --language ko --model base
```
**주의**: 대역폭/처리 시간 소요로 사용자 확인 필수Related Skills
azure-ai-transcription-py
Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization. Triggers: "transcription", "speech to text", "Azure AI Transcription", "TranscriptionClient".
youtube-downloader
Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.
extract-transcripts
Extract readable transcripts from Claude Code and Codex CLI session JSONL files
youtube-summarizer
Extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks
youtube-automation
Automate YouTube tasks via Rube MCP (Composio): upload videos, manage playlists, search content, get analytics, and handle comments. Always search tools first for current schemas.
azure-quotas
Check/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection. WHEN: "check quotas", "service limits", "current usage", "request quota increase", "quota exceeded", "validate capacity", "regional availability", "provisioning limits", "vCPU limit", "how many vCPUs available in my subscription".
raindrop-io
Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.
zlibrary-to-notebooklm
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式，自动转换，一键创建知识库。
discover-skills
当你发现当前可用的技能都不够合适（或用户明确要求你寻找技能）时使用。本技能会基于任务目标和约束，给出一份精简的候选技能清单，帮助你选出最适配当前任务的技能。
web-performance-seo
Fix PageSpeed Insights/Lighthouse accessibility "!" errors caused by contrast audit failures (CSS filters, OKLCH/OKLAB, low opacity, gradient text, image backgrounds). Use for accessibility-driven SEO/performance debugging and remediation.
project-to-obsidian
将代码项目转换为 Obsidian 知识库。当用户提到 obsidian、项目文档、知识库、分析项目、转换项目 时激活。 【激活后必须执行】： 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入规则（默认到 00_Inbox/AI/、追加式、统一 Schema） 3. 执行 STEP 0: 使用 AskUserQuestion 询问用户确认 4. 用户确认后才开始 STEP 1 项目扫描 5. 严格按 STEP 0 → 1 → 2 → 3 → 4 顺序执行 【禁止行为】： - 禁止不读 SKILL.md 就开始分析项目 - 禁止跳过 STEP 0 用户确认 - 禁止直接在 30_Resources 创建（先到 00_Inbox/AI/） - 禁止自作主张决定输出位置
obsidian-helper
Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。 【激活后必须执行】： 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩（00_Inbox/AI/、追加式、白名单字段） 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤，不要自作主张 【禁止行为】： - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记（除非用户明确指定）