一键导入
youtube-watcher
Fetch and summarize YouTube video transcripts. Use when asked to watch, summarize, or answer questions about a YouTube video.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Fetch and summarize YouTube video transcripts. Use when asked to watch, summarize, or answer questions about a YouTube video.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Advanced browser automation patterns. Connect to existing Chrome, handle SPAs, manage sessions, extract data efficiently.
How to use Firecrawl for web search and clean page scraping inside FRIDAY. Use when an agent needs reliable web context, when Tavily caps out, or when fetch_page returns thin/JS-shell content.
Assess task complexity before responding. Simple tasks get fast answers. Complex tasks get deep analysis.
Structured coding workflow — plan before coding, test after, verify before delivering. Use for any code task.
Build beautiful modern UIs — landing pages, dashboards, components. Quality bar is a real startup site, not a tutorial project.
Make AI-generated text sound human and natural. Apply when writing emails, cover letters, tweets, messages, or any text that should not sound like AI wrote it.
| name | youtube-watcher |
| description | Fetch and summarize YouTube video transcripts. Use when asked to watch, summarize, or answer questions about a YouTube video. |
| agents | ["research_agent","deep_research_agent"] |
When Travis sends a YouTube link or says "summarize this video", "watch this", "what's this video about":
Run this command via the terminal/exec tool:
yt-dlp --write-auto-sub --sub-lang en --skip-download --print-json "VIDEO_URL" 2>/dev/null | python3 -c "
import json, sys
data = json.load(sys.stdin)
subs = data.get('subtitles', {}).get('en') or data.get('automatic_captions', {}).get('en', [])
if subs:
# Get the vtt/json subtitle URL
for s in subs:
if s.get('ext') == 'json3':
print(s['url'])
break
else:
print(subs[0]['url'])
else:
print('NO_SUBS')
"
Simpler approach — just get the subtitle text directly:
yt-dlp --write-auto-sub --sub-lang en --skip-download -o "/tmp/yt_sub" "VIDEO_URL" 2>/dev/null && cat /tmp/yt_sub.en.vtt 2>/dev/null | grep -v "^$" | grep -v "^WEBVTT" | grep -v "^Kind:" | grep -v "^Language:" | grep -v "^[0-9][0-9]:" | head -200
yt-dlp --print "%(title)s|%(uploader)s|%(duration_string)s|%(view_count)s" "VIDEO_URL" 2>/dev/null
Returns: title | channel | duration | views