Youtube watcher
55+ AI agent skills for sales, content, research, and fleet operations. Free lite editions. Full alpha at koino.capital
npx -y skills add koinod/skills --skill youtube-watcherAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.
SKILL.md
1.5 KB, 214 tokens by cl100k_base, as published. Nobody here has run it
YouTube Watcher
Fetch transcripts from YouTube videos to enable summarization, QA, and content extraction.
Usage
Get Transcript
Retrieve the text transcript of a video.
python3 {baseDir}/scripts/get_transcript.py "https://www.youtube.com/watch?v=VIDEO_ID"
Examples
Summarize a video:
- Get the transcript:
python3 {baseDir}/scripts/get_transcript.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ" - Read the output and summarize it for the user.
Find specific information:
- Get the transcript.
- Search the text for keywords or answer the user's question based on the content.
Notes
- Requires
yt-dlpto be installed and available in the PATH. - Works with videos that have closed captions (CC) or auto-generated subtitles.
- If a video has no subtitles, the script will fail with an error message.
What ships with it: 3 files
2.5 KB alongside SKILL.md, 3 of them executable
.clawhub/
- origin.jsonruns147 B
scripts/
- get_transcript.pyruns2.2 KB
- _meta.jsonruns134 B
Gives 0 of the 12 instructions most social media skills give in 214 tokens
Counted across 489 of the 492 authors here whose files we hold, read 2026-08-07
- Adapt formats and tone to each platformin 26 of 489, across 14 files
- Build content around three to five pillarsin 25 of 489, across 13 files
- Read product marketing context before asking questionsin 23 of 489, across 13 files
- Respond to all comments on your postsin 21 of 489, across 9 files
- Use the output flag to specify an output directoryin 14 of 489, across 4 files
- Generate output logo images with white backgroundin 13 of 489, across 4 files
- Fix failing generation scripts directlyin 13 of 489, across 4 files
- Ask user about HTML preview after logo generationin 12 of 489, across 3 files
- Run the download script with a URLin 12 of 489, across 3 files
- Implement exponential backoff for 429 responsesin 12 of 489, across 3 files
- Write the hook firstin 12 of 489, across 7 files
- Include a single clear call to actionin 12 of 489, across 9 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.