media-transcript-search
Extract and search transcripts from multimedia sources (primarily YouTube). Allows finding specific topics within long content without watching the whole video.
npx skills add majiayu000/claude-skill-registry --skill media-transcript-search-joshuaroll-research-skills-3 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Multimedia Transcript Search Skill This skill turns opaque video content into searchable text data, essential for analyzing speeches, lectures, and news clips. ## Capabilities 1. **Get Transcript**: Download the full transcript of a YouTube video. 2. **Keyword Search**: Find timestamps where specific keywords or phrases are mentioned. 3. **Context Window**: Return surrounding text to understand the context of the mention. ## Usage Run the python script `get_transcript.py`. ### Arguments * `video_id` (required): The YouTube Video ID (e.g., `dQw4w9WgXcQ`). * `--search` (optional): Keyword to find. * `--lang` (optional): Language code (default 'en'). ### Example ```bash # Get full transcript for a video python3 get_transcript.py dQw4w9WgXcQ # Find where "climate change" is discussed python3 get_transcript.py dQw4w9WgXcQ --search "climate change" ``` ## Dependencies This skill requires the `youtube-transcript-api` library. ```bash pip install youtube-transcript-api ``` ## Output Format A JSON object containing: * `video_id` * `transcript`: Full list of segments (if no search) OR * `matches`: List of segments matching the search term: * `text`: The text segment. * `start`: Start time
- Capabilities
- Usage
- Arguments
- Example
- Dependencies
- Output Format
- Tips for the Agent
Get full transcript for a video python3 get_transcript.py dQw4w9WgXcQ Find where "climate change" is discussed python3 get_transcript.py dQw4w9WgXcQ --search "climate change" pip install youtube-transcript-api
What does the media-transcript-search skill do?
Extract and search transcripts from multimedia sources (primarily YouTube). Allows finding specific topics within long content without watching the whole video.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill media-transcript-search-joshuaroll-research-skills-3 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.