joshuaroll/research-skills · Archived

media-transcript-search

Extract and search transcripts from multimedia sources (primarily YouTube). Allows finding specific topics within long content without watching the whole video.

First seen Feb 4, 2026

Installation

$ npx skills add joshuaroll/research-skills --skill media-transcript-search

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from joshuaroll/research-skills.

npx skills add joshuaroll/research-skills

Browse all from joshuaroll/research-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,491 B
  • docs SUMMARY.md 191 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 3 installs

SKILL.md

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 or Playlist.
  2. Keyword Search: Find timestamps where specific keywords or phrases are mentioned.
  3. Metadata: Automatically fetches Video Title to context script.
  4. Export: Dump transcripts as .txt or .srt for external use.

Usage

Run the python script get_transcript.py.

Arguments

  • id (required): The YouTube Video ID (e.g., dQw4w9WgXcQ) or Playlist ID.
  • --playlist (optional): Set if the ID is a playlist. Limits to first 10 videos.
  • --search (optional): Keyword to find.
  • --format (optional): "json" (default), "txt", or "srt".

Example

# Find "climate change" in a Playlist
python3 get_transcript.py PLAYLIST_ID --playlist --search "climate change"

# Export a clean text script for a video
python3 get_transcript.py VIDEO_ID --format txt

Tips for the Agent

  • Playlist Limits: Playlists are limited to the first 10 videos to ensure speed.
  • SRT Format: Use srt if you need to re-upload captions or import into a video editor.