Menu
Fetch and store transcripts from YouTube videos for deep content analysis.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Specialized in the MLCommons Croissant metadata specification. Can generate, validate, and serialize dataset metadata into compliant JSON-LD.
Universal Numeric Fingerprint (UNF) generator. For strings, it splits into words and sorts them alphabetically to provide order-invariant fingerprints. Supports dataframes and files too.
Send results and data files to stakeholders via email.
The Visual Systems Architect is an expert in translating complex technical requirements and infrastructure setups into structured, visually intuitive architectural diagrams (Mermaid.js).
Secure GitHub Orchestrator for Croissant Toolkit. Connect any repository, discovery skills, and audit ODRL sovereignty status.
ODRL Secure Login Interface. Uses authorization keys from ~/.odrl/authorize.did to automatically unpackage protected skills from the vault.
| name | transcriber |
| description | Fetch and store transcripts from YouTube videos for deep content analysis. |
The Transcriber skill allows the agent to download the text transcript (closed captions) of YouTube videos. This is essential for converting video tutorials and discussions into searchable and indexable text for the Croissant metadata engine.
Transcripts are stored locally in ./data/transcripts/ as plain text files named by their YouTube Video ID.
Fetches the transcript for a single video ID/URL or automatically processes the youtube_search_results.json if no arguments are provided.
Usage:
# Transcribe a specific video
python3 transcriber/scripts/transcribe.py <VIDEO_URL_OR_ID>
# Batch transcribe the results from the last Youtuber search
python3 transcriber/scripts/transcribe.py
Extracts high-fidelity metadata (Title, Description, Views, Upload Date) in Schema.org JSON-LD format.
Usage:
python3 transcriber/scripts/get_metadata.py <VIDEO_URL_OR_ID>
Output:
Metadata is saved to ./data/metadata/<VIDEO_ID>.json.
Example:
python3 transcriber/scripts/transcribe.py https://www.youtube.com/watch?v=6cWcZ2G53gE