Menu
The ultimate data integrator. Orchestrates transcription, translation, NLP analysis, and Croissant serialization into a single automated pipeline.
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
Fetch and store transcripts from YouTube videos for deep content analysis.
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.
| name | wizard |
| description | The ultimate data integrator. Orchestrates transcription, translation, NLP analysis, and Croissant serialization into a single automated pipeline. |
The Wizard skill is the high-level conductor of the Croissant Toolkit. It automates the entire journey from a raw data source (like a YouTube video or a foreign-language document) to a fully compliant and enriched Croissant JSON-LD file.
Transcriber (for videos) or reads local files.Translator to ensure it's in English and refined.NLP Expert (via the Croissant Expert integration) to automatically detect creators, locations, and dates.Croissant JSON-LD file in ./data/croissant/.Runs the full integration flow on any provided content or URL.
Usage:
# Process a YouTube video into a Croissant file
python3 wizard/scripts/wizard.py "https://www.youtube.com/watch?v=VIDEO_ID" "My Dataset Name"
# Process a local file
python3 wizard/scripts/wizard.py ./data/my_notes.txt "Notes Dataset"
# Process raw text
python3 wizard/scripts/wizard.py "Long description of my dataset..." "My Dataset"