croissant-toolkit
croissant-toolkit contains 22 collected skills from codata, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
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.
ODRL Secure Login Interface. Uses authorization keys from ~/.odrl/authorize.did to automatically unpackage protected skills from the vault.
Comprehensive testing suite for all toolkit skills (navigator, youtuber, transcriber, translator, croissant_expert, nlp_expert, wizard, communication_officer, obsidian_expert).
Recognize the language of input content or video scripts and translate them precisely into English using Gemini 3.
Specialized in creating RO-Crate packages from Dataverse metadata, with integrated ODRL-based DID (Decentralized Identifier) attribution and provenance via the ro-crate-py library.
Deposit research objects and add semantic annotations to the RO-Hub portal using the rohub library.
Captures visual snapshots (screenshots) of web pages and records screen sessions (video).
Send results and notifications to Telegram channels or users.
Search for videos on YouTube based on specific keywords. Get list of videos with title, description, and URL.
The ultimate data integrator. Orchestrates transcription, translation, NLP analysis, and Croissant serialization into a single automated pipeline.
Extract named entities (persons, organizations, dates, locations) from text and provide them in structured JSON-LD format.
Deep crawl functionality that extracts and visits internal links from a webpage.
Convert Croissant datasets into structured Obsidian Markdown notes with frontmatter and semantic tags.
Store and query Croissant datasets in a Neo4j Graph Database for relational discovery and semantic search.
Orchestrator agent that has comprehensive knowledge and command over all available skills in this toolkit to create complex workflows.
Open Google Chrome or Firefox, search Google, and extract all web pages from the search results.
Discovers and executes all test scripts across all skills in the project to verify system integrity. Use this to run a comprehensive test suite.