What is the primary purpose of the Model Registry Maintainer skill?

It provides a standardized workflow to update model metadata, pricing, and capabilities within the MassGen backend registry to keep it current with provider releases.

Does it support providers other than OpenAI and Anthropic?

Yes, it includes specific guidelines and data for Google Gemini, xAI Grok, and other providers supported through the LiteLLM and OpenRouter ecosystems.

How does this skill handle pricing updates?

It prioritizes fetching real-time data from the LiteLLM database, while providing instructions for hardcoded fallbacks in token_manager.py for custom or new models.

Which specific files are managed by this skill?

The skill focuses on maintaining capabilities.py for model features and release dates, and token_manager.py for pricing and context window limits.

How can I verify that my registry updates are correct?

The skill includes specific validation commands using pytest and massgen config generation flags to test the registry integrity after updates.

Model Registry Maintainer

Name: Model Registry Maintainer
Author: Activer007

byActiver007

Ciencia de Datos y ML

Manages and updates AI model registries, pricing structures, and context window limits for the MassGen backend.

Acerca de

The Model Registry Maintainer skill provides a comprehensive workflow for keeping AI model metadata synchronized with the latest provider releases. It guides developers through updating backend capabilities and token management files, ensuring that pricing, context windows, and model features are accurate for cost estimation and configuration. By leveraging LiteLLM data sources and providing standardized validation steps, this skill streamlines the process of integrating new models from providers like OpenAI, Anthropic, Google, and xAI while maintaining system-wide consistency.

Características Principales

Pricing management for input, output, and cached tokens
Automated validation scripts for registry and documentation integrity
Integration steps for LiteLLM and OpenRouter data sources
0 GitHub stars
Context window and max output token configuration guidance
Standardized workflow for updating model capabilities and release dates

Casos de Uso

Updating token pricing for existing providers to ensure accurate cost tracking
Configuring backend support for new AI model capabilities and features
Integrating a newly released AI model into the MassGen ecosystem

Acerca de

Características Principales

Pricing management for input, output, and cached tokens
Automated validation scripts for registry and documentation integrity
Integration steps for LiteLLM and OpenRouter data sources
0 GitHub stars
Context window and max output token configuration guidance
Standardized workflow for updating model capabilities and release dates

Casos de Uso

Updating token pricing for existing providers to ensure accurate cost tracking
Configuring backend support for new AI model capabilities and features
Integrating a newly released AI model into the MassGen ecosystem