How does it handle model pricing updates?

The skill prioritizes fetching data from the LiteLLM database for over 500 models, providing fallback patterns for custom or internal models.

What files does this skill help maintain?

It specifically helps maintain capabilities.py for model features and token_manager.py for pricing and context limits within the MassGen architecture.

How do I validate the changes I make to the registry?

The skill provides specific pytest commands to verify the backend capabilities and token manager functionality after updates.

Does this skill support providers like xAI or Google?

Yes, it includes specific configuration patterns for OpenAI, Anthropic, Google Gemini, and xAI Grok models.

Can it help with documentation?

Yes, it includes workflows for regenerating backend tables and documentation to reflect the latest model updates.

Model Registry Maintainer

Name: Model Registry Maintainer
Author: Microck

byMicrock

•

Data Science & ML

Manages AI model configurations, pricing, and capabilities within backend registries for LLM-powered applications.

About

The Model Registry Maintainer skill provides a standardized framework for managing Large Language Model (LLM) registries across backend systems. It guides developers through the process of updating model metadata, including release dates, context window limits, and pricing structures for providers such as OpenAI, Anthropic, and Google. By leveraging integration patterns with LiteLLM and OpenRouter, the skill ensures that backend configurations remain current with the fast-moving AI landscape, enabling accurate cost estimation, token counting, and capability validation.

Key Features

Standardized workflows for adding new AI models and providers
Validation testing for backend capabilities and registry integrity
Automated documentation generation for model tables
Context window and token limit management
Pricing synchronization with LiteLLM and OpenRouter databases
81 GitHub stars

Use Cases

Configuring model-specific capabilities like vision or code execution
Synchronizing token pricing to maintain accurate cost tracking and estimation
Updating a backend registry when a provider releases a new model version

About

Key Features

Standardized workflows for adding new AI models and providers
Validation testing for backend capabilities and registry integrity
Automated documentation generation for model tables
Context window and token limit management
Pricing synchronization with LiteLLM and OpenRouter databases
81 GitHub stars

Use Cases

Configuring model-specific capabilities like vision or code execution
Synchronizing token pricing to maintain accurate cost tracking and estimation
Updating a backend registry when a provider releases a new model version