Which AI providers are covered?

The skill includes built-in patterns for OpenAI, Anthropic, Google Gemini, xAI (Grok), and many others via LiteLLM integration.

Does it support real-time pricing updates?

Yes, it provides instructions for fetching real-time data from LiteLLM's GitHub database and OpenRouter's API for over 500+ models.

How do I verify model updates?

The skill includes specific pytest validation commands to test backend capabilities and token manager integrity after making changes.

What files does this skill help maintain?

It specifically targets capabilities registries (like models and features) and token managers (pricing and context limits) typically found in Python backends.

Model Registry Maintainer

Name: Model Registry Maintainer
Author: Microck

byMicrock

•

Data Science & ML

Maintains and updates AI model registries including pricing, context windows, and provider capabilities.

About

The Model Registry Maintainer is a specialized skill designed to manage the lifecycle of LLM metadata within application backends. It provides structured workflows for adding new models, updating token pricing, and managing context window limits across systems like MassGen. By integrating with live data sources like LiteLLM and OpenRouter, this skill ensures that your application's model catalog remains accurate, enabling precise cost estimation, feature validation, and up-to-date documentation for the latest releases from OpenAI, Anthropic, Google, and other major providers.

Key Features

Support for tracking release dates, vision capabilities, and tool-use features
Integration guidance for LiteLLM and OpenRouter pricing databases
81 GitHub stars
Standardized workflows for updating Python-based model registries and token managers
Automated validation through pre-defined pytest commands
Documentation regeneration scripts for maintaining backend tables

Use Cases

Synchronizing internal pricing tables with the latest official API costs
Updating context window limits and output token caps for existing models
Adding support for newly released LLMs like GPT-5 or Claude 4 variants

About

Key Features

Support for tracking release dates, vision capabilities, and tool-use features
Integration guidance for LiteLLM and OpenRouter pricing databases
81 GitHub stars
Standardized workflows for updating Python-based model registries and token managers
Automated validation through pre-defined pytest commands
Documentation regeneration scripts for maintaining backend tables

Use Cases

Synchronizing internal pricing tables with the latest official API costs
Updating context window limits and output token caps for existing models
Adding support for newly released LLMs like GPT-5 or Claude 4 variants