When is the best time to use the Model Registry Maintainer?

Use this skill whenever a model provider updates their pricing, releases a new model version, changes context window limits, or introduces new features like vision or reasoning.

Which AI providers are supported by default?

The skill includes specific maintenance patterns for OpenAI, Anthropic, Google (Gemini), and xAI (Grok), but can be extended to any provider supported by the backend.

How does this skill handle LLM pricing updates?

It utilizes the LiteLLM database as a primary source for over 500 models while providing a hardcoded fallback mechanism for custom or brand-new models that haven't been indexed yet.

Does this skill help with documentation?

Yes, it includes specific steps and validation commands to regenerate documentation tables so your external docs always match your internal model registry.

How does it ensure data accuracy?

The skill provides built-in validation commands and pytest scripts to verify the integrity of the capabilities registry and the token manager after any update.

Model Registry Maintainer

Name: Model Registry Maintainer
Author: Activer007

byActiver007

Ciencia de Datos y ML

Maintains and updates model registries, pricing data, and capability maps for LLM backends and providers.

Acerca de

The Model Registry Maintainer skill provides a standardized framework for keeping AI model configurations accurate and current within the MassGen ecosystem. It guides developers through the complex process of updating model availability, release dates, pricing tiers, and context window limits across system-critical files like capabilities.py and token_manager.py. By integrating with the LiteLLM database and providing structured fallback patterns, this skill ensures that backend cost estimation, token counting, and feature validation stay synchronized with the fast-moving landscape of provider releases from OpenAI, Anthropic, Google, and xAI.

Características Principales

Precise management of context windows and input/output token limits
Automated documentation and backend table regeneration scripts
Automated pricing synchronization via LiteLLM database integration
Standardized workflow for adding new LLM models and providers
Capability mapping for vision, web search, and reasoning features
0 GitHub stars

Casos de Uso

Configuring model-specific capability flags to enable advanced AI features
Updating API pricing models to maintain accurate cost monitoring and budgeting
Integrating a newly released model like GPT-5 or Claude 4 into an existing backend

Acerca de

Características Principales

Precise management of context windows and input/output token limits
Automated documentation and backend table regeneration scripts
Automated pricing synchronization via LiteLLM database integration
Standardized workflow for adding new LLM models and providers
Capability mapping for vision, web search, and reasoning features
0 GitHub stars

Casos de Uso

Configuring model-specific capability flags to enable advanced AI features
Updating API pricing models to maintain accurate cost monitoring and budgeting
Integrating a newly released model like GPT-5 or Claude 4 into an existing backend