How does it handle pricing updates?

The skill prioritizes checking the LiteLLM database for real-time pricing and provides a fallback workflow for manual updates in the PROVIDER_PRICING dictionary.

Which AI providers are supported by default?

It includes predefined patterns and documentation workflows for OpenAI, Anthropic, Google Gemini, and xAI (Grok).

What files does this skill help maintain?

It primarily targets maintenance for capabilities.py (handling model features and release dates) and token_manager.py (handling pricing and context limits).

Can I use this for internal or custom AI models?

Yes, the skill includes specific instructions for adding custom models and internal organization endpoints that aren't listed in public databases.

Model Registry Maintainer

Name: Model Registry Maintainer
Author: Activer007

byActiver007

Data Science & ML

Maintains and updates AI model registries, pricing databases, and backend capabilities for LLM-powered applications.

About

The Model Registry Maintainer skill provides a structured framework for keeping AI model metadata accurate and up-to-date. It guides users through the process of updating model versions, release dates, pricing tiers, and context window limits within the MassGen backend. By leveraging the LiteLLM database for automated lookups and providing standardized workflows for adding new providers like OpenAI, Anthropic, and Google, it ensures that cost estimation and model selection logic remains reliable as the AI landscape rapidly changes.

Key Features

Automated documentation regeneration for backend model tables
Validation scripts for testing registry and token manager integrity
0 GitHub stars
Integration with LiteLLM database for automated metadata retrieval
Support for custom provider and internal model additions
Standardized workflows for updating model capabilities and pricing

Use Cases

Synchronizing local model pricing with global provider changes
Adding support for new AI providers and their specific API identifiers
Updating backend configurations immediately after a new LLM release

About

Key Features

Automated documentation regeneration for backend model tables
Validation scripts for testing registry and token manager integrity
0 GitHub stars
Integration with LiteLLM database for automated metadata retrieval
Support for custom provider and internal model additions
Standardized workflows for updating model capabilities and pricing

Use Cases

Synchronizing local model pricing with global provider changes
Adding support for new AI providers and their specific API identifiers
Updating backend configurations immediately after a new LLM release