model-discovery

Fetch and classify AI provider models into fast, default, and heavy tiers.

8|1|Updated Jul 11, 2025

Search Tags:#automation #devops #cache #ai models #provider integration #model discovery #model tiers

Ready to run

npx skills add https://github.com/ViperJuice/treesitter-chunker --skill model-discovery-viperjuice

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-discovery
Source: https://github.com/ViperJuice/treesitter-chunker/tree/main/.ai-dev-kit/skills/model-discovery
Command: npx skills add https://github.com/ViperJuice/treesitter-chunker --skill model-discovery-viperjuice

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Fetch up-to-date AI provider models and categorize them into tiers for routing and usage across AI services.

Core Features & Use Cases

Fetch models from Anthropic, OpenAI, Gemini, and Ollama.
Classify models into fast/default/heavy tiers and detect new models for automatic updates.
Keep a centralized registry of known models to avoid hardcoding and support cross-skill references.

Quick Start

Run the model-discovery workflow to fetch the latest models and classify any new ones.

Frequently Asked Questions about model-discovery

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I fetch current AI models from multiple providers without hardcoding model IDs?▼

To fetch current AI models without hardcoding, use a fetch/cache mechanism that retrieves up-to-date model names from providers and checks them against a centralized known-model registry.

How do I classify AI models into fast, default, and heavy tiers for routing?▼

Classify AI models into fast, default, and heavy tiers by applying a tier-mapping configuration to the fetched model names, which guides categorization for routing and usage across AI services.

Can I automatically detect new AI models from Anthropic, OpenAI, Gemini, and Ollama?▼

Yes, you can automatically detect new AI models from Anthropic, OpenAI, Gemini, and Ollama by running a workflow that compares live provider data against a known-model registry to identify and classify new entries.

What is the best way to maintain a centralized registry of known AI models for cross-skill references?▼

Maintain a centralized registry of known AI models by using a discovery workflow that fetches live provider data, updates the registry automatically, and supports cross-skill references to avoid hardcoded model IDs.

Does this model discovery tool work with local Ollama models?▼

Yes, the model discovery tool works with local Ollama models alongside Anthropic, OpenAI, and Gemini, fetching their model names and classifying them into appropriate routing tiers.

Why does my AI workflow break when providers release new models?▼

AI workflows break when providers release new models because hardcoded model IDs become outdated, a problem solved by using a fetch/cache mechanism with a known-model registry that detects and classifies new models automatically.