skills.rest
EndUser123
EndUser123COMMUNITY
Explore all skills by this author →
GitHub

ai_models

Discover and analyze LLM models from provider APIs with local judge results.

Updated Apr 26, 2026
Search Tags:#benchmarking#ai-models#gap-analysis#leaderboard#model-discovery#provider-apis
One-click install
npx skills add https://github.com/EndUser123/cc-marketplace --skill ai-models-enduser123
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai_models
Source: https://github.com/EndUser123/cc-marketplace/tree/main/plugins/cc-skills-ai-api/skills/ai-models
Command: npx skills add https://github.com/EndUser123/cc-marketplace --skill ai-models-enduser123

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Teams need a single view into available LLM models, a way to benchmark them locally, and actionable insights to guide procurement and experimentation.

Core Features & Use Cases

  • Provider API discovery for multiple providers (OpenRouter, Chutes, Groq, Mistral) and future additions.
  • Internet research integration to surface benchmarks, comparisons, and recommendations.
  • Local performance analysis via a leaderboard and gap analysis to prioritize testing.
  • Use Case: A product team wants to select a model for a new feature and iteratively compare models using judge_results data and external benchmarks.

Quick Start

Run /ai-models discover --free-only to list available models and their performance profiles.

Frequently Asked Questions about ai_models

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

FAQPage Schema
How do I benchmark available LLM models from provider APIs?▼

You can benchmark available LLM models by running provider API discovery to list models, testing them locally, and storing the performance outputs in judge_results for comparative analysis.

What's the best way to discover and compare models across providers like OpenRouter and Groq?▼

Discover and compare models by orchestrating provider API discovery across multiple providers, integrating internet research for external benchmarks, and analyzing local leaderboard data for gap identification.

Can I filter model discovery to only show free LLM models?▼

Yes, you can filter model discovery to show only free models by running the discover command with the free-only flag to list available models and their performance profiles.

How does gap analysis help prioritize which AI models to test next?▼

Gap analysis identifies untested areas by comparing local judge_results and external benchmarks, helping teams prioritize future testing and make data-driven model selection decisions for coding and reasoning tasks.

Does this model benchmarking approach work for both coding and reasoning tasks?▼

Yes, the benchmarking and gap analysis capability applies to teams needing decision support for model selection across specific tasks including coding, reasoning, and analysis.

Why use a unified leaderboard instead of checking individual provider APIs manually?▼

A unified leaderboard provides a single view into available models, local judge_results, and external research, enabling faster model discovery and actionable insights for procurement than manual API checks.

Related Skills

Explore More Software Engineering Skills→
KarlinskySKarlinskyS

hermes-agent-setup

Configure Hermes Agent CLI and gateway environments with providers, models, tools, and voice integrations.

Community
Intermediate
tractorjuicetractorjuice
2.1k

arckit-wardley

Generate Wardley Maps for strategic landscape and component evolution analysis.

Community
Advanced
ovachieverovachiever
52

lm-evaluation-harness

Evaluate language models across 60+ academic benchmarks with lm-evaluation-harness.

Community
Advanced
ElwinLiuElwinLiu

skill-installer

Install Codex skills from curated lists or GitHub repos into CODEX_HOME/skills.

Community
Intermediate