Rank models by APEX ELO scores and write a YAML inventory.
npx skills add https://github.com/dzackgarza/ai --skill model-selection-dzackgarza
Please help me install this Agent Skill. Skill: model-selection Source: https://github.com/dzackgarza/ai/tree/main/opencode/skills/model-selection Command: npx skills add https://github.com/dzackgarza/ai --skill model-selection-dzackgarza
Selecting the right large language model for a given task can be difficult when multiple providers and dynamic model inventories exist. This Skill automates the choice by ranking models using real-world notes like APEX ELO scores and available context.
Run the provider-models fetch script to refresh the inventory and then review provider-models.yaml.
High-intent search queries and answers about installing and using this skill.
To select the best LLM, rank models using APEX ELO scores and available context, then map them to tiers like S+ or A− to match model capabilities with your task requirements.
APEX ELO scores are real-world performance ratings used to rank large language models into tiered categories such as S+, S, A+, A−, B+, B, and C, helping you identify optimal models for specific tasks.
You map providers by pulling model lists, cross-referencing them with models.dev data for enrichment, and writing a provider-grouped YAML inventory output that maps models to APEX-based tiers.
Yes, you can generate a YAML inventory by fetching provider model lists, enriching them with models.dev data, and writing a structured YAML file suitable for operational loading into agents.
Find a coding LLM by filtering an enriched model inventory using APEX ELO scores and available context data to select models that meet your strict context window requirements for coding tasks.
pwwangRank genes by differential expression to identify enriched pathways in single-cell data.
kriscendobotRoutes AI agent tasks to appropriate model tiers with fallback logic.
LidianAIDiscover compatible endpoints and consume them with structured JSON parameters.
agentic-inBenchmark LLM performance across 60+ academic benchmarks with reproducible scoring.
