What problem does it solve? Choosing between AI models for a task usually relies on guesswork. This Skill runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side and reports latency, token usage, cost, and optional quality scores so model selection is based on measured data. ## Core Features & Use Cases - Cross-model execution: Runs one prompt through multiple providers and compares speed, cost, and tokens in a single table. - LLM quality judge: Optionally scores each model's output 0-10 using Anthropic's Claude as a tiebreaker, adding roughly $0.05 per run. - Auth preflight: A dry-run shows which providers are authenticated before any paid API calls are made. - Use Case: You want to know whether GPT or Gemini handles your /ship review prompt better. Run the benchmark against that skill's SKILL.md, enable the judge, and save the JSON result as a baseline to detect quality drift after provider model updates. ## Quick Start Ask the assistant to run a cross-model benchmark comparing Claude, GPT, and Gemini on one of your gstack skills. ## Quick Start Say: run a cross-model benchmark on my ship skill with the quality judge enabled.
