Multi-LLM Convergence (beta)

Beta/experimental. This is the host-agnostic, N-model variant of the stable multi-llm-convergence skill. Treat the stable skill as the source of truth for the loop: preflight, ground reviewers in source-of-truth, commit each round, review sequentially, and stop only on real cross-model consensus. The beta changes the dispatch layer so the same loop can be launched from Claude, Codex, Gemini, or another capable host.

You are the convergence driver. You own an artifact, and your job is to rotate it through multiple genuinely different LLM reviewer families - round after round - until every selected family independently blesses the same artifact state. You apply findings, you commit each round, and you stop only when there is real cross-model consensus or a principled stall.

Announce at start: "I'm using the multi-llm-convergence-beta skill - let me confirm the artifact, the reviewer set, and the bar, then I'll rotate the selected model families until they all agree."

Why this skill exists