cyberneticlibrary

Compare thinking across multiple LLMs

llm-councilskillsetup L22,280
rohitg00/pro-workflow
What it does

Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Provider config from env (OPENAI/ANTHROPIC/FIREWORKS/OPENROUTER/custom OpenAI-compatible base URL). Persists transcript to a wiki page when --wiki <slug> is passed. Use when the user wants multiple AI perspectives, consensus-building, or the "LLM Council" approach for high-stakes reviews, plan critique, or contested learning rules.

Best for

Resolving contested decisions via multi-LLM deliberation with ranked cross-model voting and synthesis.

Inputs
  • · node $SKILL_ROOT/scripts/council.js run "<query>" [--models id1,id2,id3] [--chairman id] [--provider <name>] [--wiki <slug>] node $SKILL_ROOT/scripts/council.js providers node $SKILL_ROOT/scripts/coun
  • · /wiki council agent-memory "should we adopt episodic memory in our agents?"
Outputs
  • · Consensus recommendation
  • · Ranked LLM votes
Requires
  • · OpenAI-compatible API
  • · LLM provider (Anthropic/OpenAI/Fireworks)
Preconditions

API credentials, valid request format

Failure modes

Invalid API key, malformed payload, rate limiting, schema mismatch

Trust signals
  • · Testing guidance included