Council Consultation Ensemble

•
8
•

Leverages a multi-model ensemble to provide diverse, parallel insights from GPT, Gemini, and Claude for complex problem-solving.

The ask-council skill empowers Claude Code users to seek consensus or diverse perspectives by querying three major AI models simultaneously. By running gpt-5.2-pro, gemini-3-pro-preview, and claude-opus-4-5-20251101 in parallel, it eliminates single-model bias and provides a comprehensive 'council' of opinions. This is particularly useful for high-stakes architectural decisions, debugging elusive edge cases, or validating complex logic where a single viewpoint might miss critical nuances during the development process.

主要功能

01Ensemble-based decision making to reduce model bias
02Parallel execution across three top-tier LLMs
03Integration with GPT-5.2, Gemini 3 Pro, and Claude Opus
04Customizable model selection for specialized domain queries
05Automated polling and result relay for seamless workflows
068 GitHub stars

使用场景

01Brainstorming creative solutions for unique technical challenges with diverse AI viewpoints
02Validating critical system architecture designs through multi-model consensus
03Resolving complex logic disagreements during code review or debugging
name description
ask-council
Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.

Consult multiple models in parallel about: $ARGUMENTS


Use the Task tool with subagent_type='consultant:consultant'. Specify multi-model consultation.

Default models (use all 3 unless user specifies otherwise):

  • gpt-5.2-pro
  • gemini/gemini-3-pro-preview
  • claude-opus-4-5-20251101

The agent handles parallel execution, polling, and output relay.