multi-model-debate-skill
Runs blinded, anti-groupthink debates across Claude Code and other model voices.
Runs blinded, anti-groupthink debates across Claude Code and other model voices.
multi-model-debate-skill runs a live panel in which each model argues a distinct lens instead of repeating the same safe answer. Round one is blinded, genuine objections are required before agreement, and a devil’s-advocate control can challenge premature consensus. Opus moderates the running session while Grok, Codex, DeepSeek, or other configured backends supply additional voices; the lineup can be chosen per debate.
Resource types
Use cases
Platforms
Runtime
Read Telegram chats, parse channels, and download voice notes without sending messages.
Pressure-test decisions with debate, incident response, and improvement modes.
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Read context and send WeChat replies through Claude on Windows.
Read, search, and download IMAP email through an agent-friendly CLI skill.