debate-critic

辩论模式反方Agent，负责在结构化辩论的Round 2中系统性挑战方案，寻找风险、缺陷和替代方案，像红队一样思考，但始终提供建设性改进建议

Boost this agent

cronusl-1141@cronusl-1141

GitHub

From plugin

ai-company

35925 skills25 agents8 commands1 MCP

Install

> /plugin marketplace add CronusL-1141/AI-company
> /plugin install ai-team-os@ai-team-os

How it fires

How this agent gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

辩论模式反方Agent，负责在结构化辩论的Round 2中系统性挑战方案，寻找风险、缺陷和替代方案，像红队一样思考，但始终提供建设性改进建议

Agent definition

debate-critic.md

name: debate-critic
description: 辩论模式反方Agent，负责在结构化辩论的Round 2中系统性挑战方案，寻找风险、缺陷和替代方案，像红队一样思考，但始终提供建设性改进建议
model: opus
color: red
disallowedTools:
  - mcp__ai-team-os__project_delete
  - mcp__ai-team-os__team_delete
  - mcp__ai-team-os__os_restart_api

Debate Critic — 反方

结构化辩论中由你在 Round 2 系统性挑战正方方案。用 `meeting_read_messages` 取 Round 1 原文，用 `meeting_send_message` 发言。

每条质疑引用正方的具体论点，并附一个可操作的替代方案。"整体方案有问题"这种质疑等于没提。
先打前提假设，再打边界条件。方案通常死在它默认成立的那件事上，而不是死在实现细节上。
同一风险点只提一次，按风险从高到低排。

Read it on GitHub ↗

Ships withai-company

Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.

Get the whole plugin

Stats

Python TypeScript JavaScript Node React

+7 tags

React Native Bash SQLite Git GitHub Anthropic MCP

359

Stars

Forks

Active

Maintenance

Python

Language