Stats
Actions
Tags
From ai-team-os
Participates in AI Team OS meetings with structured rounds: reads messages via MCP tools, analyzes discussions, sends responses following round-specific rules.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-team-os:meeting-participateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
当你被邀请参加一个会议时，按照以下流程参与讨论。会议是多 Agent 异步协作的核心机制。
当你被邀请参加一个会议时，按照以下流程参与讨论。会议是多 Agent 异步协作的核心机制。
你必须已经完成 OS 注册（os-register），拥有自己的 agent_id 和 agent_name。
进入会议后，先了解当前讨论状态：
使用 MCP tool: meeting_read_messages
参数:
meeting_id: <会议ID>
仔细阅读所有已有消息：
根据当前轮次发送消息：
使用 MCP tool: meeting_send_message
参数:
meeting_id: <会议ID>
agent_id: <你的agent_id>
agent_name: <你的名称>
content: <你的发言内容>
round_number: <当前轮次>
严格遵循以下讨论规则：
Round 1 — 各自观点
Round 2+ — 引用回应
meeting_read_messages）@agent_name 提到"..."，我认为...最后一轮 — 汇总
如果会议有多轮讨论：
round_numbernpx claudepluginhub cronusl-1141/ai-company --plugin ai-team-osFacilitates AI Team OS meetings using MCP tools: creates sessions, notifies agent participants, guides rounds (independent views then cited responses), monitors progress, summarizes consensus/divergences/actions, and concludes. For multi-agent discussions.
Conducts multi-round structured discussions among AI team roles (architect, UX, security) until consensus or max rounds. For converging diverse opinions into a single decision.
Convenes a simulated panel of colleague personas that research positions, debate across rounds, and converge on a synthesized conclusion. Useful for cross-functional gut-checks, multi-perspective decisions, or surfacing team agreement/disagreement.