anbeime/skill / skills/multi-agent-meeting/multi-agent-meeting
multi-agent-meeting
Verified项目管理专家与产品经理在做项目决策、技术评审或商业策略制定时,当需要多视角碰撞以打破思维局限,请用此技能模拟多智能体真实会议辩论,一键生成包含决策结论、核心论据与风险提示的完整会议记录,让复杂决策高效落地!
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.6 KB |
| assets/meeting-templates/customer-insight-analysis.md | markdown | 6.2 KB |
| assets/meeting-templates/product-feature-review.md | markdown | 6.1 KB |
| assets/meeting-templates/product-pricing-strategy.md | markdown | 1.8 KB |
| assets/meeting-templates/project-risk-assessment.md | markdown | 2.0 KB |
| assets/meeting-templates/tech-architecture-decision.md | markdown | 1.8 KB |
| references/agent-roles.md | markdown | 5.6 KB |
| references/meeting-record-format.md | markdown | 7.0 KB |
assets/meeting-templates/project-risk-assessment.md
View on GitHub# 项目风险评估会议模板
## 会议类型
项目风险评估会议
## 适用场景
- 新项目立项评估
- 项目阶段性风险评估
- 项目变更影响评估
- 项目终止决策
- 项目优先级排序
## 推荐角色组合
### 最小组合(4人)
1. **项目经理**: 主持讨论,从项目管理角度评估
2. **技术专家**: 评估技术可行性风险
3. **业务负责人**: 评估业务价值和市场风险
4. **法务顾问**: 评估合规和法律风险
### 完整组合(6人)
1. **项目经理**: 进度、资源、风险管控
2. **技术专家**: 技术实现和架构风险
3. **运营专家**: 用户和运营风险
4. **法务顾问**: 合规和知识产权风险
5. **财务顾问**: 成本和预算风险
6. **部门负责人**: 资源支持和战略决策
## 典型讨论点
### 技术风险
- 技术选型和架构风险
- 团队能力和经验不足
- 第三方依赖风险
- 技术债务积累
### 运营风险
- 用户接受度和市场风险
- 运营能力和资源不足
- 数据安全和隐私风险
- 监管政策变化
### 项目风险
- 时间延期风险
- 成本超支风险
- 人员流失风险
- 需求变更频繁
### 商业风险
- 竞争对手动作
- 市场需求变化
- 收入不达预期
- 投资回报率低
## 风险评估维度
| 维度 | 评估标准 |
|------|---------|
| **可能性** | 极低/低/中/高/极高 |
| **影响程度** | 极小/小/中/大/极大 |
| **可发现性** | 易于发现/难以及时发现 |
| **可控性** | 完全可控/部分可控/难以控制 |
## 典型决策结果类型
- **绿灯**: 风险可控,建议启动项目
- **黄灯**: 需制定风险缓解措施后方可启动
- **红灯**: 风险过高,建议暂缓或取消
- **调整**: 需要修改项目范围或目标后再评估
- **分阶段**: 分阶段实施,降低整体风险
## 示例会议主题
- 新项目立项的风险评估
- 核心系统重构项目可行性评估
- 海外市场拓展项目风险评估
- 大型技术平台建设项目风险评估
- AI产品开发项目风险评估
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |