multi-agent-brainstorming

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Multi-Agent Brainstorming (Structured Design Review)

多Agent头脑风暴(结构化设计评审)

Purpose

目的

Transform a single-agent design into a robust, review-validated design by simulating a formal peer-review process using multiple constrained agents.
This skill exists to:
  • surface hidden assumptions
  • identify failure modes early
  • validate non-functional constraints
  • stress-test designs before implementation
  • prevent idea swarm chaos
This is not parallel brainstorming. It is sequential design review with enforced roles.

将单Agent设计转化为经过评审验证的稳健设计 通过多个受限Agent模拟正式的同行评审流程。
此Skill的作用是:
  • 揭示隐藏假设
  • 尽早识别失效模式
  • 验证非功能约束
  • 在实施前对设计进行压力测试
  • 避免想法混乱
不是并行头脑风暴。 它是具有强制职责的顺序设计评审

Operating Model

运行模式

  • One agent designs.
  • Other agents review.
  • No agent may exceed its mandate.
  • Creativity is centralized; critique is distributed.
  • Decisions are explicit and logged.
The process is gated and terminates by design.

  • 一个Agent负责设计。
  • 其他Agent负责评审。
  • 任何Agent不得超出其职责范围。
  • 创意集中化;评审分散化。
  • 决策需明确记录。
该流程是门控式的,并且按设计要求终止

Agent Roles (Non-Negotiable)

Agent职责(不可协商)

Each agent operates under a hard scope limit.
每个Agent都在严格的范围限制下运作。

1️⃣ Primary Designer (Lead Agent)

1️⃣ 主设计师(Lead Agent)

Role:
  • Owns the design
  • Runs the standard
    brainstorming
    skill
  • Maintains the Decision Log
May:
  • Ask clarification questions
  • Propose designs and alternatives
  • Revise designs based on feedback
May NOT:
  • Self-approve the final design
  • Ignore reviewer objections
  • Invent requirements post-lock

职责:
  • 拥有设计所有权
  • 运行标准的
    brainstorming
    Skill
  • 维护决策日志
允许:
  • 提出澄清问题
  • 提出设计方案和替代方案
  • 根据反馈修订设计
禁止:
  • 自行批准最终设计
  • 忽略评审人员的异议
  • 在需求锁定后新增需求

2️⃣ Skeptic / Challenger Agent

2️⃣ 质疑者/挑战者Agent

Role:
  • Assume the design will fail
  • Identify weaknesses and risks
May:
  • Question assumptions
  • Identify edge cases
  • Highlight ambiguity or overconfidence
  • Flag YAGNI violations
May NOT:
  • Propose new features
  • Redesign the system
  • Offer alternative architectures
Prompting guidance:
“Assume this design fails in production. Why?”

职责:
  • 假设设计会失败
  • 识别弱点和风险
允许:
  • 质疑假设
  • 识别边缘情况
  • 突出模糊点或过度自信
  • 标记YAGNI违规情况
禁止:
  • 提出新功能
  • 重新设计系统
  • 提供替代架构
提示指导:
“假设此设计在生产环境中失败,原因是什么?”

3️⃣ Constraint Guardian Agent

3️⃣ 约束守护者Agent

Role:
  • Enforce non-functional and real-world constraints
Focus areas:
  • performance
  • scalability
  • reliability
  • security & privacy
  • maintainability
  • operational cost
May:
  • Reject designs that violate constraints
  • Request clarification of limits
May NOT:
  • Debate product goals
  • Suggest feature changes
  • Optimize beyond stated requirements

职责:
  • 执行非功能约束和现实世界约束
重点领域:
  • 性能
  • 可扩展性
  • 可靠性
  • 安全与隐私
  • 可维护性
  • 运营成本
允许:
  • 否决违反约束的设计
  • 请求明确限制条件
禁止:
  • 争论产品目标
  • 建议更改功能
  • 超出既定要求进行优化

4️⃣ User Advocate Agent

4️⃣ 用户代言人Agent

Role:
  • Represent the end user
Focus areas:
  • cognitive load
  • usability
  • clarity of flows
  • error handling from user perspective
  • mismatch between intent and experience
May:
  • Identify confusing or misleading aspects
  • Flag poor defaults or unclear behavior
May NOT:
  • Redesign architecture
  • Add features
  • Override stated user goals

职责:
  • 代表终端用户
重点领域:
  • 认知负荷
  • 可用性
  • 流程清晰度
  • 用户视角下的错误处理
  • 意图与体验不匹配
允许:
  • 识别易混淆或有误导性的方面
  • 标记不合理的默认设置或不清晰的行为
禁止:
  • 重新设计架构
  • 添加功能
  • 推翻既定的用户目标

5️⃣ Integrator / Arbiter Agent

5️⃣ 整合者/仲裁者Agent

Role:
  • Resolve conflicts
  • Finalize decisions
  • Enforce exit criteria
May:
  • Accept or reject objections
  • Require design revisions
  • Declare the design complete
May NOT:
  • Invent new ideas
  • Add requirements
  • Reopen locked decisions without cause

职责:
  • 解决冲突
  • 确定最终决策
  • 执行退出标准
允许:
  • 接受或否决异议
  • 要求修订设计
  • 宣布设计完成
禁止:
  • 提出新想法
  • 添加需求
  • 无正当理由重新开启已锁定的决策

The Process

流程

Phase 1 — Single-Agent Design

阶段1 — 单Agent设计

  1. Primary Designer runs the standard
    brainstorming
    skill
  2. Understanding Lock is completed and confirmed
  3. Initial design is produced
  4. Decision Log is started
No other agents participate yet.

  1. 主设计师运行标准的
    brainstorming
    Skill
  2. 完成并确认理解锁定
  3. 生成初始设计
  4. 启动决策日志
此时其他Agent不参与。

Phase 2 — Structured Review Loop

阶段2 — 结构化评审循环

Agents are invoked one at a time, in the following order:
  1. Skeptic / Challenger
  2. Constraint Guardian
  3. User Advocate
For each reviewer:
  • Feedback must be explicit and scoped
  • Objections must reference assumptions or decisions
  • No new features may be introduced
Primary Designer must:
  • Respond to each objection
  • Revise the design if required
  • Update the Decision Log

按以下顺序依次调用各Agent:
  1. 质疑者/挑战者
  2. 约束守护者
  3. 用户代言人
对于每个评审Agent:
  • 反馈必须明确且符合范围
  • 异议必须引用假设或决策
  • 不得引入新功能
主设计师必须:
  • 回应对每个异议
  • 根据需要修订设计
  • 更新决策日志

Phase 3 — Integration & Arbitration

阶段3 — 整合与仲裁

The Integrator / Arbiter reviews:
  • the final design
  • the Decision Log
  • unresolved objections
The Arbiter must explicitly decide:
  • which objections are accepted
  • which are rejected (with rationale)

整合者/仲裁者评审:
  • 最终设计
  • 决策日志
  • 未解决的异议
仲裁者必须明确决定:
  • 哪些异议被接受
  • 哪些被否决(并说明理由)

Decision Log (Mandatory Artifact)

决策日志(强制工件)

The Decision Log must record:
  • Decision made
  • Alternatives considered
  • Objections raised
  • Resolution and rationale
No design is considered valid without a completed log.

决策日志必须记录:
  • 做出的决策
  • 考虑过的替代方案
  • 提出的异议
  • 解决方案和理由
未完成日志的设计视为无效。

Exit Criteria (Hard Stop)

退出标准(硬性停止)

You may exit multi-agent brainstorming only when all are true:
  • Understanding Lock was completed
  • All reviewer agents have been invoked
  • All objections are resolved or explicitly rejected
  • Decision Log is complete
  • Arbiter has declared the design acceptable
If any criterion is unmet:
  • Continue review
  • Do NOT proceed to implementation If this skill was invoked by a routing or orchestration layer, you MUST report the final disposition explicitly as one of: APPROVED, REVISE, or REJECT, with a brief rationale.

只有当以下所有条件都满足时,才能退出多Agent头脑风暴:
  • 已完成理解锁定
  • 已调用所有评审Agent
  • 所有异议均已解决或被明确否决
  • 决策日志已完成
  • 仲裁者已宣布设计可接受
如果任何条件未满足:
  • 继续评审
  • 不得进入实施阶段 如果此Skill是由路由或编排层调用的,必须明确报告最终处置结果,为以下之一:APPROVED、REVISE或REJECT,并附上简要理由。

Failure Modes This Skill Prevents

此Skill可预防的失效模式

  • Idea swarm chaos
  • Hallucinated consensus
  • Overconfident single-agent designs
  • Hidden assumptions
  • Premature implementation
  • Endless debate

  • 想法混乱
  • 幻觉共识
  • 过度自信的单Agent设计
  • 隐藏假设
  • 过早实施
  • 无休止的争论

Key Principles

核心原则

  • One designer, many reviewers
  • Creativity is centralized
  • Critique is constrained
  • Decisions are explicit
  • Process must terminate

  • 一位设计师,多位评审者
  • 创意集中化
  • 评审受约束
  • 决策明确
  • 流程必须终止

Final Reminder

最终提醒

This skill exists to answer one question with confidence:
“If this design fails, did we do everything reasonable to catch it early?”
If the answer is unclear, do not exit this skill.
此Skill的存在是为了自信地回答一个问题:
“如果这个设计失败了,我们是否已采取一切合理措施尽早发现问题?”
如果答案不明确,请勿退出此Skill