council

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Council

Use this skill when the user wants a multi-perspective council rather than a single answer. Good triggers include:

"run a council on this"
"get multiple perspectives"
"debate this decision"
"stress test this plan"
architecture, product, strategy, debugging, risk, or founder tradeoffs

$ARGUMENTS

is non-empty, treat it as the problem statement. Otherwise ask the user for the question to deliberate on.

当用户需要多视角委员会的分析而非单一答案时，使用此技能。适用触发场景包括：

"针对此事运行一个委员会"
"获取多种观点"
"就该决策展开辩论"
"对该计划进行压力测试"
架构、产品、战略、调试、风险或创始人层面的权衡事项

若

$ARGUMENTS

非空，则将其视为问题陈述。否则请用户提供需要审议的问题。

First Step

第一步

Read only the references you need:

```
references/profiles.yaml
```
for panel selection
```
references/protocol.md
```
for orchestration
```
references/verdict-template.md
```
for final output shape
```
references/personas/<member>.md
```
only for the members you actually select

仅阅读所需的参考资料：

```
references/profiles.yaml
```
用于选择委员会成员
```
references/protocol.md
```
用于流程编排
```
references/verdict-template.md
```
用于最终输出格式
```
references/personas/<member>.md
```
仅用于你实际选中的成员资料

Defaults

默认设置

Prefer 3 members unless the user asks for a full panel or the problem is unusually ambiguous.
Default to
```
classic
```
+
```
architecture
```
if nothing else is specified.
Keep the final verdict compact unless the user asks to see the rounds.

除非用户要求完整委员会或问题异常模糊，否则优先选择3名成员。
若无其他指定，默认使用
```
classic
```
+
```
architecture
```
组合。
除非用户要求查看各轮内容，否则最终结论需保持简洁。

Workflow

工作流程

1. Resolve The Panel

1. 确定委员会成员

Honor, in order:

explicit
```
--members
```
explicit
```
--triad
```
explicit
```
--profile
```
keyword triad match
fallback default

按以下优先级执行：

明确指定的
```
--members
```
参数
明确指定的
```
--triad
```
参数
明确指定的
```
--profile
```
参数
关键词匹配的三人组
回退至默认设置

2. Round 1: Independent Analysis

2. 第一轮：独立分析

Run each selected member independently.
Keep round 1 blind-first: each member sees only the problem statement and their own persona text.
Ask for a compact standalone analysis that ends with a clear verdict, confidence, and where the member may be wrong.

Preferred orchestration:

If the host supports explicit subagents or forked contexts, use one independent delegate per selected member.
In Codex, prefer
```
spawn_agent
```
, then
```
send_input
```
and
```
wait_agent
```
.
In Amp, prefer one
```
oracle
```
call per selected member.
In Claude Code, use parallel or forked agent contexts when they are available. If they are not easy to access, keep the protocol in the main session and separate the member outputs clearly.

Suggested round 1 packet:

text

You are operating as one member of a structured council.

Persona:
{persona}

Problem:
{problem}

Produce a compact standalone analysis.
End with a clear verdict, confidence, and where you may be wrong.
Do not anticipate the other members.

让每位选中的成员独立开展分析。
第一轮初始阶段保持盲态：每位成员仅能查看问题陈述和自身角色设定文本。
要求成员提供简洁的独立分析，结尾需包含明确结论、置信度以及自身可能存在的疏漏点。

推荐编排方式：

若宿主支持明确的子代理或分叉上下文，可为每位选中的成员分配一个独立代理。
在Codex中，优先使用
```
spawn_agent
```
，随后调用
```
send_input
```
和
```
wait_agent
```
。
在Amp中，优先为每位成员调用一次
```
oracle
```
。
在Claude Code中，若支持并行或分叉代理上下文则使用该方式；若不易实现，则在主会话中遵循流程，清晰区分各成员的输出内容。

第一轮建议数据包：

text

You are operating as one member of a structured council.

Persona:
{persona}

Problem:
{problem}

Produce a compact standalone analysis.
End with a clear verdict, confidence, and where you may be wrong.
Do not anticipate the other members.

3. Round 2: Cross-Examination

3. 第二轮：交叉质询

Share the round 1 outputs with each member.
Ask each member to:
- name the position they most disagree with and why
- name one insight that strengthened their thinking
- say whether anything changed
- restate their position after the exchange
Prefer sequential execution so later responses can react to earlier disagreements.

If another delegate pass would be disproportionate, run the cross-exam locally and disclose that choice.

Suggested round 2 packet:

text

Here are the other council members' round 1 analyses:

{peer_outputs}

Respond to all of the following:
1. Which member do you most disagree with, and why?
2. Which member strengthened your thinking, and how?
3. What changed, if anything?
4. Restate your position after the exchange.

Keep it compact and engage at least two members by name.

将第一轮的输出内容共享给每位成员。
要求每位成员：
- 指出最不同意的观点及其原因
- 指出一个强化自身思路的见解
- 说明是否有任何观点变化
- 阐述交流后的立场
优先采用顺序执行，以便后续回应能针对前期分歧作出反应。

若再次委托代理执行过于繁琐，可在本地完成交叉质询并告知用户此选择。

第二轮建议数据包：

text

Here are the other council members' round 1 analyses:

{peer_outputs}

Respond to all of the following:
1. Which member do you most disagree with, and why?
2. Which member strengthened your thinking, and how?
3. What changed, if anything?
4. Restate your position after the exchange.

Keep it compact and engage at least two members by name.

4. Round 3: Final Position

4. 第三轮：最终立场

Ask for a short final stance only.
No new arguments unless a host limitation forces a condensed fallback.
Socrates may ask one final question before stating a position.

仅要求成员提供简短的最终立场。
除非宿主限制导致需采用简化回退方案，否则不提出新论点。
Socrates可在陈述立场前提出最后一个问题。

5. Synthesis

5. 综合总结

Use
```
references/verdict-template.md
```
.
Default to the final verdict only.
If the user asks to show rounds, include concise round summaries after the verdict.

使用
```
references/verdict-template.md
```
模板。
默认仅输出最终结论。
若用户要求查看各轮内容，则在结论后添加各轮的简洁摘要。

Fallback Mode

回退模式

If the host cannot cleanly support multi-round orchestration, or the full protocol would be disproportionate:

simulate round 1 as clearly separated persona sections
simulate round 2 as explicit cross-exam sections
simulate round 3 as final positions
disclose that you used the single-agent fallback

若宿主无法清晰支持多轮编排，或完整流程过于繁琐：

模拟第一轮为清晰分隔的角色板块
模拟第二轮为明确的交叉质询板块
模拟第三轮为最终立场板块
告知用户使用了单代理回退模式

Guardrails

约束规则

Do not force consensus.
If the panel converges too quickly, run one counterfactual pass.
Prefer substance over theater: the council should improve the answer, not just decorate it.

不强制达成共识。
若委员会成员观点过快趋同，则执行一次反事实验证。
优先注重实质内容而非形式：委员会应优化答案，而非仅作表面装饰。