Best fit
- 召集四方会议处理模糊决策、权衡取舍及继续/停止决策。当存在多个有效路径且需要在选择前进行结构化异议时使用。
affaan-m/ECC
council
召集四方会议处理模糊决策、权衡取舍及继续/停止决策。当存在多个有效路径且需要在选择前进行结构化异议时使用。
66Collecting
See how to use itView GitHub source
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/council"Automated source guide
Source checked Jul 28, 2026·Refresh due Oct 26, 2026
Reorganized from the pinned upstream SKILL.md
Turn council's source instructions into a guide you can follow
According to the pinned SKILL.md from affaan-m/ECC: 上下文中的Claude声音 怀疑论者子代理 实用主义者子代理 批评者子代理
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/council"Bring this context
- A concrete task that matches the documented purpose of council.
- The files, examples, or context the task depends on.
- Your constraints, target environment, and definition of done.
Expected outputs
- A result that follows the pinned council instructions.
- A concise record of assumptions, inputs used, and unresolved questions.
- A final check against the source workflow and relevant permission signals.
Key source sections
Read council through these 5 source sections
Sections are extracted automatically from the pinned SKILL.md and link back to the source.
何时使用
决策存在多个可行路径且无明显优胜者 需要明确权衡利弊 用户要求第二意见、异议或多角度分析 存在对话锚定效应的真实风险 通过对抗性挑战能优化"执行/放弃"决策
决策存在多个可行路径且无明显优胜者需要明确权衡利弊用户要求第二意见、异议或多角度分析
何时不使用
Review the “何时不使用” section in the pinned source before continuing.
Review and apply the “何时不使用” source section.
角色
三个外部声音应作为全新子代理启动，仅提供问题和相关上下文，而非完整对话历史。这是反锚定机制。
三个外部声音应作为全新子代理启动，仅提供问题和相关上下文，而非完整对话历史。这是反锚定机制。
工作流程
我们在决定什么？ 哪些约束条件重要？ 什么算成功？
我们在决定什么？哪些约束条件重要？什么算成功？
1. 提取真实问题
我们在决定什么？ 哪些约束条件重要？ 什么算成功？
我们在决定什么？哪些约束条件重要？什么算成功？
SkillSignal prompt templates
Provide the task, context, and acceptance criteria
These prompts were written by SkillSignal from the source structure; they are not upstream text.
Task-start prompt
Confirm source fit, inputs, and outputs before acting.
Use council to help me with: [specific task]. Context: [files, data, or background]. Constraints: [environment, scope, and prohibited actions]. Before acting, check the pinned SKILL.md and explain which sections apply, what inputs are still missing, and what you will deliver.
Source-guided execution
Make the Agent explicitly follow the key extracted sections.
Apply the pinned council source to [task]. Pay particular attention to these source sections: “何时使用”, “何时不使用”, “角色”, “工作流程”, “1. 提取真实问题”. Preserve the important decision at each step. Mark facts not covered by the source as “needs confirmation” instead of inventing them. Then verify the result against my acceptance criteria: [criteria].
Result-review prompt
Check omissions, permissions, and source drift before delivery.
Review the current council result: (1) does it satisfy the original task; (2) were any applicable steps or limits in the pinned SKILL.md missed; (3) did it perform any unauthorized file, command, network, or data action; and (4) which conclusions remain unverified? List issues first, then fix only what the source or user authorization supports.
Output checklist
Verify each item before delivery
The task matches the purpose documented in the SKILL.md.
The source section “何时使用” has been checked.
The source section “何时不使用” has been checked.
The source section “角色” has been checked.
The source section “工作流程” has been checked.
Inputs, constraints, and acceptance criteria are explicit.
Unverified facts, compatibility, and outcome claims are clearly marked.
Any file, command, network, or data action has been reviewed.
Choose a different workflow
When another Skill is the better fit
council
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailcouncil
曖昧な決定、トレードオフ、ゴー/ノーゴーの判断のために4つの声のカウンシルを召集します。複数の有効なパスが存在し、選択前に構造化された異議が必要な場合に使用します。
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
A separate implementation from coreyhaines31/marketingskills; compare its source, maintenance signals, and permission requirements.
Open source detailFAQ
What does council do?
上下文中的Claude声音 怀疑论者子代理 实用主义者子代理 批评者子代理
How do I start using council?
The catalog detected this source-specific install command: npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/council". Inspect the command and pinned source before running it.
Which Agent platforms does it declare?
No dedicated Agent platform is declared in the pinned source record.
Repository stars
234,327
Repository forks
35,711
Quality
66/100
Source repository last pushed
Quality breakdown
Based on traceable docs and repository signals; stars are not treated as quality.
Documentation20/30
Specificity14/25
Maintenance20/20
Trust signals12/25
Compare before choosing
Related Agent Skills and source variants
These links are selected from shared tasks, functions, stacks, platforms, and same-name variants. Compare the source owner, documentation, permissions, and maintenance signals.
council by affaan-m
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.
council by affaan-m
曖昧な決定、トレードオフ、ゴー/ノーゴーの判断のために4つの声のカウンシルを召集します。複数の有効なパスが存在し、選択前に構造化された異議が必要な場合に使用します。
ab-testing by coreyhaines31
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
churn-prevention by coreyhaines31
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o
design-intelligence by event4u-app
Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.
View original Skill.mdThis page is parsed directly from the repository SKILL.md without editorial rewriting. Collected: Jul 28, 2026 · about 1 min
顾问团
在模糊决策时召集四位顾问：
- 上下文中的Claude声音
- 怀疑论者子代理
- 实用主义者子代理
- 批评者子代理
这适用于模糊性下的决策制定，而非代码审查、实施规划或架构设计。
何时使用
在以下情况使用顾问团：
- 决策存在多个可行路径且无明显优胜者
- 需要明确权衡利弊
- 用户要求第二意见、异议或多角度分析
- 存在对话锚定效应的真实风险
- 通过对抗性挑战能优化"执行/放弃"决策
示例：
- 单一仓库 vs 多仓库
- 立即发布 vs 打磨后发布
- 功能开关 vs 全面上线
- 简化范围 vs 保持战略广度
何时不使用
| 不应使用顾问团的情况 | 应使用 |
|---|---|
| 验证输出是否正确 | santa-method |
| 将功能拆解为实施步骤 | planner |
| 设计系统架构 | architect |
| 审查代码中的错误或安全漏洞 | code-reviewer 或 santa-method |
| 直接的事实性问题 | 直接回答 |
| 明确的执行任务 | 直接执行 |
角色
| 声音 | 视角 |
|---|---|
| 架构师 | 正确性、可维护性、长期影响 |
| 怀疑论者 | 质疑前提、简化、打破假设 |
| 实用主义者 | 交付速度、用户影响、运营现实 |
| 批评者 | 边缘情况、下行风险、失败模式 |
三个外部声音应作为全新子代理启动，仅提供问题和相关上下文，而非完整对话历史。这是反锚定机制。
工作流程
1. 提取真实问题
将决策简化为一个明确提示：
- 我们在决定什么？
- 哪些约束条件重要？
- 什么算成功？
如果问题模糊，在召集顾问团前先提出一个澄清性问题。
2. 仅收集必要上下文
如果决策与代码库相关：
- 收集相关文件、代码片段、问题描述或指标
- 保持简洁
- 仅包含决策所需的上下文
如果决策是战略/通用性的：
- 除非能实质性改变答案，否则跳过仓库代码片段
3. 首先形成架构师立场
在阅读其他声音之前，写下：
- 你的初始立场
- 支持该立场的三个最强理由
- 首选路径的主要风险
先完成此步骤，以确保综合意见不会简单镜像外部声音。
4. 并行启动三个独立声音
每个子代理获得：
- 决策问题
- 必要的简洁上下文
- 严格角色定义
- 无多余对话历史
提示模板：
你是四声部决策委员会中的[角色]。
问题：
[决策问题]
背景：
[仅包含相关片段或约束条件]
回复格式：
1. 立场 — 1-2句话
2. 理由 — 3个简洁要点
3. 风险 — 你建议中最大的风险
4. 意外点 — 其他声部可能忽略的一个方面
直接明了，不要含糊。控制在300字以内。
角色重点：
- 怀疑论者：挑战框架、质疑假设、提出最简单的可信替代方案
- 实用主义者：优化速度、简单性和实际执行
- 批评者：揭示下行风险、边缘情况以及计划可能失败的原因
5. 通过偏见护栏进行综合
你既是参与者也是综合者，因此需遵循以下规则：
- 不得无故驳回外部观点，需说明理由
- 若外部声音改变了你的建议，需明确说明
- 始终包含最强烈的异议，即使你最终拒绝它
- 若两个声音一致反对你的初始立场，将其视为真实信号
- 在最终裁决前保持原始立场可见
6. 呈现简洁裁决
使用以下输出格式：
## 委员会：[简短决策标题]
**架构师：** [1-2句立场陈述]
[1行理由说明]
**怀疑论者：** [1-2句立场陈述]
[1行理由说明]
**实用主义者：** [1-2句立场陈述]
[1行理由说明]
**批评者：** [1-2句立场陈述]
[1行理由说明]
### 裁决
- **共识点：** [各方达成一致之处]
- **最大分歧：** [最重要的争议点]
- **前提检验：** [怀疑论者是否质疑了问题本身？]
- **建议方案：** [综合后的行动路径]
确保在手机屏幕上可快速浏览。
持久化规则
不要从此技能向 ~/.claude/notes 或其他隐藏路径写入临时笔记。
若顾问团实质性改变了建议：
- 使用
knowledge-ops将经验教训存储在正确的持久化位置 - 或使用
/save-session（若结果属于会话记忆） - 或直接更新相关的GitHub/Linear问题（若决策改变了当前执行事实）
仅在决策改变实际内容时进行持久化。
多轮跟进
默认为一轮。
若用户要求另一轮：
- 保持新问题聚焦
- 仅在必要时包含上一轮裁决
- 尽可能保持怀疑论者的"干净"状态以保留反锚定价值
反模式
- 将顾问团用于代码审查
- 在任务仅为实施工作时使用顾问团
- 向子代理提供完整对话记录
- 在最终裁决中隐藏分歧
- 无论重要性如何都持久化每个决策
相关技能
santa-method— 对抗性验证knowledge-ops— 正确持久化重要决策变更search-first— 在顾问团前收集外部参考资料（如需要）architecture-decision-records— 当决策成为长期系统策略时正式化结果
示例
问题：
我们现在应该以 alpha 版本发布 ECC 2.0，还是等到控制平面 UI 更完善后再发布？
可能的顾问团形态：
- 架构师推动结构完整性并避免混乱的界面
- 怀疑论者质疑UI是否真的是瓶颈因素
- 实用主义者询问在不损害信任的前提下现在可以交付什么
- 批评者关注支持负担、期望债务和上线混乱
价值不在于达成一致。价值在于在选择前让分歧清晰可见。
- Source repo
- affaan-m/ECC
- Skill path
- docs/zh-CN/skills/council/SKILL.md
- Commit SHA
- 4e973d3eaf92
- Repository license
- MIT
- Data collected