Council by danielmiessler/personal_ai_infrastructure
npx skills add https://github.com/danielmiessler/personal_ai_infrastructure --skill Council执行前,请检查用户自定义配置于: ~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/Council/
如果此目录存在,则加载并应用其中找到的任何 PREFERENCES.md、配置或资源。这些将覆盖默认行为。如果目录不存在,则使用技能默认设置。
多智能体辩论系统,其中专业化的智能体通过多轮讨论议题,回应彼此的观点,并通过智力摩擦揭示洞见。
与 RedTeam 的主要区别: Council 是协作对抗性的(通过辩论寻找最佳路径),而 RedTeam 是纯粹对抗性的(攻击想法)。Council 生成可见的对话记录;RedTeam 生成强化论证和反驳论证。
执行工作流时,请同时执行以下两项操作:
发送语音通知:
curl -s -X POST http://localhost:8888/notify
-H "Content-Type: application/json"
-d '{"message": "Running the WORKFLOWNAME workflow from the Council skill"}'
> /dev/null 2>&1 &
输出文本通知:
Running the WorkflowName workflow from the Council skill...
完整文档: ~/.claude/skills/CORE/SkillNotifications.md
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
根据请求路由到相应的工作流。
执行工作流时,直接输出此通知:
Running the **WorkflowName** workflow from the **Council** skill...
| 触发条件 | 工作流 |
|---|---|
| 完整结构化辩论(3轮,可见记录) | Workflows/Debate.md |
| 快速共识检查(1轮,快速) | Workflows/Quick.md |
| 纯粹对抗性分析 | RedTeam 技能 |
| 工作流 | 目的 | 轮数 | 输出 |
|---|---|---|---|
| DEBATE | 完整结构化讨论 | 3 | 完整记录 + 综合结论 |
| QUICK | 快速视角检查 | 1 | 仅初始立场 |
| 文件 | 内容 |
|---|---|
CouncilMembers.md | 智能体角色、视角、语音映射 |
RoundStructure.md | 三轮辩论结构和时序 |
OutputFormat.md | 记录格式模板 |
起源: 最佳决策源于不同视角间的相互挑战。不仅仅是收集意见,而是专家们对彼此实际观点进行回应的真正智力摩擦。
速度: 轮内并行执行,轮间顺序执行。一个包含 4 个智能体的 3 轮辩论 = 12 次智能体调用,但只有 3 次顺序等待。通常在 30-90 秒内完成。
"Council: Should we use WebSockets or SSE?"
-> 调用 DEBATE 工作流 -> 3 轮记录
"Quick council check: Is this API design reasonable?"
-> 调用 QUICK 工作流 -> 快速视角
"Council with security: Evaluate this auth approach"
-> 添加 Security 智能体的 DEBATE
与以下配合良好:
最后更新: 2025-12-20
每周安装数
63
仓库
GitHub 星标数
9.7K
首次出现
2026年1月23日
安全审计
安装于
codex51
gemini-cli50
opencode49
claude-code47
github-copilot46
amp41
Before executing, check for user customizations at: ~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/Council/
If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.
Multi-agent debate system where specialized agents discuss topics in rounds, respond to each other's points, and surface insights through intellectual friction.
Key Differentiator from RedTeam: Council is collaborative-adversarial (debate to find best path), while RedTeam is purely adversarial (attack the idea). Council produces visible conversation transcripts; RedTeam produces steelman + counter-argument.
When executing a workflow, do BOTH:
Send voice notification :
curl -s -X POST http://localhost:8888/notify \
-H "Content-Type: application/json" \
-d '{"message": "Running the WORKFLOWNAME workflow from the Council skill"}' \
> /dev/null 2>&1 &
Output text notification :
Running the **WorkflowName** workflow from the **Council** skill...
Full documentation: ~/.claude/skills/CORE/SkillNotifications.md
Route to the appropriate workflow based on the request.
When executing a workflow, output this notification directly:
Running the **WorkflowName** workflow from the **Council** skill...
| Trigger | Workflow |
|---|---|
| Full structured debate (3 rounds, visible transcript) | Workflows/Debate.md |
| Quick consensus check (1 round, fast) | Workflows/Quick.md |
| Pure adversarial analysis | RedTeam skill |
| Workflow | Purpose | Rounds | Output |
|---|---|---|---|
| DEBATE | Full structured discussion | 3 | Complete transcript + synthesis |
| QUICK | Fast perspective check | 1 | Initial positions only |
| File | Content |
|---|---|
CouncilMembers.md | Agent roles, perspectives, voice mapping |
RoundStructure.md | Three-round debate structure and timing |
OutputFormat.md | Transcript format templates |
Origin: Best decisions emerge from diverse perspectives challenging each other. Not just collecting opinions - genuine intellectual friction where experts respond to each other's actual points.
Speed: Parallel execution within rounds, sequential between rounds. A 3-round debate of 4 agents = 12 agent calls but only 3 sequential waits. Complete in 30-90 seconds.
"Council: Should we use WebSockets or SSE?"
-> Invokes DEBATE workflow -> 3-round transcript
"Quick council check: Is this API design reasonable?"
-> Invokes QUICK workflow -> Fast perspectives
"Council with security: Evaluate this auth approach"
-> DEBATE with Security agent added
Works well with:
Last Updated: 2025-12-20
Weekly Installs
63
Repository
GitHub Stars
9.7K
First Seen
Jan 23, 2026
Security Audits
Gen Agent Trust HubWarnSocketPassSnykPass
Installed on
codex51
gemini-cli50
opencode49
claude-code47
github-copilot46
amp41
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
69,600 周安装
Microsoft Teams自动化指南:通过Rube MCP实现频道消息、聊天与会议管理
72 周安装
Electrobun 最佳实践:TypeScript + Bun 跨平台桌面应用开发指南
72 周安装
ATXP Memory:AI代理记忆管理工具 - 云端备份与本地向量搜索
72 周安装
Brave Search Spellcheck API:智能拼写检查与查询纠正,提升搜索准确性
72 周安装
Amazon竞品分析器 - 自动化抓取ASIN数据,深度分析竞争对手定价、规格与评论
72 周安装
qa-use:AI驱动开发工作流的端到端测试与浏览器自动化工具
72 周安装