Dbs Chatroom
Run a moderated multi-expert chatroom on a topic—recommended or user-picked personas—with parallel agents and a closing judge summary.
Overview
dbs-chatroom is a journey-wide agent skill that simulates a multi-expert chatroom on your topic—usable whenever a solo builder needs structured perspectives before committing.
Install
npx skills add https://github.com/dontbesilent2025/dbskill --skill dbs-chatroomWhat is this skill?
- Four-step workflow: detect mode, recommend 3–5 experts, parallel Agent-tool dialogue, Claude judge wrap-up
- Supports user-specified experts via /dbs-chatroom Name1 Name2 or auto-recommendation from the topic
- Hard gate: stop after recommendations until user confirms 确认 or 开始
- Per-expert prompt template with thinking methods, honesty rules, and ~200-character style constraint
- Judge section scores insight quality, missing angles, and 2–3 actionable takeaways
- 4-step workflow
- Recommends 3–5 experts
- Judge delivers 2–3 actionable suggestions
Adoption & trust: 6.1k installs on skills.sh; 6.3k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are wrestling with a fuzzy decision and one assistant voice keeps flattening tradeoffs you need from distinct expert frameworks.
Who is it for?
Indie founders exploring strategy, psychology, or product bets who want named thinker lenses without booking a live panel.
Skip if: Tasks needing verified citations, legal/medical decisions, or hands-on code generation without a discussion phase.
When should I use this skill?
/dbs-chatroom、/定向聊天室、「定向聊天室」—topic-based directed chatroom with recommended or user-specified experts.
What do I get? / Deliverables
You get parallel expert responses plus a judge summary with blind-spot coverage and 2–3 concrete actions to take next.
- Formatted multi-expert transcript
- Claude judge summary with quality critique
- 2–3 actionable recommendations
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Frame a market entry question and let recommended investors and psychologists argue premises before you prototype.
Stress-test MVP scope by pitting frugal operators against growth-oriented advisors under a judge recap.
Debate build-vs-buy for a feature with architects who disagree on complexity and incentives.
Explore positioning angles with contrasting marketing minds before picking a launch narrative.
Shape a newsletter thesis by running named thinkers in parallel, then extracting actionable editorial lines.
How it compares
Facilitated multi-agent panel skill—not a single-shot brainstorm template or an MCP research crawler.
Common Questions / FAQ
Who is dbs-chatroom for?
Solo builders and creators who want moderated, multi-persona dialogue in Chinese or mixed contexts before acting on a topic.
When should I use dbs-chatroom?
In Idea for opportunity framing, Validate to stress-test scope, Build for architecture disagreements, Grow for positioning—or anytime you invoke /dbs-chatroom with a topic.
Is dbs-chatroom safe to install?
It orchestrates parallel agents on your topic; review Prism Security Audits and avoid piping secrets into simulated expert sessions.
SKILL.md
READMESKILL.md - Dbs Chatroom
# dbs-chatroom：定向聊天室 你是定向聊天室的主持人。根据话题推荐或接受用户指定的专家，模拟多角色对话。 --- ## 工作流程 ### 第一步：检测模式 **情况 A：用户指定了人物** - 格式：`/dbs-chatroom [人物1] [人物2] [人物3]` - 示例：`/dbs-chatroom 查理·芒格 丹尼尔·卡尼曼 雷·达里奥` - 动作：直接跳到第三步 **情况 B：用户未指定人物** - 格式：`/dbs-chatroom`（或其他触发词） - 动作：进入第二步 --- ### 第二步：推荐人物（仅情况 B） 分析话题，推荐 3-5 位专家： ``` 🎯 根据话题「{话题总结}」，推荐以下专家： 1. {人物1}：{核心观点一句话} 2. {人物2}：{核心观点一句话} 3. {人物3}：{核心观点一句话} 确认后启动聊天室。 ``` **停在这里，等用户回复「确认」「开始」或调整人选。不要继续执行。** --- ### 第三步：生成对话（使用 Agent tool） 确认人物后，使用 Agent tool 并行调用多个专家。每个专家一个独立 Agent。 #### Prompt 模板结构 为每位专家生成如下结构的 prompt： ``` 你是 {专家名字}。 话题：{用户的话题} 思考方式： 1. {该专家的核心思维方法1} 2. {该专家的核心思维方法2} 3. {该专家的核心思维方法3} 诚实规则： - 如果不确定，承认不确定 - 避免套公式，给出真实洞察 - 可以质疑话题本身的前提 说话：{该专家的说话风格}。200字左右。 请从你的视角回应这个话题。 ``` #### 动态生成专家 prompt 的要点 1. **思考方式**：提炼该专家最核心的 3 个思维方法 - 例如芒格：「逆向思考」「多元思维模型」「激励机制分析」 - 例如阿德勒：「目的论视角」「社会情境分析」「勇气心理学」 2. **诚实规则**：统一使用上述模板，确保专家不会强行给答案 3. **说话风格**：一句话概括该专家的表达特点 - 例如芒格：「直接、犀利、用商业案例说话」 - 例如阿德勒：「温和但犀利、用生活场景举例、强调行动」 4. **200字左右**：明确要求，确保输出有实质内容 #### 输出格式 并行调用所有 Agent 后，按以下格式整理输出： ``` 💬 **{专家1}**： {Agent 返回的内容} 💬 **{专家2}**： {Agent 返回的内容} 💬 **{专家3}**： {Agent 返回的内容} ``` --- ### 第四步：判官总结 所有专家发言后，你（Claude）作为判官发言： ``` 🎯 **Claude 判官总结** **讨论质量**： - 有真洞察吗？（超出常识的观点） - 有交锋吗？（不同观点的碰撞） **补盲区**： - 所有人都没提到但重要的视角 **可执行建议**： - 用户可以带走的具体判断 - 可执行的行动建议（2-3 条） ``` --- ## 注意事项 1. **必须使用 Agent tool**：每个专家一个独立 Agent，并行调用 2. **推荐模式必须等确认**：不要自作主张直接启动对话 3. **判官总结必须有**：这是 skill 的核心价值 4. **200字左右**：每个专家的回复要有实质内容，不能太短 5. **动态生成 prompt**：根据专家特点定制思考方式和说话风格