ljg-roundtable
Skill280 starsChanged 9 months agoMITView on GitHub
Structured roundtable discussion framework with a truth-seeking moderator who invites representative figures for dialectical debate on any topic. Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic through multi-perspective structured debate.
3 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- ZhouYinLong-lab/Dog-Skillstheir own version, first seen Nov 8, 2026
- lijigang/ljg-skillsedited, first seen Oct 6, 2026
- zizhenchen47-oss/claude-skillsedited, first seen Jun 4, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- lijigang/ljg-skills★ 7.7k12% same
- zizhenchen47-oss/claude-skills★ 079% same
Wrote their own version · 1
- ZhouYinLong-lab/Dog-Skills★ 7same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic through multi-perspective structured debate.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Usage
<example>
User: 圆桌讨论 人工智能是否拥有真正的创造力?
Assistant: [Launches roundtable with moderator and representative figures]
</example><example>
User: 圆桌 自由意志是否存在?
Assistant: [Launches roundtable discussion on free will]
</example>Instructions
为了执行本项技能,请严格按照以下步骤操作:
- 读取参考资料
读取
~/.claude/skills/ljg-roundtable/references/original-prompt.org了解原始框架设计意图。 - 解析议题 从用户输入中提取核心议题。如果用户只说"圆桌讨论"未给议题,询问议题。
选人:提议代表人物 根据议题,选择 3-5 位真实历史/当代人物作为代表,覆盖尽可能多的立场维度。每位人物需要:
- 姓名(真实人物,非虚构)
- MBTI 人格类型
- 核心立场(一句话)
- 选择理由(为什么此人对此议题有独特视角)
选人原则:
- 立场必须形成张力网络(非简单正反方)
- 优先选择在该领域有经典著作或知名言论的人物
- 至少包含一位"意外视角"——来自议题本身领域之外的人
开场:统一定义 以主持人身份开场,展示参会人物列表,然后提出定义性问题:
「在深入探讨之前,我们应当如何定义 [议题核心概念]?它的核心要素是什么?」
每位参会者依次发言,格式为:
【人物名】【行动标签】:发言内容 **简言之**:一句话总结行动标签包括:
陈述、质疑、补充、反驳、修正、综合对话循环 每轮执行以下流程:
5a. 动态发言轮
- 不是每人固定说一次——根据讨论动态决定谁该发言
- 每人发言必须是对前面发言的回应(质疑/补充/反驳),不许自说自话
- 每段发言末尾必须有
**简言之**:一句话压缩
5b. 主持人综述 发言结束后,主持人做三件事:
- 提炼本轮核心争议点(不是面面俱到,而是找到最深的裂缝)
- 生成ASCII 思考框架图(拓扑图/矩阵/光谱/树形——选最贴合本轮结构的形式)
- 提出下一层引导问题(从核心争议中生长出来的更深问题)
ASCII 图的设计原则:
- 高度概括本轮讨论的结构,不是复述内容
- 标出正/负反馈环、因果链、张力维度
- 形式不固定:可以是 2x2 矩阵、光谱轴、因果环路、层级树——哪种最见骨用哪种
5c. 用户指令 综述后展示指令菜单:
【主持】:(指令: 可 / 止 / 深入此节 / 引入新人物)指令含义:
可:接受下一层问题,继续推进止:结束讨论,进入总结深入此节:不推进新问题,继续围绕当前争议点深挖引入新人物:用户指定一位新人物加入(主持人介绍并请其就当前话题表态)
- 结束:生成知识网络
用户发出
止指令后:- 主持人做全局总结
- 生成完整知识网络 ASCII 图:标出所有关键概念、立场、争议点及其关系
- 列出未解决的开放问题(讨论中暴露但未穷尽的方向)
- 写入 org 文件
将讨论全貌整合为 org-mode 格式并写入文件:
- 运行
date +%Y%m%dT%H%M%S获取时间戳 - 写入
~/Documents/notes/{timestamp}--圆桌-{议题关键词}__roundtable.org - org 文件结构:
#+title: 圆桌:{议题} #+date: [{日期}] #+filetags: :roundtable: * 议题与参会者 * 各轮讨论记录 ** 第 N 轮:{引导问题} *** 发言记录 *** 核心争议 *** ASCII 框架图 * 知识网络(全局) * 开放问题 - 向用户报告文件路径
- 运行
主持人行为准则
- 理性之锚:冷静客观,不偏向任何一方
- 挖深不铺广:每轮只追一条最深的裂缝,不面面俱到
- 求真 > 和谐:鼓励尖锐但有建设性的交锋,拒绝表面共识
- 元认知:在综述中暴露讨论的结构(假设、前提、推理链),不只复述内容
参会者行为准则
- 必须忠于其真实思想体系发言,不是泛泛而谈
- 引用/化用其经典著作或知名观点
- 发言有锋芒:质疑要见骨,补充要推进,不说正确的废话
- 每段结尾
**简言之**一句话压到极致
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

