lijigang avatar

Ljg Roundtable

This is a structured debate framework that runs multilayered roundtable discussions with historical or contemporary figures. When you say "圆桌讨论" or "roundtable," it picks 3-5 real people with opposing viewpoints on your topic, has them define core terms first, then cycles through dynamic exchanges where participants must respond to each other rather than monologue. The moderator draws ASCII diagrams after each round to map the argument structure, finds the deepest point of disagreement, and asks a new layer question. You control pacing with commands like "可" to continue or "深入此节" to dig deeper without moving on. Everything gets saved verbatim to an org-mode file with the full discussion tree and knowledge network diagram.

skills.sh installs
6.9K
GitHub stars
7.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add lijigang/ljg-skills --skill ljg-roundtable --agent claude-code

Installs into .claude/skills of the current project.

Files

Usage

User: 圆桌讨论 人工智能是否拥有真正的创造力? Assistant: [主持人开场,请出人物,从定义谈起] User: 圆桌 自由意志是否存在? Assistant: [就自由意志展开圆桌]

Instructions

先读 references/original-prompt.md,这套框架的原始设计在里面,主持人的性格和整个流程都从它来。

一、定议题

用户给了议题直接用。只说「圆桌讨论」没带议题,先问一句。

二、请人

按议题挑 3-5 位真实人物,历史的当代的都行,不要虚构。每位给四样:

  • 姓名
  • MBTI
  • 立场,一句话
  • 为什么请他:他看这个议题的角度,别人给不了

挑人看三条:

  • 几个人的立场要能互相较劲,光分正方反方两队不够
  • 优先挑在这个题上写过经典、说过名言的人
  • 至少一位行外人

三、开场

主持人开场,亮出人物名单和请他们来的理由,然后抛出定义问题:

「开谈之前,先把『议题核心概念』说清楚:它指什么?哪些要素少不了?」

每人依次就定义发言。发言格式全场统一:

【人物名】【行动标签】:发言内容

**简言之**:一句话总结

行动标签六种:陈述、质疑、补充、反驳、修正、综合。

四、讨论循环

每轮三步。

发言。 谁说话看讨论走势定,不排班。每段发言必须接着前面的话说,质疑、补充、反驳都行,不许自说自话。说完照例收一句 简言之。

综述。 一轮说完,主持人做三件事:

  • 点出本轮核心争议点。挑最深的那一个,别求全。
  • 画一张 ASCII 图:2x2 矩阵、光谱轴、因果环、层级树,哪种贴合本轮结构用哪种。图画的是讨论的结构:立场怎么分布、因果怎么绕、正负反馈环在哪。别拿图复述内容。
  • 从争议点里引出下一层问题。

等指令。 综述后亮菜单:

【主持】:(指令: 可 / 止 / 深入此节 / 引入新人物)
  • 可:接受下一层问题,继续
  • 止:收场,进入总结
  • 深入此节:不推进,围着当前争议点再挖
  • 引入新人物:用户点名一位新人物,主持人介绍后请他先就当前话题表态

五、收场

用户下了 止:

  • 主持人做全局总结
  • 画一张完整的知识网络 ASCII 图:这场讨论的关键概念、各家立场、争议点,彼此怎么连
  • 列出开放问题:讨论里冒出来、但没谈透的方向

六、存档

讨论全文写进 Markdown 文件,一字不差。发言、ASCII 图、综述,全部原文照录,不摘要,不压缩,不改写。

Sponsors

Details

Repository
github.com/lijigang/ljg-skills
First seen
Apr 16, 2026

More from lijigang/ljg-skills

All 25

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs