ljg-roundtable SKILL.md skillA

ljg-roundtable from lijigang/ljg-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lijigang/ljg-skills/ljg-roundtable@git:20261026.a6b1118

Pins git:20261026.a6b1118 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lijigang/ljg-skills
Path
skills/ljg-roundtable/SKILL.md
Versions recorded
6
Latest version
git:20261026.a6b1118, committed Oct 26, 2026
First version recorded
Mar 24, 2026
Size
4,567 bytes
Repository stars
7,668
License
MIT

一个议题,一场圆桌:主持人请来 3-5 位真实人物,定义开场,逐轮交锋, 每轮收一张 ASCII 结构图,用户用指令控节奏(可/止/深入此节/引入新人物), 散场后全文存入 Markdown 笔记。Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic through multi-perspective structured debate.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

## Usage

<example>
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]
</example>

<example>
User: 圆桌 自由意志是否存在?
Assistant: [就自由意志展开圆桌]
</example>

## 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。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add lijigang/ljg-skills/ljg-roundtable@sha256:0864c98f26973f68

The line at the top of this page pins the label git:20261026.a6b1118, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pupladdsw23ctfyv.svg)](https://markdownregistry.com/a/art_pupladdsw23ctfyv)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Mar 24, 2026 and Oct 26, 2026, about one every 43 days.

versioncommittedcommitsizeaudit
git:20261026.a6b1118 latest2026-10-26 a6b1118 4,567 BA view · diff
git:20260817.cbea5792026-08-17 cbea579 4,552 BA view · diff
git:20260702.d89fa0d2026-07-02 d89fa0d 4,560 BA view · diff
git:20260417.197f1f12026-04-17 197f1f1 5,708 BA view · diff
git:20260405.4d5f3722026-04-05 4d5f372 5,740 BA view · diff
git:20260324.91fec862026-03-24 91fec86 5,079 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4567 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

lijigang/ljg-skills · 7,668 stars · license MIT · pushed 2026-11-02 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_pupladdsw23ctfyv
GET https://markdownregistry.com/api/v1/resolve?ref=lijigang/ljg-skills/ljg-roundtable
GET https://markdownregistry.com/api/v1/blob/0864c98f26973f68cc75c3fc59ccddcf37098d6a1a98544ee0108f9b31abdb4b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from lijigang/ljg-skills

CLAUDE.md CLAUDE.md file
lijigang/ljg-skills · CLAUDE.md
git:20261003.1e97b53 · audit A · 7,668 stars
ljg-analogy SKILL.md skill
lijigang/ljg-skills · skills/ljg-analogy/SKILL.md · 基于结构映射理论,为场景或两个对象的差异寻找精妙类比与关系隐喻,保留关键关系、解释增量与迁移边界。USE WHEN 用户说「找个类比」「打个比方」「有什么精妙的隐喻」「用类比讲清两者区别」「换个场景理解」或调用…
v1.1.0 · audit A · 7,668 stars
ljg-blind SKILL.md skill
lijigang/ljg-skills · skills/ljg-blind/SKILL.md · 盲区扫描——读昨天你与 AI 的全部对话,照出暴露的思维盲区(不是不懂的知识,是让某类真相一直看不见的思维习惯),再从微信读书挑一本书的一章精准补上,落成一篇完整分析笔记。Use when user says '扫盲区', '盲区'…
git:20261026.a6b1118 · audit A · 7,668 stars
ljg-book SKILL.md skill
lijigang/ljg-skills · skills/ljg-book/SKILL.md · Explain a whole book to readers without specialist knowledge: what it follows, how its main threads connect, where it…
git:20261102.76b5fb9 · audit A · 7,668 stars
ljg-business-model SKILL.md skill
lijigang/ljg-skills · skills/ljg-business-model/SKILL.md · 基于《商业模式新生代》的 Business Model Canvas,把用户提供的项目介绍、访谈、产品资料或商业计划整理成九模块商业模式画布卡片,交付 PNG 与可修改的 HTML。USE WHEN 用户调用…
v1.0.0 · audit A · 7,668 stars
ljg-card SKILL.md skill
lijigang/ljg-skills · skills/ljg-card/SKILL.md · Content caster (铸). Transforms text into PNG through precise HTML typography and, when the mold needs it, generated…
v7.4.2 · audit A · 7,668 stars
ljg-classic SKILL.md skill
lijigang/ljg-skills · skills/ljg-classic/SKILL.md · 古文逐字注解、组合排版、章节意旨图与全章解读生成器。把原文、字词注、句义注、无字顶部配图和章节解读排成一张可读的长 PNG。USE WHEN 用户调用 ljg-classic OR…
v1.1.2 · audit A · 7,668 stars
ljg-constraint SKILL.md skill
lijigang/ljg-skills · skills/ljg-constraint/SKILL.md · 给一个领域、专业、角色、产品或争论找出真正框住它的几条约束,判明它们属于世界/规则/解释(硬/软/自设),看这组约束如何定义身份、补全问题、框出解空间并解释实际行为;尤其用于区分目标相同但约束不同导致的方案分歧,识别被误当硬事实的旧解释。U…
git:20261030.36ad0ac · audit A · 7,668 stars
ljg-explain SKILL.md skill
lijigang/ljg-skills · skills/ljg-explain/SKILL.md · 把概念、公式、机制与原理讲到能辨认、能推导、能迁移:用通俗中文接通具体情境、判别依据、运作过程和成立条件。USE WHEN 用户调用 ljg-explain、说「通俗易懂地讲解」「讲透这个概念或公式」「费曼讲解」「ELI5」,或希望从零理解…
v1.0.2 · audit A · 7,668 stars
ljg-invest SKILL.md skill
lijigang/ljg-skills · skills/ljg-invest/SKILL.md · 投资分析。给一个项目(公司名、BP、创始人对话记录),写一份深度投资分析报告。不走传统投资分析的路——核心判断只有一个:这个项目是不是一台「秩序创造机器」。Use when user says '投资报告', '投资分析'…
git:20261026.a6b1118 · audit A · 7,668 stars
ljg-is SKILL.md skill
lijigang/ljg-skills · skills/ljg-is/SKILL.md · 把一个名词或概念写成可使用的理解:先用普通话讲清它是什么、与相邻概念差在哪里,再说明它怎样运作、会改写什么判断,最后给出面对它时的行动抓手。USE WHEN 用户问 X…
v5.0.0 · audit A · 7,668 stars
ljg-learn SKILL.md skill
lijigang/ljg-skills · skills/ljg-learn/SKILL.md · Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics…
git:20261026.a6b1118 · audit A · 7,668 stars

Every file in lijigang/ljg-skills

Browse by kind, by grade A, or by owner.