Agent skill

Roundtable Debate

by lijigang in lijigang/ljg-skills

Hosts a structured roundtable debate on one topic with 3 to 5 real people, an ASCII structure diagram each round, user-controlled pacing and a saved org-mode transcript.

MITAuto-check passedKnowledge Management

SKILL.md written in Chinese; this summary is our English description.

Install Roundtable Debate

skills CLI
$ npx skills add lijigang/ljg-skills --skill ljg-roundtable -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lijigang/ljg-skills ljg-roundtable --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ljg-roundtable .claude/skills/ljg-roundtable && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ljg-roundtable
GitHub stars
7.5k
Token cost
~529 tokens
SKILL.md length
88 words
Files
2 (incl. references)
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

Hosts a structured roundtable debate on one topic with 3 to 5 real people, an ASCII structure diagram each round, user-controlled pacing and a saved org-mode transcript.

  • Works in 4 steps: date +%Y%m%dT%H%M%S 取时间戳 → 写入… → 文件结构 → …
  • Exploring a contested topic through a multi-perspective structured debate
  • SKILL.md covers Usage and Instructions
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Triggered by words like roundtable or debate, the skill makes the agent a neutral host. It picks 3 to 5 real people, historical or contemporary and never fictional, and gives each a name, MBTI type, one-line stance and the reason for inviting them. Guests should have positions that clash, ideally authors of classic work on the topic, with at least one outsider. The host opens with a definition question about the topic's core concept, and every speech uses one format: the person's name, an action tag (state, question, add, rebut, revise or synthesize) and a one-line summary.

Each round has three parts. Speakers respond directly to what came before, then the host names the core dispute, draws an ASCII diagram such as a 2x2 matrix, spectrum, causal loop or tree that shows how positions are structured, and poses a deeper follow-up question. You steer with four commands: continue, stop, dig deeper into the current section, or bring in a new person. On stop, the host gives an overall summary, a full knowledge-network ASCII diagram and a list of open questions.

The whole discussion is then saved verbatim as an org file in the ~/Context folder under a timestamped name, and the path is reported. The host takes no side, pursues one dispute per round and pushes past polite agreement, while guests stay faithful to the real thinking of the person they play. The agent first reads references/original-prompt.org, which holds the original design.

When your agent uses it

  • Exploring a contested topic through a multi-perspective structured debate
  • Pressure-testing an idea against well-known thinkers with opposing views
  • Keeping a full written record of a discussion as an org-mode note

Example prompts

  • “Roundtable: does free will exist?”
  • “Run a roundtable on whether AI can be truly creative, and save the transcript.”
  • “Hold a debate with five real thinkers on remote work versus office work.”

Requirements

  • A writable ~/Context folder for the saved org transcript

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. date +%Y%m%dT%H%M%S 取时间戳
  2. 写入 ~/Context/{timestamp}--圆桌-{议题关键词}__roundtable.org
  3. 文件结构
  4. 写完把文件路径报给用户。

What it can do on your machine

Read from SKILL.md and the folder at commit 9e75497. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are org).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Roundtable Debate loads about 529 tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 88 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~529
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lijigang/ljg-skills at commit 9e75497, republished under its MIT licence (© lijigang). 88 words, ~529 tokens.

Download SKILL.mdSave it as .claude/skills/ljg-roundtable/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ljg-roundtable
description
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 org 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.

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.org,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 org 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。

  1. date +%Y%m%dT%H%M%S 取时间戳

  2. 写入 ~/Context/{timestamp}--圆桌-{议题关键词}__roundtable.org

  3. 文件结构:

    org
    #+title: 圆桌:{议题}
    #+date: [{日期}]
    #+filetags: :roundtable:
    * 议题与参会者
    [人物名单:姓名、MBTI、立场、入选理由]
    * 开场:定义
    [主持人开场词 + 每人的定义发言]
    * 各轮讨论记录
    ** 第 N 轮:{引导问题}
    *** 发言记录
    [本轮全部发言原文,含行动标签和简言之]
    *** 主持人综述
    [争议点 + ASCII 图 + 下一层问题]
    * 知识网络(全局)
    [全局总结 + 知识网络图]
    * 开放问题
    [没谈完的方向]
  4. 写完把文件路径报给用户。

主持人怎么当
  • 不站队。
  • 每轮只追一个争议点,追到底,别摊大饼。
  • 要交锋。参会者说得客气、绕开分歧,主持人要点破,把分歧摆回桌面。表面共识等于没讨论。
  • 综述时把各方的底牌摊开:站在什么假设上,前提是什么,推理链在哪里分岔。光复述谁说了什么,不够。
参会者怎么说
  • 忠于本人真实的思想体系,说这个人真会说的话,引他写过的书、说过的名言。
  • 泛泛而谈的正确废话不要。质疑就指出对方哪个前提站不住,补充就把论证往前推一步。

© lijigang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/ljg-roundtable of lijigang/ljg-skills.

  • SKILL.md
  • references/original-prompt.org

Open the folder on GitHubat commit 9e75497

Compare with similar skills

Roundtable Debate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Roundtable Debate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Roundtable Debate this skilllijigang/ljg-skills7.5k—~529Automated safety check: PassMIT
Panning for GoldNateBJones-Projects/OB14.7k—~5kAutomated safety check: PassCustom licence
YouTube Talk Notetakerdair-ai/dair-academy-plugins614—~2.3kAutomated safety check: PassMIT
Viral Short Form Ideasvyralcontent/content-skills1331 repos~2.9kAutomated safety check: PassMIT
Agent Carnet Notebookyamadashy/repomix29k—~1.2kAutomated safety check: PassMIT
Personal Knowledge Wikizhayujie/CowAgent47k—~924Automated safety check: PassMIT

Similar skills

  • Panning for Gold

    NateBJones-Projects/OB1

    Processes voice transcripts and brain dumps in three phases, extracting every idea thread, evaluating the strongest and saving a permanent inventory and synthesis.

    4.7k GitHub stars~5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • YouTube Talk Notetaker

    dair-ai/dair-academy-plugins

    Converts a YouTube talk into a markdown study note with slide images, a timestamped transcript and editable notes, browsable through a small local server.

    614 GitHub stars~2.3k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed
  • Viral Short Form Ideas

    vyralcontent/content-skills

    Generate short-form video ideas at volume and stop the blank-page problem for good.

    133 GitHub starsUsed in 1 repo~2.9k tokens
    Media & CreativeAuto-check passed
  • Agent Carnet Notebook

    yamadashy/repomix

    Saves and recalls markdown notes between agent sessions with the agent-carnet CLI, tracking which notes proved useful so stale ones expire and good ones stay.

    29k GitHub stars~1.2k tokensUpdated 6 days ago
    Knowledge ManagementAuto-check passed
  • Personal Knowledge Wiki

    zhayujie/CowAgent

    Maintains a structured Markdown knowledge base in a knowledge/ folder by ingesting shared articles, synthesizing conversations and answering questions from it.

    47k GitHub stars~924 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Qmd

    alsk1992/CloddsBot

    Local hybrid search for markdown notes and docs. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 3 repos~1.2k tokens
    Knowledge ManagementAuto-check passed

More from lijigang/ljg-skills

All 26 skills in this repo
  • Whole-Book Explainer Notes

    lijigang/ljg-skills

    Explains a whole book to someone who has not read it, keeping its specific content and showing how its threads connect, and saves the result as an Org note.

    7.5k GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Ljg Paper

    lijigang/ljg-skills

    Explain research papers to readers without a specialist background: what the paper studies, what the authors contribute, how the findings follow, and what the evidence does not establish.

    7.5k GitHub stars~798 tokensUpdated yesterday
    Auto-check passed
  • Text to PNG Card Caster

    lijigang/ljg-skills

    Turns text, URLs or local files into tall PNG cards through HTML typography, with four modes: long reading card, full-text layout, comic and whiteboard.

    7.5k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Turns a named classical Chinese chapter, such as one from the Tao Te Ching or the Analects, into a single annotated PNG image with notes and commentary.

    7.5k GitHub stars~551 tokensUpdated yesterday
    Auto-check passed
  • Constraint Engine

    lijigang/ljg-skills

    Finds the handful of constraints that truly define a domain, role, product or debate, grades each by hardness, and explains the behavior those constraints produce.

    7.5k GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Offline HTML Talk Decks

    lijigang/ljg-skills

    Builds single-file offline HTML talk decks from Org or Markdown outlines, with faithful layout or editorial condensing and keyboard navigation.

    7.5k GitHub stars~506 tokensUpdated yesterday
    Auto-check passed

Questions about Roundtable Debate

What does Roundtable Debate do?

Hosts a structured roundtable debate on one topic with 3 to 5 real people, an ASCII structure diagram each round, user-controlled pacing and a saved org-mode transcript. Triggered by words like roundtable or debate, the skill makes the agent a neutral host. It picks 3 to 5 real people, historical or contemporary and never fictional, and gives each a name, MBTI type, one-line stance and the reason for inviting them.

When should I use Roundtable Debate?

Roundtable Debate fits situations like: exploring a contested topic through a multi-perspective structured debate; pressure-testing an idea against well-known thinkers with opposing views; keeping a full written record of a discussion as an org-mode note.

How do I install Roundtable Debate in Claude Code?

Run `npx skills add lijigang/ljg-skills --skill ljg-roundtable -a claude-code`. Or copy the skill folder (skills/ljg-roundtable in lijigang/ljg-skills) into .claude/skills/ljg-roundtable in your project. Claude Code loads it when a task matches its description.

How do I install Roundtable Debate in Codex?

Run `npx skills add lijigang/ljg-skills --skill ljg-roundtable -a codex`. Or copy the skill folder (skills/ljg-roundtable in lijigang/ljg-skills) into .agents/skills/ljg-roundtable in your project. Codex loads it when a task matches its description.

Can I use Roundtable Debate in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lijigang/ljg-skills --skill ljg-roundtable -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ljg-roundtable, .gemini/skills/ljg-roundtable, .github/skills/ljg-roundtable and .opencode/skills/ljg-roundtable in your project.

What does Roundtable Debate need to run?

SKILL.md names no scripts, command-line tools or credentials: Roundtable Debate is instructions for the agent only. Our summary lists: A writable ~/Context folder for the saved org transcript.

Does Roundtable Debate access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Roundtable Debate safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Roundtable Debate use?

Roundtable Debate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Roundtable Debate use?

About 529 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Roundtable Debate?

Skills that share tags, products or a category with Roundtable Debate: Panning for Gold (NateBJones-Projects/OB1, 4.7k stars), YouTube Talk Notetaker (dair-ai/dair-academy-plugins, 614 stars), Viral Short Form Ideas (vyralcontent/content-skills, 133 stars) and Agent Carnet Notebook (yamadashy/repomix, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Roundtable Debate?

lijigang (a GitHub user) maintains it in lijigang/ljg-skills, which has 7,474 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 8, 2026.

Source: lijigang/ljg-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.