ljg-roundtable
The ljg-roundtable skill facilitates structured multi-perspective debates by simulating 3-5 real-world figures. It manages the discussion flow through rounds of debate, ASCII diagram generation, and user-controlled pacing. The skill archives the full transcript, including diagrams and summaries, into an org-mode file.
Is ljg-roundtable safe to install?
Review the source first: our audit of ljg-roundtable's source files found 1 shell command, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands to generate timestamps and writes files to the user's local directory structure.
How we audit skills: our security review methodology.
Who is this skill for?
Users who want to explore complex topics through structured, multi-perspective debates involving historical or contemporary figures.
What can you do with it?
- Conducting a structured debate on a specific topic.
- Exploring different viewpoints on philosophical or technical questions.
- Generating an org-mode file containing a full transcript of a simulated roundtable discussion.
- Visualizing debate structures using ASCII diagrams.
How good is this skill?
Quality score: 5/10. The skill provides clear, structured instructions for role-playing and file management. It maintains a consistent format for outputs and includes specific requirements for the archival process.
What does the skill file contain?
## 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...
Frequently asked questions
How does the skill select participants?
The skill selects 3-5 real-world figures based on the topic. It prioritizes individuals who have written or spoken extensively on the subject, ensures a mix of conflicting viewpoints, and includes at least one person from outside the specific field.
Can I control the flow of the discussion?
Yes. After each round, the skill provides a menu allowing you to continue, stop, delve deeper into the current point, or introduce a new participant.
Where is the discussion saved?
The skill saves the full transcript into an org-mode file located at ~/Documents/notes/ using a timestamped filename.
Related skills
lark-workflow-meeting-summary
219.7KUsers who need to summarize meeting minutes, generate weekly reports, or review meeting history within the Lark ecosystem
The lark-workflow-meeting-summary skill provides a structured workflow for agents to aggregate meeting minutes from Lark VC, generate summaries, and create or update reports in Lark Docs.
caveman-review
219.4KDevelopers and reviewers who prefer terse, actionable feedback on code changes
The caveman-review skill generates concise, one-line code review comments for pull requests. It enforces a strict format of location, problem, and fix to reduce noise in feedback.
caveman-commit
214.4KDevelopers who want to maintain clean, terse, and informative git commit histories
The caveman-commit skill generates concise commit messages following the Conventional Commits specification. It prioritizes the reasoning behind changes over the description of the changes themselves.
notion-api
52.2KDevelopers and AI agents requiring programmatic access to Notion workspaces
This skill provides instructions for interacting with the Notion REST API. It enables agents to read, create, update, and delete Notion pages, databases, blocks, and comments using curl and jq.