skills/research-learning-knowledge/roundtable/SKILL.md
Multi-perspective roundtable discussion skill for exploring a topic through a truth-seeking moderator and a small set of representative real figures. Use when the user asks for 圆桌讨论 / roundtable / 多人物观点碰撞 / 让几位思想家讨论 / 模拟多方思想交锋 / 结构化辩论探索, or wants to examine one topic through disciplined multi-party debate rather than a plain summary. Do not use it for ordinary argumentative writing, generic pros/cons lists, or a single-speaker explanation.
npx skillsauth add bahayonghang/my-claude-code-settings roundtableInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
把一个议题放进高张力、多视角、可推进的结构化讨论里。
这个 skill 的核心不是“热闹”,而是“挖到结构”。主持人要找到最深的裂缝,让不同思想体系在同一个问题上正面相撞。
你是这场圆桌的主持人。你的任务不是替用户得出一个“正确答案”,而是组织一场能逼近问题骨架的深度讨论。
references/original-prompt.org,把它当作设计意图参考。SKILL.md 的流程执行。默认选择 3-4 位真实历史或当代人物。每位人物必须给出:
选人原则:
事实护栏:
第一次响应默认只做一轮,不要自动失控展开成长篇连载。首轮固定包含:
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?如果用户明确说“一次性给我完整讨论,不要分轮”,可以在一条回复里完成:首轮交锋 + 主持人综述 + 终局总结,但仍要保留结构化主持和 ASCII 图。
每轮只让最该发言的人发言,通常 2-3 位,不要求人人轮流。
每段发言都必须:
对话展示格式:
【人物名】【行动标签】:发言内容
简言之:一句话总结
行动标签使用:陈述、质疑、补充、反驳、修正、综合
每轮发言后,主持人必须做三件事:
ASCII 图原则:
每轮综述后,展示:
【主持】:(指令: 可 / 止 / 深入此节 / 引入新人物)
四个控制动作:
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:继续围绕当前裂缝深挖,不换题引入新人物:加入一位用户指定的新人物,并请其先对当前问题表态如果用户没有精确输入这四个短指令,而是用了自然语言,就按语义映射到最接近的控制动作。
当用户发出 止 或等价的结束意图后:
默认先保证对话内结果完整。文件导出是增强项,不是前置条件。
如果环境允许读写文件,再额外导出 org 文件:
Get-Date -Format "yyyyMMddTHHmmss" 与 Get-Date -Format "yyyy-MM-dd ddd HH:mm"date +%Y%m%dT%H%M%S 与 date "+%Y-%m-%d %a %H:%M"New-Item -ItemType Directory -Force ~/Documents/notes | Out-Nullmkdir -p ~/Documents/notes~/Documents/notes/{timestamp}--圆桌-{议题关键词}__roundtable.org导出的 org 文件必须是纯 org-mode:
* 开始,不跳级。#+begin_example / #+end_example 块。推荐 org 结构:
#+title: 圆桌:{议题}
#+date: [{日期}]
#+filetags: :roundtable:
* 议题与参会者
* 第一轮:定义与开场
** 发言记录
** 核心争议
** ASCII 框架图
* 后续轮次
** 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)
* 主要分歧轴
* 局部共识
* 开放问题
development
Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and pause/block conditions. Use when the user asks for Codex goal instructions, Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, plan-to-goal interviews, success criteria, verification commands, or bounded agent work definitions.
tools
Write, debug, and validate ast-grep structural code search rules. Use this skill when the user needs syntax-aware code search, AST pattern matching, structural refactor discovery, language-construct queries, or searches that plain text tools like rg can miss, such as finding functions with particular descendants, calls inside specific contexts, missing error handling, React hook shapes, decorators, or other Tree-sitter-backed code structures.
development
Use when the user asks to ground an ambitious proposal, avoid over-grand designs, make a bold direction executable, pressure-test feasibility, prevent "too much vision and too little landing", or turn a strategy/refactor/product idea into the smallest verifiable first move with stop rules. Trigger for requests such as 落地, 先落地, 别太飘, 收一收, 可执行, 可验证, 止损, and for follow-ups after geju-style big-picture thinking. Do not trigger for ordinary code review or implementation unless the user explicitly asks to ground or shrink the plan first.
development
Use when the user explicitly asks to think bigger, open up the design space, challenge conservative design, avoid over-indexing on backward compatibility, escape local-detail fixation, or make a bold high-level product or architecture direction call. Use for strategic reframing, not for ordinary code review, PRD writing, implementation planning, or adversarial risk review.