菜单
Runs structured multi-agent discussions for open-ended @samchon/graph topics. Use only when the user explicitly asks for a Discussion or team debate with transcripts and conclusions; do not use for Self-Review, Review Cycle, research review, issue discovery, or implementation.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/samchon/compiler-graph --skill discussion命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | discussion |
| description | Runs structured multi-agent discussions for open-ended @samchon/graph topics. Use only when the user explicitly asks for a Discussion or team debate with transcripts and conclusions; do not use for Self-Review, Review Cycle, research review, issue discovery, or implementation. |
Discussion explores a topic without changing code or turning the exchange into a review queue. Reviews and issue discovery use the review skill instead.
Form the largest practical team within the available concurrency. Give every participant a self-contained brief with the topic, constraints, known evidence, output expectations, and the exact repository instructions and skills to read. Do not give a preferred conclusion or divide the topic into assigned slices.
Create .discussions/<topic>/ with a short filesystem-safe name. Do not delete or overwrite an existing discussion directory unless the user explicitly requests it.
Each participant maintains a personal wiki-style subdirectory under the topic directory. Participants read the live transcript and one another's statements between turns, continue researching, and revise their own notes.
Run three unrestricted transcript rounds as round1.md, round2.md, and round3.md. The lead moderates and records every statement in speaking order as a live transcript, not a retrospective summary. Do not narrow the topic unless the user does.
After round3.md, the lead writes agreed conclusions, disagreements, and major open points to summary.md, reports the result, and waits. Discussion does not authorize implementation or remote actions.
