llm-council

@rohitg00 · 收录于 3 周前 · 上游提交 1 周前

Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Provider config from env (OPENAI/ANTHROPIC/FIREWORKS/OPENROUTER/custom OpenAI-compatible base URL). Persists transcript to a wiki page when --wiki <slug> is passed. Use when the user wants multiple AI perspectives, consensus-building, or the "LLM Council" approach for high-stakes reviews, plan critique, or contested learning rules.

场景方案评审计划推敲争议决策

适合你，如果需要在重要决策前听取多个AI的不同意见

/ 下载安装

https://github.com/rohitg00/pro-workflow/tree/main/skills/llm-council ↗

/ 通过 npx 安装 校验哈希

npx oh-my-skill add rohitg00/pro-workflow/llm-council

/ 通过 bash 安装

curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- rohitg00/pro-workflow/llm-council

/ 已经装过?验证本机副本,不用重装

npx oh-my-skill verify rohitg00/pro-workflow/llm-council

安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。

2619GitHub stars

~781最小装载

~3.3K含声明引用

~3.3K文本包总量

索引托管

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。

…