rohitg00/pro-workflow✦ 精选0°

llm-council

仓库创建 2026年2月2日最近提交 6 天前SkillHot 收录 20 天前

⬈ GitHub 仓库 ⬈ SKILL.md 原文件 ⬇ Raw 原始文件

▸ 精选理由

适合高风险或冲突意见场景，用多模型投票提升决策鲁棒性。

▸ 风险提示

可能向多家模型服务发送相同数据，增加数据泄露面。

这个 Skill 做什么

基于多模型独立回应、匿名排名与主席合成的跨模型审议流程。

把多个 LLM 当成评审团：先各自独立回应，再匿名互评排序，最后由一位“主席”合成共识意见。适合高风险决策、架构评审或需要多个模型视角来打分和达成一致的场景。特点是 provider-agnostic，可接不同供应商的模型并能把会话纪录存到 wiki 以便审计与复盘。

▸ 展开 SKILL.md 英文原文

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.

研究检索多模型投票模型合成决策审查通用

2.7k

Stars

257

Forks

仓库内 Skill

+55

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/rohitg00/pro-workflow/main/skills/llm-council/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/rohitg00/pro-workflow/main/skills/llm-council/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# LLM Council

Karpathy's LLM Council pattern, provider-agnostic. dair-academy's version hardcoded Fireworks; ours reads any OpenAI-compatible endpoint via env.

## When to use

- High-stakes plan review (`/plan` crosses N-file threshold)
- Conflicting learning-rules → re-resolve via vote
- User invokes `/council "<query>"` or `/wiki council`
- Architecture decisions where you want multiple viewpoints captured
- Persisting deliberation as a wiki page for future reference

## Three phases

1. **Independent**: each model answers in parallel
2. **Ranking**: each model ranks anonymized peer responses
3. **Synthesis**: chairman model reads all responses + rankings → final answer

## Provider conf

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有