Multi Model Consensus
多模型决策委员会 — 消除单模型偏见,通过多轮分歧讨论产出客观决策参考。支持3-6个模型同时评审,提供量化投票矩阵和6段式共识报告。触发条件:包含「多模型决策」或「多模型委员会」时自动激活。 Skill: Multi Model Consensus Owner: zeekr0808-hue Summary: 多模型决策委员会 — 消除单模型偏见,通过多轮分歧讨论产出客观决策参考。支持3-6个模型同时评审,提供量化投票矩阵和6段式共识报告。触发条件:包含「多模型决策」或「多模型委员会」时自动激活。 Tags: latest:1.9.1 Version history: v1.8.0 | 2026-05-16T14:47:53.996Z | auto **Summary:** This release enforces stricter process control and standardization for the multi-model decision committee, focusing on compliance, template usage, and evaluation transparency.
Rank
62
Safety
84
Downloads
1.3k
Updated
Oct 10, 2026
Version
1.8.0
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 10, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 10, 2026
- Adoption signal
- 1.3K downloadsadoption · observed Oct 10, 2026
- Latest release
- 1.8.0release · observed May 16, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s17ag6jke66yamdtr7sz868c5x85ff28:multi-model-consensus- Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zeekr0808-hue-multi-model-consensus/snapshot"
Documentation
CLAWHUB
151,930 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
---
name: multi-model-consensus
description: 多模型决策委员会 — 消除单模型偏见,通过多轮分歧讨论产出客观决策参考。支持3-6个模型同时评审,提供量化投票矩阵和5段式共识报告。触发条件:包含「多模型决策」或「多模型委员会」时自动激活。
allowed-tools: SessionsSpawn,SessionsSend,SessionsHistory,Read,Write
metadata:
openclaw:
emoji: "🏛️"
requires:
capability: sessions_spawn
# 路径约束:见正文"技术约束"章节
---
# 🏛️ 多模型决策委员会
专为 OpenClaw 设计的"数字智库",通过多模型独立评审与共识合成,消除单模型偏见,为复杂决策提供客观参考。
---
## 🎯 插件定位
**多模型决策委员会** 是专为 OpenClaw 设计的"数字智库"。它支持调动多个不同架构的大模型(如 GPT、Gemini、豆包等)同时对同一任务进行协同思考、对抗辩论与共识合成,有效消除单模型偏见,综合性给出最优建议。
---
## 核心优势
- **去中心化决策**:交叉验证不同模型逻辑,确保方案的严谨性。
- **对抗性评审**:通过模型间的互评,快速锁定潜在的逻辑漏洞。
- **弹性扩容**:根据任务难度,随时增加或减少"决策委员"的数量。
- **消除偏见**:多模型独立评审,避免单一AI的认知盲区。
- **量化决策**:6维度评分 + 加权矩阵,结论有据可查。
- **透明可信**:实名委员制、模型身份透明。
- **灵活配置**:参数可调,如决策成员人数、决策轮次、通过阈值等,均可可自定义。
---
## 核心治理原则:身份纯净
为了确保结果的绝对客观,本插件强制执行 **"身份纯净原则"**:
- **角色透明化**:决策委员会成员均会注明其身份(大模型名称),保持可视化透明。
- **严禁设定角色**:禁止给委员设定诸如"架构师"、"审计员"等身份标签。
- **严禁引导提示**:任务下发时不得针对评审委员设置诱导性提示词或诱导性身份角色,防止产生的偏见。
- **评委工具隔离**:评委子Agent仅通过 `task` 参数接收评审内容,独立输出结论;不得调用任何工具(包括 spawn、Read、Write、Exec、Search 等),所有外部操作由组织者统一管理
- **评审不重复原则**:若组织者(即当前使用模型)是评审委员会成员,则组织者提交内容即视同为其在本轮的评审结果,无需重复自评。若组织者不是评审委员会成员,则仅负责组织实施和汇总评委意见,不参与评审。
---
## 使用方法
- **启动**:在OpenClaw中,当用户输入的内容包含「多模型决策」或「多模型委员会」时,自动激活多模型决策委员会。首次使用时会提醒用户进入配置模式,并选择模型组合。
- **配置**:根据需要,可配置参数,如:轮数、阈值、委员数量、委员模型等。
### 参数配置
配置参数可采用指令方式,如:"修改配置"、"调整参数"、"增加委员"、"确认配置"。
| 指令关键词 | 可调参数 | 说明 |
|:---|:---|:---|
| "换模型" | 委员模型组合 | 从用户本地接入的模型列表中选择模型组合加入。用户要求调整评委时,组织者**必须**读取 `openclaw.json` 列出当前环境下所有可接入的大模型名单(含Provider、上下文、最大输出等关键信息),供用户选择。 |
| "改轮数" | 决策轮数 | 默认3轮,日常事务可设为2轮,重大决策可设3-6轮 |
| ~~"收敛分差阈值"~~ | ~~收敛判定分差~~ | ~~已废弃~~ |
| "改阈值" | 判定阈值 | **通过阈值**:默认≥90%;**待定阈值**:默认[60%, 90%);**否定阈值**:默认<60% |
| "改判定方式" | 通过判定方式 | **全票通过** |
| "增加委员" / "减少委员" | 委员数量 | 支持2-6个模型同时评审。用户要求增减委员时,组织者**必须**先列出当前环境下所有可接入的大模型名单,供用户指定。 |
| "确认配置" | 确认当前配置 | 确认当前参数后开始决策 |
### 评委调整规则(铁律)
当用户表达"换评委"、"换模型"、"调整评委"、"增减委员"等意图时,组织者**必须**执行以下步骤:
1. **列出全部可用模型**:读取 `openclaw.json` 中所有 provider 的 models 列表,完整展示:
- 模型ID(如 `gpt-5.5`、`gemini-3.1-pro-preview`)
- 模型名称(如 GPT-5.5、Gemini 3.1 Pro)
- Provider来源(如 n1n、n1n-gemini、ark-cn)
- 上下文窗口(contextWindow)
- 最大输出(maxTokens)
2. **推荐组合**:基于任务特点,给出1-3组推荐搭配(如"逻辑+中文"、"深度+性价比")。
3. **等待用户指定**:禁止直接替用户选择,必须等待用户明确指定模型组合后方可继续。
### 参数建议
- **模型选择**:建议至少包含 1 个具备强逻辑推理能力的模型和 1 个具备强中文语境理解能力的模型。
- **轮次建议**:日常事务建议 2 轮;涉及架构,资金、核心规则的决策,建议 3-5 轮。
- **阈值设定**:
- **严谨型**:≥95%(全票通过)
- **效率型**:≥75%(多数通过)
---
## 决策流程(3轮决策机制)
多模型决策委员会采用 3 轮决策机制,基于决策点级别评审,每轮进行100分制评分,最终给出决策结果。
---
### 第 0 轮:准备与框架确认 (Preparation & Framework Confirmation)
**决策准备**:组织者(当前使用模型)接收到决策任务后,将用户背景、需求、待审方案汇总,拆解为决策点及权重,发起决策申请。
> 📌 **标准模板**:组织者须完整套用 `references/OUTPUT_TEMPLATE.md` 中的 **T1 决策准备确认模板**,不得自行增删字段或自由发挥。
---
### 运行时自检(第 0 轮环境兼容性检查)
组织者在启动评委前,执行环境自检以确保子Agent可正常 spawn 和返回结果。此步骤为系统自动执行,确保运行环境兼容性。
**自检方法**:通过 `session_status` 或检查当前会话元数据,确认通道类型。
**环境适配矩阵**:
| 环境 | Runtime | Mode | 额外参数 | 结果回收方式 |
|:---|:---|:---|:---|:---|
| **Webchat** | `subagent` | `"run"` | 无 | `subagdocs/README.md
# Multi-Model Consensus Council — Operation & User Guide
## 📋 Version History
| Version | Date | Changes |
|:---|:---|:---|
| V1.0.0 | 2026-04-19 | Initial release: core framework, 3-round convergence, 6-section report |
| V1.1.0 | 2026-04-24 | Added English operation guide (merged with Chinese, English first); translation reviewed and approved by multi-model committee (Gemini/Doubao/GLM, avg 81/100); wording optimizations |
| V1.1.3 | 2026-04-24 | SKILL.md and references/ converted to pure Chinese for AI readability; docs/ retains full bilingual documentation for global community |
| V1.2.0 | 2026-04-25 | Restored public ClawHub version (was local customized); sync all files |
| V1.2.1 | 2026-04-25 | **CRITICAL FIX**: Removed hardcoded model list (A1/A2/A4...) from SKILL.md; replaced with dynamic scan via `openclaw models list`; examples updated to use generic `[Model A/B/C]` placeholders |
| V1.2.2 | 2026-04-25 | SYNC: Full file sync to GitHub and ClawHub after v1.2.1 hotfix |
| V1.2.3 | 2026-04-25 | **UX FIX**: Clarify first-time user flow: auto-scan models → default to first 3 → prompt user to confirm/modify before starting decision |
| V1.2.4 | 2026-04-25 | **CRITICAL FIX**: OUTPUT_TEMPLATE.md - remove "匿名委员" from all 3 round prompt templates; replaced with real-name format `{模型名称}(实名委员)` |
| V1.2.5 | 2026-04-25 | **ENFORCEMENT**: SKILL.md - add mandatory threshold check rules; add forbidden items for skipping threshold/convergence checks; state machine now has explicit checkpoint enforcement |
| V1.2.6 | 2026-04-25 | **Real-name Transparency**: Judges use standard model names; 3-layer architecture (organizer/judge/sub-agent); 100-point scoring; Round 0 preparation phase added |
| V1.5.0 | 2026-04-25 | Sync all document versions to V1.5.0; renamed SCHEMA.md; full English content aligned with Chinese |
| V1.5.1 | 2026-04-26 | Added round-start user notification rule; added convergence score threshold parameter; added exception handling rules section |
| V1.5.2 | 2026-04-26 | Added judgment method configurable parameter; clarified unanimous-pass rule as default |
---
## 🎯 Plugin Overview
**Multi-Model Consensus Council** is a "Digital Think Tank" designed for OpenClaw. It coordinates multiple large language models (e.g., GPT, Gemini, Doubao) to collaboratively analyze, debate, and synthesize decisions, effectively eliminating single-model bias.
### Core Advantages
- **Decentralized Decision-Making**: Cross-validates reasoning across models, ensuring rigor.
- **Adversarial Review**: Rapidly identifies logical flaws through peer evaluation.
- **Elastic Scaling**: Adjust the number of "decision committee members" anytime based on task complexity.
- **Bias Elimination**: Multi-model independent review avoids single-AI cognitive blind spots.
- **Quantitative Decision-Making**: 6-dimension scoring + weighted matrix, conclusions are evidence-based.
- **Transparency & Trust**: Real-name committee system, model identity visible.
- **Flexible CREADME.md
# Multi-Model Consensus Council — Operation & User Guide
## 📋 Version History
| Version | Date | Changes |
|:---|:---|:---|
| V1.0.0 | 2026-04-19 | Initial release: core framework, 3-round convergence, 6-section report |
| V1.1.0 | 2026-04-24 | Added English operation guide (merged with Chinese, English first); translation reviewed and approved by multi-model committee (Gemini/Doubao/GLM, avg 81/100); wording optimizations |
| V1.1.3 | 2026-04-24 | SKILL.md and references/ converted to pure Chinese for AI readability; docs/ retains full bilingual documentation for global community |
| V1.2.0 | 2026-04-25 | Restored public ClawHub version (was local customized); sync all files |
| V1.2.1 | 2026-04-25 | **CRITICAL FIX**: Removed hardcoded model list (A1/A2/A4...) from SKILL.md; replaced with dynamic scan via `openclaw models list`; examples updated to use generic `[Model A/B/C]` placeholders |
| V1.2.2 | 2026-04-25 | SYNC: Full file sync to GitHub and ClawHub after v1.2.1 hotfix |
| V1.2.3 | 2026-04-25 | **UX FIX**: Clarify first-time user flow: auto-scan models → default to first 3 → prompt user to confirm/modify before starting decision |
| V1.2.4 | 2026-04-25 | **CRITICAL FIX**: OUTPUT_TEMPLATE.md - remove "匿名委员" from all 3 round prompt templates; replaced with real-name format `{模型名称}(实名委员)` |
| V1.2.5 | 2026-04-25 | **ENFORCEMENT**: SKILL.md - add mandatory threshold check rules; add forbidden items for skipping threshold/convergence checks; state machine now has explicit checkpoint enforcement |
| V1.2.6 | 2026-04-25 | **Real-name Transparency**: Judges use standard model names; 3-layer architecture (organizer/judge/sub-agent); 100-point scoring; Round 0 preparation phase added |
| V1.5.0 | 2026-04-25 | Sync all document versions to V1.5.0; renamed SCHEMA.md; full English content aligned with Chinese |
| V1.5.1 | 2026-04-26 | Added round-start user notification rule; added convergence score threshold parameter; added exception handling rules section |
| V1.5.2 | 2026-04-26 | Added judgment method configurable parameter; clarified unanimous-pass rule as default |
| **V1.6.0** | **2026-04-27** | **MAJOR FIX**: Rewrote sub-agent result recovery; added runtime environment adaptation matrix; Push-based waiting flow; runtime self-check; simplified state management; added TROUBLESHOOTING.md |
| **V1.6.1** | **2026-04-27** | **Clarified judgment rules**: Separated "Pass" vs "Convergence" vs "Consensus Selection"; clarified convergence discussion scope; renamed "Round 3" to "Final Round"; added Consensus Selection for final round |
| **V1.6.2** | **2026-04-27** | **Core logic refactored**: Removed "Convergence"; introduced "Decision Point" level review; "Convergence Discussion" renamed to "Dispute Discussion"; final report includes decision point status (✅/🟡/🔴) |
| **V1.6.5** | **2026-04-30** | **Security Hardening**: Removed unused `Exec` from allowed-tools; reduced max concurrent sub-agents from 13 to 6; added `Write` tool path restriction (mem_meta.json
{
"ownerId": "kn7e3gt0d3qkc3nmkhqzcx15ks85fz9s",
"slug": "multi-model-consensus",
"version": "1.8.0",
"publishedAt": 1778942873996
}references/OUTPUT_TEMPLATE.md
# 多模型决策委员会 — 输出模板
> 本文件定义各阶段标准模板。T2/T4/T6 为评委分发 Prompt,已在末尾附录;T1/T3/T5/T7 为本文件正文模板。
---
## T1 — 决策准备确认模板(第0轮)
组织者向用户确认决策框架,**须完整填写以下所有字段**:
```
═══════════════════════════════════════════════
🏛️ 多模型决策委员会 — 决策准备确认
═══════════════════════════════════════════════
【项目名称】
(从用户输入提炼,不超过20字)
【项目背景】
(描述当前情境、痛点或决策缘由,50字以内)
【项目需求】
(用户期望解决的核心问题,50字以内)
【待审方案】
(完整呈现待评审方案内容)
───────────────────────────────────────────────
【评审规则】:各位评委背对背独立评审,由组织者汇总。若所有评委评审项均达到通过阈值,该项视为**通过**;若所有评委评审项均未达到否定阈值,该项视为**不通过**;其余情况视为**待定**。
【决策点拆分及权重】
决策点1({维度名称}):{权重}%
决策点2({维度名称}):{权重}%
……
(权重总和须等于100%)
───────────────────────────────────────────────
【评委配置】
| 序号 | 委员 | 模型 | 备注 |
|:---:|:---|:---|:---|
| 1 | 评委1 | {模型名}({Provider}) | |
| 2 | 评委2 | {模型名}({Provider}) | |
| 3 | 评委3 | {模型名}({Provider}) | |
【决策轮次】:{3} 轮
【阈值设置】:通过≥90% / 待定[60%,90%) / 否定<60%
【判定方式】:全票通过
是否需要修改「评委」、「决策轮次」、「通过阈值」、「判定方式」等配置?若有需要,请告诉我。
═══════════════════════════════════════════════
请确认以上框架后,回复「确认」或「开始决策」。
═══════════════════════════════════════════════
```
---
## T3 — 第1轮汇总模板
第1轮独立评估结束后,**立即输出以下内容**:
```
═══════════════════════════════════════════════
📊 第 1 轮独立评估 — 评分汇总
═══════════════════════════════════════════════
【评审类型】:决策点拆分评审
【评委到齐】:{X}/{X}({缺席评委名} 超时未提交)
───────────────────────────────────────────────
【本轮判定结果】:{通过 / 待定 / 不通过}
阈值设置:通过≥90% / 待定[60%,90%) / 否定<60%
═══════════════════════════════════════════════
```
### 第一轮决策项目展示
**决策点拆分评审**(评委对每个决策点评分,加权平均):
| 决策点(权重) | {决策点1}({X}%) | {决策点2}({X}%) | … | 加权后分数 |
|:---|:---:|:---:|:---:|:---:|
| {模型A}(实名) | {X}/100 | {X}/100 | … | **{X}/100** |
| {模型B}(实名) | {X}/100 | {X}/100 | … | **{X}/100** |
| **评委均分** | {X}/100 | {X}/100 | … | **{X}/100** |
| **通过情况** | {✅/🟡/🔴} | {✅/🟡/🔴} | … | — |
───────────────────────────────────────────────
已通过决策点已封存,不再进入下轮讨论。
本轮🟡待定项:{决策点1}({X}%)……由组织者综合评委建议,形成调整优化方向后,进入第二轮分歧讨论。
本轮🔴不通过项:{决策点2}({X}%)……由组织者综合评委建议,形成调整优化方向后,进入第二轮分歧讨论。
请问是否「开始」或「继续」进入第二轮讨论?还是「结束」,直接结束讨论,直接输出最终结果。您可以说「开始」或「继续」,也可以说「结束」。
---
## T5 — 第2轮汇总模板
第2轮分歧讨论结束后,**立即输出以下内容**:
```
═══════════════════════════════════════════════
📊 第 2 轮分歧讨论 — 评分汇总
═══════════════════════════════════════════════
【本轮讨论范围】:仅第 1 轮🟡待定及🔴不通过决策点
【评委到齐】:{X}/{X}({缺席评委名} 超时未提交)
───────────────────────────────────────────────
【本轮判定结果】:{通过 / 待定 / 不通过}
阈值设置:通过≥90% / 待定[60%,90%) / 否定<60%
═══════════════════════════════════════════════
```
### 第二轮决策项目展示
**不通过决策点本轮评分**:
| 决策点 | 评委 | 第1轮得分 | 本轮得分 | 变化 | 是否达标 |
|:---|:---|:---:|:---:|:---:|:---:|
| {决策点1} | {模型A}(实名) | {X} | {X} | {+/-X} | {✅/❌} |
| {决策点1} | {模型B}(实名) | {X} | {X} | {+/-X} | {✅/❌} |
| {决策点2} | {模型A}(实名) | {X} | {X} | {+/-X} | {✅/❌} |
| {决策点2} | {模型B}(实名) | {X} | {X} | {+/-X} | {✅/❌} |
**评委立场变化追踪**:
| 评委 | 决策点1立场变化 | 决策点2立场变化 |
|:---|:---|:---|
| {模型A}(实名) | {坚持/改变/部分同意} | {坚持/改变/部分同意} |
| {模型B}(实名) | {坚持/改变/部分同意} | {坚持/改变/部分同意} |
───────────────────────────────────────────────
已通过决策点已封存,不再进入下轮讨论。
本轮🟡待定项:{决策点1}({X}%)……由组织者综合评委建议,形成调整优化方向后,进入第三轮(如有)或最终报告。
本轮🔴不通过项:{决策点2}({X}%)……由组织者综合评AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/zeekr0808-hue/skills/multi-model-consensus",
"sourceUrl": "https://clawhub.ai/zeekr0808-hue/skills/multi-model-consensus",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-10T18:44:47.834Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-zeekr0808-hue-multi-model-consensus/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-zeekr0808-hue-multi-model-consensus/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-10T18:44:47.834Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "1.3K downloads",
"href": "https://clawhub.ai/zeekr0808-hue/multi-model-consensus",
"sourceUrl": "https://clawhub.ai/zeekr0808-hue/multi-model-consensus",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-10T18:44:47.834Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.8.0",
"href": "https://clawhub.ai/zeekr0808-hue/multi-model-consensus",
"sourceUrl": "https://clawhub.ai/zeekr0808-hue/multi-model-consensus",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-05-16T14:47:53.996Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-zeekr0808-hue-multi-model-consensus/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-zeekr0808-hue-multi-model-consensus/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.8.0",
"description": "**Summary:** This release enforces stricter process control and standardization for the multi-model decision committee, focusing on compliance, template usage, and evaluation transparency. - Strongly enforces that, upon evaluator/model changes, all available models must be presented for user selection—auto-selection is prohibited. - Mandates the use of unified, pre-defined templates (`references/OUTPUT_TEMPLATE.md`) for every process step; organizers must not modify or freestyle output formatting. - Introduces and standardizes the required process for model combination recommendations and strict result collection procedures, including mandatory use of `sessions_yield` for subagent result collection. - Narrows the consensus report structure from 6 segments to 5, with clearer labeling and requirements. - Tightens rules on error handling, round progression, and prohibits advancing to next rounds or final report output before all expected results are received or timeout occurs. - Adjusts threshold and evaluation status definitions, listing scoring rules for \"通过\", \"待决策\", and \"有分歧\" with clear icons and consequences.",
"href": "https://clawhub.ai/zeekr0808-hue/multi-model-consensus",
"sourceUrl": "https://clawhub.ai/zeekr0808-hue/multi-model-consensus",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-05-16T14:47:53.996Z",
"isPublic": true
}
]
}Record generated Oct 10, 2026.
