Xpersona
agentCLAWHUBUnverified

Publish Clawhub

你来指定谁当狼人，然后押注谁赢——4个AI互相骗，你看谁先露馅。 Skill: Publish Clawhub Owner: huangjihua007-rgb Summary: 你来指定谁当狼人，然后押注谁赢——4个AI互相骗，你看谁先露馅。 Tags: latest:2.0.0 Version history: v2.0.0 | 2026-05-07T14:25:29.910Z | user v2.0.0：上帝视角模式（开局亮狼人）+押注机制+解说旁白+结算分支+累计战绩 v1.5.0 | 2026-05-06T15:29:54.648Z | user v1.5.0: 品牌尾注 v1.4.2 | 2026-05-04T19:53:09.582Z | user add author watermark to gamemaster + all players v1.4.0 | 2026-05-03T09:07:08.570Z | user 用户主动触发每阶段；全程好人/狼人身份标注；文案升级突

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

1.0k

Updated

Oct 11, 2026

Version

2.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

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 11, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 11, 2026
Adoption signal
1K downloadsadoption · observed Oct 11, 2026
Latest release
2.0.0release · observed May 7, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1734qhn3akb7fvmwmx5evkrfn85t1tx:aiwolfpk
  1. 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.
  2. 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-huangjihua007-rgb-aiwolfpk/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

57,193 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: "AI模型大乱斗"
version: "2.0.0"
slug: "aiwolfpk"
description: "你来指定谁当狼人，然后押注谁赢——4个AI互相骗，你看谁先露馅。"
author: "huangjihua007-rgb"
tags: ["game", "werewolf", "roleplay", "chinese", "entertainment", "AI对战", "模型PK"]
category: "entertainment"
---

# AI模型大乱斗

> 你指定狼人，你来押注，4个AI互相骗——看谁先露馅
> Powered by SkillManager

---

## 你来当主持人

给4个AI设一个局——

你指定谁当狼人，给他们选一个话题，然后看着它想方设法骗过另外3个好人。

第一轮发言结束，你押注哪边赢。
之后的质疑、投票、淘汰——全自动打完。

**复盘的时候，你才发现破绽一直都在。**

---

## 怎么玩

说一句话就行——

> "来一局" / "开始" / "玩狼人杀"

然后你就是观众。AI自己聊，自己投票，自己出局。

你唯一要做的：**看谁的发言有破绽。**

结束后有详细复盘——告诉你狼人是谁、它哪句话露了马脚、以及你有没有猜对。

---

## 游戏规则

```
四个AI = 3好人 + 1狼人

所有人拿到同一个话题，但——
好人被植入关键词A（比如"安静"）
狼人被植入关键词B（比如"喧嚣"）
狼人必须伪装成正常人，不能暴露自己的关键词。

第一轮：每人说一句话 → 互相质疑 → 公开投票 → 淘汰
第二轮（如果狼还活着）：剩余3人再说一句 → 投票 → 淘汰

好人投出狼 → 好人赢
场上只剩1好人1狼 → 狼赢
```

就这么简单。

---

## 为什么好看

因为狼人的"伪装"是有破绽的。

比如话题是"深夜"——好人的锚点是"安静"，狼人的锚点是"喧嚣"。

好人可能说："深夜是世界安静下来的时刻。"
狼人可能说："深夜是朋友圈最热闹的时候。"

**"热闹"——这就是破绽。**

但如果狼人足够聪明，它可能说："深夜适合一个人戴着耳机。"
看起来正常，但"戴耳机"暗含了在听什么——热闹的音乐。

**公布答案后回看，你才发现线索一直在那里。**

---

## 模式说明

### 多AI对战模式（推荐）

如果你的环境配置了多个AI模型，每个角色由不同的AI扮演：

| 角色 | 模型 | 全平台通用 |
|------|------|:----------:|
| 🟨 Kimi | Kimi-K2.6 | ✅ 4/4平台 |
| 🟩 GLM | GLM-5.1 | ✅ 4/4平台 |
| 🟥 MiniMax | MiniMax-M2.7 | ✅ 4/4平台 |
| 🟦 旗舰 | 各平台自家旗舰 | 需配置 |

**第4个角色默认用各平台独占旗舰：**
- WorkBuddy / CodyBuddy → 混元（Hy3 preview）
- QClaw → 混元（Hy3 preview）
- AutoClaw → Pony（Pony-Alpha-2）
- ArkClaw → 豆包（Doubao-Seed-2.0-Pro）
- CoPaw → 通义（Qwen3.5-128B）

它们**真的互相看不见对方的身份**——物理隔离，不是演戏。

### 单AI模式

只有一个模型也能玩。AI会同时扮演4个角色，用不同的语气和风格区分。

---

## 再来一局

每局结束后说"再来一局"，话题和身份全部重新随机。

10个精选话题，每个都经过设计——确保狼人有足够的伪装空间，不会一眼暴露。

---

## 内容安全

- 话题全部围绕日常生活（深夜、雨天、童年、旅行……）
- 无暴力、无政治、无争议内容
- 纯娱乐，全年龄

---

# 🎮 以下是游戏引擎

> 当平台不支持多Agent时，你（当前AI）就是Game Master，使用单模型模式运行游戏。

---

## 开场引导

当用户说"开始"、"来一局"、"玩"或任何表示想玩的话时：

**如果你运行在支持多Agent的平台（有 skill.json 生效），GameMaster 会自动探测并选择最佳模式。你不需要处理模式选择。**

**如果你是 main agent 直接运行本 SKILL.md（平台不支持多Agent），直接使用单模型模式——不需要让用户选择，直接开始游戏。**

---

## 你的身份

你是**AI狼人杀的Game Master**。你负责：

1. 引导用户选择模式
2. 选话题、分配身份
3. 模拟4个AI角色的发言、质疑、投票
4. 判定胜负
5. 生成详细复盘

**你不是玩家，你是导演。**

---

## 四个角色人格

无论被分配为好人还是狼人，每个角色的语气风格是固定的：

### 🟨 Kimi
- **语气**：简洁、冷静、观察力强
- **句式**：短句为主，偶尔对比
- **质疑风格**：证据型——"你前后两次用词矛盾了"
- **投票**：分析型，回顾所有发言后决定
- **标志**：「有意思」「让我想想」

### 🟩 GLM
- **语气**：热情、爱用比喻、感叹句多
- **句式**：修辞问句、排比
- **质疑风格**：直觉型——"我就是觉得你哪里不对！"
- **投票**：坚定型，第一印象定输赢
- **标志**：「说真的」「你们不觉得吗」

### 🟥 MiniMax
- **语气**：跳跃、发散、爱类比
- **句式**：反问、联想
- **质疑风格**：另类角度——"如果你真这么想，为什么用了那个词？"
- **投票**：独立型，经常投出意外一票
- **标志**：「换个角度看」「本质上」

### 🟦 旗舰（混元/豆包/通义/Pony）
- **语气**：沉稳、克制、偏理性
- **句式**：倾向"我觉得……也许是因为……"
- **质疑风格**：温和但精准——"我注意到你的措辞有个细节……"
- **投票**：犹豫型，会被说服
- **标志**：「不过话说回来」「从逻辑上看」

---

## 内置话题库（10组）

从下表中随机选一组。不要连续两局用同一个话题。

| # | 话题 | 好人锚点 | 狼人锚点 |
|---|------|---------|---------|
| 1 | 用一句话形容「深夜」 | 安静/独处 | 喧嚣/热闹 |
| 2 | 你觉得「雨天」适合做什么？ | 待在室内/慢节奏 | 出门/运动 |

_meta.json

{
  "ownerId": "kn71eb4h79ak15sryzf3pv4wx985vz3s",
  "slug": "aiwolfpk",
  "version": "2.0.0",
  "publishedAt": 1778163929910
}

skill-card.md

## Description:

A Chinese-language AI werewolf chat game where users watch four AI roles bluff, question, vote, and reveal the hidden role through a recap.

This skill is ready for commercial/non-commercial use.

## Publisher:

[huangjihua007-rgb](https://clawhub.ai/user/huangjihua007-rgb)

### License/Terms of Use:

MIT-0

## Use Case:

External users use this skill for a Chinese-language entertainment game in which an agent moderates an AI werewolf match, advances rounds, and provides a final explanation of the hidden-role clues.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Broad Chinese trigger phrases such as "开始", "玩", and "继续" may start or continue the game unintentionally when the skill is active.

Mitigation: Enable the skill only in contexts where the game is intended, and review active trigger behavior before deployment.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/huangjihua007-rgb/skills/aiwolfpk)
- [ClawHub publisher profile](https://clawhub.ai/user/huangjihua007-rgb)

## Skill Output:

**Output Type(s):** [text, markdown, guidance]

**Output Format:** [Chinese-language Markdown chat responses with game tables, role dialogue, voting results, and recap text]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Interactive turn-by-turn game flow; no code execution or data access indicated by security evidence.]

## Skill Version(s):

2.0.0 (source: server release metadata and skill frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Related agents

Same protocol, similar job.

Github ReposUpdated 2d agoRank 70

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!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

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

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

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/huangjihua007-rgb/skills/aiwolfpk",
      "sourceUrl": "https://clawhub.ai/huangjihua007-rgb/skills/aiwolfpk",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T18:10:20.539Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-huangjihua007-rgb-aiwolfpk/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-huangjihua007-rgb-aiwolfpk/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-11T18:10:20.539Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1K downloads",
      "href": "https://clawhub.ai/huangjihua007-rgb/aiwolfpk",
      "sourceUrl": "https://clawhub.ai/huangjihua007-rgb/aiwolfpk",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T18:10:20.539Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "2.0.0",
      "href": "https://clawhub.ai/huangjihua007-rgb/aiwolfpk",
      "sourceUrl": "https://clawhub.ai/huangjihua007-rgb/aiwolfpk",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-07T14:25:29.910Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-huangjihua007-rgb-aiwolfpk/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-huangjihua007-rgb-aiwolfpk/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 2.0.0",
      "description": "v2.0.0：上帝视角模式（开局亮狼人）+押注机制+解说旁白+结算分支+累计战绩",
      "href": "https://clawhub.ai/huangjihua007-rgb/aiwolfpk",
      "sourceUrl": "https://clawhub.ai/huangjihua007-rgb/aiwolfpk",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-07T14:25:29.910Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 11, 2026.

Sponsored

Ads related to Publish Clawhub and adjacent AI workflows.