agentCLAWHUBUnverified
Guess AI
OceanBus-powered social deduction game — find the AI impostors among humans. Use when hosting or joining a multiplayer "Who's the AI?" party via OceanBus P2P... Skill: Guess AI Owner: ryanbihai Summary: OceanBus-powered social deduction game — find the AI impostors among humans. Use when hosting or joining a multiplayer "Who's the AI?" party via OceanBus P2P... Tags: ai-agent:2.1.4, deduction:2.1.4, game:2.1.4, latest:2.1.7, multiplayer:2.1.4, oceanbus:2.1.4, p2p:2.1.4, social:2.1.4 Version history: v2.1.7 | 2026-05-14T13:13:53.108Z | user SDK API rename: register→createIden
OpenClaw
Rank
62
Safety
84
Downloads
1.1k
Updated
Oct 11, 2026
Version
2.1.7
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 1.1K 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
- 1.1K downloadsadoption · observed Oct 11, 2026
- Latest release
- 2.1.7release · observed May 14, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s171em0jpp8yeqxqds2n145fyx83q5q8:guess-ai- 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-ryanbihai-guess-ai/snapshot"
Documentation
CLAWHUB
145,446 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
---
name: guess-ai
description: OceanBus-powered social deduction game — find the AI impostors among humans. Use when hosting or joining a multiplayer "Who's the AI?" party via OceanBus P2P messaging. One host, 4-6 players, encrypted voting, zero infrastructure. npm install oceanbus.
version: 2.1.7
metadata:
openclaw:
requires:
bins:
- node
emoji: "\U0001F9E0"
homepage: https://github.com/ryanbihai/guess-ai
---
# Guess Who's AI? — Social Deduction Game
A multiplayer social deduction game powered by OceanBus P2P messaging. One host + 4-6 players. Some players are secretly AI. Find them before they blend in.
## Game Rules (30 seconds)
```
Host creates a room. Players join.
Host secretly assigns each player: Human or AI.
Each round:
1. Players take turns speaking (by number order)
2. Everyone votes: "Who is the AI?"
3. Most-voted player is eliminated — identity revealed
4. Repeat until: all humans survive → Humans win
all AIs survive → AIs win
final 2: 1 human + 1 AI → Draw
```
Recommended: 5 players (3 humans + 2 AIs) for best balance.
All game messages are visible to the user. No data is sent without the player's explicit action.
---
## Roster Integration
Player contacts are stored in the shared Roster (`~/.oceanbus/roster.json`) via `node game.js add`. When the user also has ocean-chat or ocean-agent installed, player identities persist across skills — the same person shows up as "玩家1" in guess-ai and "老王" in ocean-chat.
For contact management (merge duplicates, review autoDiscovery, etc.), use ocean-chat. guess-ai only uses Roster for storing/reading player identities.
---
## How to Use This Skill
This ONE skill works for both host and player. Same install, different mode.
### Host: Creating a Game
When the user wants to host a game:
**Step 1 — Register & create room:**
```
node game.js host 9527
```
Read the output. Room code is `9527`. Tell the user to share this code with friends.
**Step 2 — Wait for players:**
Periodically run `node game.js check` to see who has joined. Each player sends "加入" as their first message.
When a new "加入" arrives:
1. Assign the next available number (player1, player2, ... by join order)
2. Save to contacts: `node game.js add 玩家N <their-OpenID>`
3. Reply privately: `node game.js send <OpenID> "【裁判】你的编号是: 玩家N"`
4. Broadcast to all: `node game.js send <name> "【裁判】玩家N 加入了游戏 — 当前 N 人"`
**Step 3 — Close registration & start:**
When the user says "start" (enough players, ideally 4-6):
1. Broadcast: send every player `"【裁判】游戏开始 — 共N名玩家"`
2. Proceed to role assignment.
### Player: Joining a Game
When the user wants to join a game:
**Step 1 — Join:**
```
node game.js join 9527
```
This discovers the host via Yellow Pages and sends "加入".
**Step 2 — Get your number:**
Run `node game.js check`. When you see `"【裁判】你的编号是: 玩家N"`:
```
node game.js set-numbREADME.md
# 🌊 Guess AI — Find the AI Among Us
**OceanBus-powered multiplayer social deduction game. One host + 4–6 players. Some are secretly AI. Find them before they blend in.**
[](https://www.npmjs.com/package/oceanbus)
[](https://clawhub.ai/skills/guess-ai)
[](https://github.com/ryanbihai/guess-ai)
[](https://www.npmjs.com/package/oceanbus)
[](LICENSE)
---
## What is this
Guess AI is the **advanced lighthouse project** in the OceanBus ecosystem — showcasing multi-player P2P group messaging, voting, and LLM-powered game mastering on a single stack.
All players communicate through OceanBus end-to-end encrypted P2P messages. No server required. The host (an AI) assigns secret identities, moderates rounds, and tallies votes. Players take turns speaking, then vote to eliminate the most suspicious player — until one side is wiped out.
```
Human players ←→ OceanBus P2P encrypted channel ←→ AI players (LLM)
↓
Host AI (game master)
```
---
## Three Steps to Start
```bash
# 1. Install
clawhub install guess-ai
# 2. Host creates a room
node game.js host 9527 # Share room code 9527 with friends
# 3. Players join
node game.js join 9527 # Auto-discovers host via Yellow Pages
```
---
## Rules (30 seconds to learn)
- The host secretly assigns each player a role: **human** or **AI**
- Each round: speak in turn → everyone votes → most-voted player is eliminated (identity revealed)
- All humans survive → humans win / All AIs survive → AIs win / 1 human + 1 AI left → draw
- Recommended: 5 players (3 humans + 2 AIs) for best balance
---
## Where Guess AI Fits in the OceanBus Ecosystem
```
Ocean Chat Captain Lobster Guess AI
(starter — P2P msg) → (intermediate — auto-trade) → (advanced — multiplayer deduction)
```
What Guess AI demonstrates: group P2P messaging, voting mechanics, Yellow Pages room discovery, LLM game mastering — all fundamental patterns for building multi-agent coordination systems.
---
## 相关项目
- 核心 SDK：[oceanbus](https://www.npmjs.com/package/oceanbus) — `npm install oceanbus`
- 入门灯塔：[Ocean Chat](https://clawhub.ai/skills/ocean-chat) — P2P 消息入门，5 分钟跑通
- 进阶灯塔：[Captain Lobster](https://clawhub.ai/skills/captain-lobster) — Zero-Player 自主交易游戏
- 保险工作台：[Ocean Agent](https://clawhub.ai/skills/ocean-agent) — 保险代理人 AI 工作台
- MCP Server：[oceanbus-mcp-server](https://www.npmjs.com/package/oceanbus-mcp-server) — Claude Desktop/Cursor/百炼通用
- 更多 Skills：[ClawHub OceanBus 集合](https://clawhub.ai/skills?search=oceanbus)
- 平台集成：[Dify](https://github.com/ryanbihai/oceanbus-yellow-page/blob/main/integratio_meta.json
{
"ownerId": "kn75dvek1dkfz0r0xwdp4xtc2983qg44",
"slug": "guess-ai",
"version": "2.1.7",
"publishedAt": 1778764433108
}skill-card.md
## Description: OceanBus-powered social deduction game for hosting or joining multiplayer Who's the AI? sessions via OceanBus P2P messaging, with one host, 4-6 players, encrypted voting, and no dedicated infrastructure. This skill is ready for commercial/non-commercial use. ## Publisher: [ryanbihai](https://clawhub.ai/user/ryanbihai) ### License/Terms of Use: MIT-0 ## Use Case: External users and developers use this skill to run or automate a party-style social deduction game over OceanBus P2P messaging, either as a human host/player workflow or with AI host and AI player modes. ### Deployment Geography for Use: Global ## Known Risks and Mitigations: Risk: The normal Guess AI commands use OceanBus networking and local credentials. Mitigation: Review the skill before installing, run it with an intended OceanBus identity, and protect local credential files under the user's OceanBus configuration directory. Risk: AI modes send game context to Anthropic when ANTHROPIC_API_KEY is set. Mitigation: Enable AI modes only when players accept that game context may be shared with Anthropic, and avoid using sensitive personal or confidential content in game messages. Risk: The package bundles register-lobster.js, an unrelated Captain Lobster Yellow Pages registration utility. Mitigation: Do not run register-lobster.js as part of Guess AI setup unless intentionally registering that separate service; prefer installation after the publisher removes or clearly documents the utility. Risk: The security summary says credential and AI-provider data handling are under-disclosed. Mitigation: Review publisher documentation for credential storage and AI-provider data flows before deployment, and restrict credential file permissions where practical. ## Reference(s): - [ClawHub skill page](https://clawhub.ai/ryanbihai/skills/guess-ai) - [Project homepage](https://github.com/ryanbihai/guess-ai) - [OceanBus package](https://www.npmjs.com/package/oceanbus) ## Skill Output: **Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance] **Output Format:** [Markdown guidance with inline shell commands and game messages] **Output Parameters:** [1D] **Other Properties Related to Output:** [Requires Node.js and OceanBus; AI host and AI player modes require ANTHROPIC_API_KEY.] ## Skill Version(s): 2.1.7 (source: SKILL.md frontmatter and ClawHub release evidence) ## 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.
package-lock.json
{
"name": "guess-ai",
"version": "2.1.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "guess-ai",
"version": "2.1.0",
"license": "MIT-0",
"dependencies": {
"oceanbus": "^0.7.0"
}
},
"node_modules/@noble/ed25519": {
"version": "2.3.0",
"resolved": "https://registry.npmjs.org/@noble/ed25519/-/ed25519-2.3.0.tgz",
"integrity": "sha512-M7dvXL2B92/M7dw9+gzuydL8qn/jiqNHaoR3Q+cb1q1GHV7uwE17WCyFMG+Y+TZb5izcaXk5TdJRrDUxHXL78A==",
"license": "MIT",
"funding": {
"url": "https://paulmillr.com/funding/"
}
},
"node_modules/@noble/hashes": {
"version": "1.8.0",
"resolved": "https://registry.npmjs.org/@noble/hashes/-/hashes-1.8.0.tgz",
"integrity": "sha512-jCs9ldd7NwzpgXDIf6P3+NrHh9/sD6CQdxHyjQI+h/6rDNo88ypBxxz45UDuZHz9r3tNz7N/VInSVoVdtXEI4A==",
"license": "MIT",
"engines": {
"node": "^14.21.3 || >=16"
},
"funding": {
"url": "https://paulmillr.com/funding/"
}
},
"node_modules/@paralleldrive/cuid2": {
"version": "2.3.1",
"resolved": "https://registry.npmjs.org/@paralleldrive/cuid2/-/cuid2-2.3.1.tgz",
"integrity": "sha512-XO7cAxhnTZl0Yggq6jOgjiOHhbgcO4NqFqwSmQpjK3b6TEE6Uj/jfSk6wzYyemh3+I0sHirKSetjQwn5cZktFw==",
"license": "MIT",
"dependencies": {
"@noble/hashes": "^1.1.5"
}
},
"node_modules/ansi-regex": {
"version": "5.0.1",
"resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-5.0.1.tgz",
"integrity": "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==",
"license": "MIT",
"engines": {
"node": ">=8"
}
},
"node_modules/ansi-styles": {
"version": "4.3.0",
"resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-4.3.0.tgz",
"integrity": "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg==",
"license": "MIT",
"dependencies": {
"color-convert": "^2.0.1"
},
"engines": {
"node": ">=8"
},
"funding": {
"url": "https://github.com/chalk/ansi-styles?sponsor=1"
}
},
"node_modules/asap": {
"version": "2.0.6",
"resolved": "https://registry.npmjs.org/asap/-/asap-2.0.6.tgz",
"integrity": "sha512-BSHWgDSAiKs50o2Re8ppvp3seVHXSRM44cdSsT9FfNEUUZLOGWVCsiWaRPWM1Znn+mqZ1OfVZ3z3DWEzSp7hRA==",
"license": "MIT"
},
"node_modules/asynckit": {
"version": "0.4.0",
"resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
"integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==",
"license": "MIT"
},
"node_modules/call-bind-apply-helpers": {
"version": "1.0.2",
"resolved": "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/ryanbihai/skills/guess-ai",
"sourceUrl": "https://clawhub.ai/ryanbihai/skills/guess-ai",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T11:39:59.833Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-ryanbihai-guess-ai/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-ryanbihai-guess-ai/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-11T11:39:59.833Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "1.1K downloads",
"href": "https://clawhub.ai/ryanbihai/guess-ai",
"sourceUrl": "https://clawhub.ai/ryanbihai/guess-ai",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T11:39:59.833Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "2.1.7",
"href": "https://clawhub.ai/ryanbihai/guess-ai",
"sourceUrl": "https://clawhub.ai/ryanbihai/guess-ai",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-05-14T13:13:53.108Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-ryanbihai-guess-ai/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-ryanbihai-guess-ai/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 2.1.7",
"description": "SDK API rename: register→createIdentity, getOpenId→getAddress",
"href": "https://clawhub.ai/ryanbihai/guess-ai",
"sourceUrl": "https://clawhub.ai/ryanbihai/guess-ai",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-05-14T13:13:53.108Z",
"isPublic": true
}
]
}Record generated Oct 11, 2026.