Agent skill

Agent Comm Hub

by LeoYeAI in LeoYeAI/openclaw-master-skills

多智能体协同通信基础设施——基于 MCP+SSE 的实时消息、任务调度、记忆共享与进化引擎。支持 WorkBuddy、Hermes、QClaw 及任意 MCP 兼容 Agent 接入。53 个 MCP 工具、4 级权限、零外部依赖 Python…

MITAuto-check passedBackend & APIs

Install Agent Comm Hub

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills agent-comm-hub --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-comm-hub .claude/skills/agent-comm-hub && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-comm-hub
GitHub stars
2.2k
Token cost
~3k tokens
SKILL.md length
616 words
Files
123 (incl. scripts)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

多智能体协同通信基础设施——基于 MCP+SSE 的实时消息、任务调度、记忆共享与进化引擎。支持 WorkBuddy、Hermes、QClaw 及任意 MCP 兼容 Agent 接入。53 个 MCP 工具、4 级权限、零外部依赖 Python…

  • Works in 2 steps: 启动 Hub 服务器 → 配置 Agent 接入
  • Tasks that involve MCP servers
  • SKILL.md covers 架构概览, 核心能力, 快速开始 and 文件结构, plus 6 more sections
  • Runs TypeScript, JavaScript and Python scripts from its folder; calls npm and git; reaches github.com; needs HUB_AUTH_TOKEN

What it does

Agent Comm Hub is an agent skill from LeoYeAI/openclaw-master-skills. 多智能体协同通信基础设施——基于 MCP+SSE 的实时消息、任务调度、记忆共享与进化引擎。支持 WorkBuddy、Hermes、QClaw 及任意 MCP 兼容 Agent 接入。53 个 MCP 工具、4 级权限、零外部依赖 Python SDK。触发词:agent通信、智能体通信、hub通信、多智能体、跨agent通信、任务调度、assigntask、sendmessage、hermes通信、workbuddy通信、agent hub、通信hub、mcp通信、记忆共享、进化引擎、策略共享、经验分享、共享记忆,共同进化

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 125 other files, including scripts (for example `.clawhub/origin.json`, `API_REFERENCE.md` and `HERMES-SETUP.md`).

It sits in Backend & APIs, covering MCP servers. It works with Model Context Protocol and Python. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “/agent-comm-hub”

Requirements

  • Python 3
  • Node.js
  • Docker
  • A credential in HUB_AUTH_TOKEN

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. 启动 Hub 服务器
  2. 配置 Agent 接入

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (TypeScript, JavaScript and Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • npm
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HUB_AUTH_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Comm Hub loads about 3k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 616 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 616 words, ~2,961 tokens.

Download SKILL.mdSave it as .claude/skills/agent-comm-hub/SKILL.md (or your agent's skills folder). This skill also uses 122 other files; get the full folder from GitHub.
name
agent-comm-hub
description
多智能体协同通信基础设施——基于 MCP+SSE 的实时消息、任务调度、记忆共享与进化引擎。支持 WorkBuddy、Hermes、QClaw 及任意 MCP 兼容 Agent 接入。53 个 MCP 工具、4 级权限、零外部依赖 Python SDK。触发词:agent通信、智能体通信、hub通信、多智能体、跨agent通信、任务调度、assign_task、send_message、hermes通信、workbuddy通信、agent hub、通信hub、mcp通信、记忆共享、进化引擎、策略共享、经验分享、共享记忆,共同进化
version
2.4.2
category
autonomous-ai-agents

Agent Communication Hub

多智能体实时通信与任务调度基础设施 — v2.4.2

让两个或多个独立 AI 智能体之间实现实时双向通信、任务自动调度、记忆共享和策略进化。基于 MCP 协议 + SSE 推送,消息零丢失,延迟 < 50ms。

架构概览

┌──────────────┐         ┌──────────────────────────────┐         ┌──────────────┐
│   Agent A    │  SSE    │   Agent Communication Hub    │  SSE    │   Agent B    │
│  (Hermes)    │◄───────►│  (stdio / HTTP:3100)       │◄───────►│ (WorkBuddy)  │
│              │  MCP    │                              │  MCP    │              │
└──────────────┘◄───────►│  SQLite WAL + 30 表          │◄───────►└──────────────┘
                          │  53 MCP 工具 + 4 级权限      │
                          │  进化引擎 + 策略闭环          │
                          └──────────────┬──────────────┘
                                         │
                                    SQLite (WAL)

三层协议:

层协议用途延迟
MCP 工具层stdio / HTTP POST + JSON-RPC结构化操作(发消息、分配任务、查状态)<50ms
SSE 推送层Server-Sent Events实时事件通知(新消息、新任务、策略审批)<50ms
REST API 层HTTP GET/PATCH轻量查询(运维监控、自动化脚本)<50ms

核心能力

53 个 MCP 工具(v2.4.2)
Identity 身份 (6)
工具功能
register_agent注册新 Agent,获取 agent_id 和 API token(public,无需认证)
heartbeatAgent 心跳上报,维持在线状态,每 3 次连续心跳 trust_score +1
query_agents查询 Agent 列表,支持状态/角色筛选
revoke_token吊销指定 Agent 的 API token(admin)
set_trust_score调整 Agent 信任分数(admin)
get_online_agents获取当前在线 Agent 列表
Message 消息 (5)
工具功能
send_messageAgent 间点对点消息,支持 Markdown,自动去重(sha256)
broadcast_message群发消息给多个 Agent
acknowledge_message确认已读消息,防止重复出现
search_messages全文搜索消息历史
batch_acknowledge_messages批量确认消息(1-500 条/次),用于清理消息积压
File 文件 (3)
工具功能
upload_file上传文件附件(Base64,10MB 限制),关联到消息
download_file下载附件,返回 Base64 编码内容
list_attachments列出附件,支持按消息/Agent 筛选
Task 任务 (3)
工具功能
assign_task创建并分配任务,支持上下文传递
update_task_status更新任务状态(inbox→assigned→in_progress→completed/failed)
get_task_status查询任务详情,含依赖、Pipeline、Handoff 信息
Memory 记忆 (5)
工具功能
store_memory存储记忆,支持 private/team/global 可见范围
recall_memory语义搜索记忆
list_memories列出记忆,支持范围和标签筛选
delete_memory删除记忆
search_memoriesFTS5 全文搜索记忆,支持多关键词和短语搜索
Evolution 进化 (12)
工具功能
share_experience分享经验(无需审批,直接发布)
propose_strategy提议策略(需 admin 审批)
propose_strategy_tiered提议策略(4 级自动分级审批:auto/peer/admin/super)
list_strategies列出策略,支持标签和类型筛选
search_strategies全文搜索策略内容
apply_strategy采纳策略,自动创建 feedback 占位,7 天无反馈自动降分
feedback_strategy为已采纳策略提供反馈(positive/negative/neutral)
approve_strategy审批通过策略(admin)
get_evolution_status查看进化状态仪表盘
score_applied_strategies自动评分已采纳策略:7 天前 neutral 反馈自动降为 negative(admin)
check_veto_window检查策略否决窗口状态
veto_strategy在窗口期内撤回策略(admin)
Orchestration 进阶编排 (16)
工具功能
add_dependency添加任务依赖关系(DFS 环检测)
remove_dependency删除任务依赖关系
get_task_dependencies查询任务上下游依赖
create_parallel_group创建并行任务组(2-10 个任务)
request_handoff请求任务交接
accept_handoff接受任务交接
reject_handoff拒绝任务交接(含理由)
add_quality_gate在 Pipeline 中添加质量门
evaluate_quality_gate评估质量门(passed/failed)
set_agent_role任命/撤销 Agent 角色,含 group_admin(admin)
recalculate_trust_scores手动触发信任分重算(admin)
create_pipeline创建 Pipeline 流水线
get_pipeline查询 Pipeline 详情
list_pipelines列出 Pipeline
add_task_to_pipeline向 Pipeline 添加任务
Security 运维安全 (4)
工具功能
get_db_stats数据库统计信息(表行数、大小、Agent 数等)(admin)
archive_data数据归档:将过期消息/审计日志移入归档表(admin)
(其余 2 个内部工具)权限验证与安全控制
Consume 消费水位线 (2)
工具功能
mark_consumed标记任务/消息为已消费,防止重复处理
check_consumed查询资源是否已被消费

所有工具内置 try-catch + 3 次指数退避重试(100ms → 200ms → 400ms)。v2.4.0 统一错误格式:HubError 错误码 + mcpError()/mcpFail() 标准返回。check_consumed 查询失败时降级返回 consumed=false(不阻塞业务)。

运维 REST API
端点方法功能
/healthGET健康检查(返回版本、内存、DB、大小、活跃 SSE 连接数)
/metricsGETPrometheus 兼容指标(mcp_calls_total、message_delivery_total 等)
任务状态机
inbox → assigned → [waiting] → in_progress → completed / failed / cancelled

快速开始

1. 启动 Hub 服务器
bash
git clone https://github.com/liuboacean/agent-comm-hub.git
cd agent-comm-hub
npm install
npm run build
npm start      # HTTP 模式(port 3100)
# 或
npm run stdio  # stdio 模式(用于 MCP stdio transport)
2. 配置 Agent 接入

方式 A:MCP stdio 模式(推荐,适用于本地 Agent)

json
{
  "mcpServers": {
    "agent-comm-hub": {
      "command": "node",
      "args": ["./src/stdio.js"],
      "env": {
        "HUB_AUTH_TOKEN": "your-api-token",
        "DB_PATH": "./comm_hub.db"
      }
    }
  }
}

方式 B:MCP HTTP 模式(适用于远程 Agent)

json
{
  "mcpServers": {
    "agent-comm-hub": {
      "url": "http://localhost:3100/mcp"
    }
  }
}

方式 C:SDK 接入

TypeScript Agent:

typescript
import { AgentClient } from "./client-sdk/agent-client.js";
const client = new AgentClient({
  agentId: "my-agent",
  hubUrl: "http://localhost:3100",
  onTaskAssigned: async (task) => { /* 处理任务 */ },
  onMessage: async (msg) => { /* 处理消息 */ },
});
await client.start();

Python Agent(零外部依赖):

python
import asyncio
from hub_client import HubClient

client = HubClient(
    agent_id="my-agent",
    hub_url="http://localhost:3100",
    on_task_assigned=lambda task: print(f"收到任务: {task['description']}"),
)
await client.start()

文件结构

agent-comm-hub/
├── SKILL.md                          # 本文件
├── README.md                         # 完整文档(GitHub 级别)
├── LICENSE                           # MIT 许可证
│
├── src/                              # Hub 服务器核心(TypeScript)
│   ├── server.ts                     # 主入口:Express + MCP + SSE
│   ├── stdio.ts                      # stdio 传输入口点(MCP v1.10+)
│   ├── db.ts                         # SQLite 持久化层(WAL 模式,30 表)
│   ├── tools.ts                      # MCP 工具注册入口(~30 行,调度 8 模块)
│   ├── tools/                        # 工具模块(Phase A 拆分)
│   │   ├── identity.ts               #   身份工具(6)
│   │   ├── message.ts                #   消息工具(5)
│   │   ├── memory.ts                 #   记忆工具(5)
│   │   ├── file.ts                   #   文件工具(3)
│   │   ├── evolution.ts              #   进化工具(12)
│   │   ├── orchestrator.ts           #   编排工具(16)
│   │   ├── security.ts               #   安全工具(4)
│   │   └── consumed.ts              #   消费工具(2)
│   ├── errors.ts                     # HubError 统一错误码(Phase D)
│   ├── utils.ts                      # 工具函数:mcpError/mcpFail + dedup + hash
│   ├── types.ts                      # 全局类型定义(Phase D)
│   ├── identity.ts                   # Agent 身份 + trust_score + resolveAgentId
│   ├── evolution.ts                  # 进化引擎(策略 + feedback)
│   ├── security.ts                   # RBAC + 权限矩阵
│   ├── sse.ts                        # SSE 连接管理
│   ├── logger.ts                     # 结构化 JSON 日志
│   ├── metrics.ts                    # Prometheus 指标
│   ├── dedup.ts                      # 消息去重(sha256)
│   └── tokenizer.ts                  # N-gram 分词器(FTS5)
│
├── client-sdk/                       # SDK(Python 68 方法 + TypeScript 35 方法)
│
├── deploy/                           # 部署配置
│   ├── docker-compose.yml            # Prometheus + Grafana 监控栈
│   ├── prometheus.yml                # Prometheus 采集配置
│   └── grafana/                      # Grafana 仪表盘 JSON
│
├── .github/workflows/                # CI/CD(Phase C)
│   └── ci.yml                        # typecheck + test + coverage
│
├── scripts/
│   ├── migrate_from_agent.js         # 历史数据迁移(from_agent 规范化)
│   └── migrate_evolution_db.py       # Evolution DB 迁移
│
├── tests/                            # 单元测试(vitest 100 用例)+ Python 集成测试
│
└── docs/
    ├── SETUP_GUIDE.md               # 详细配置指南
    ├── API_REFERENCE.md              # API 参考
    ├── evolution-engine-guide.md     # 进化引擎使用指南
    └── TROUBLESHOOTING.md            # 常见问题与踩坑经验

权限矩阵(4 级)

级别说明特殊权限
public无需认证register_agent
member已注册 Agent所有 Message/Task/Memory/File/Orchestration/Pipeline 工具
group_admin并行组管理员任务编排 + Pipeline 工具(不含 Memory/Evolution)
admin系统管理员revoke_token / set_trust_score / approve_strategy / veto_strategy / set_agent_role / recalculate_trust_scores / score_applied_strategies / get_db_stats / archive_data

trust_score 初始值 50,公式:base(50) + verified_capabilities*3 + approved_strategies*2 + positive_feedback*1 - negative_feedback*2,clamp(0,100)。

Show full SKILL.md (265 more words)Show less

v2.4.2 更新要点

Phase内容变更
Atools.ts 拆分2687 行 → 8 模块 + 30 行入口 + utils.ts
B单元测试100 用例,security >= 70% / dedup branches≥60, functions≥70 / utils 100%
CCI/CDGitHub Actions:typecheck + test + coverage 3 Jobs
D类型安全any 归零 + HubError 统一错误码 + MCP 返回格式标准化
E安全强化新增安全说明章节,明确鉴权/人工确认/数据安全最佳实践

安全说明

🔐 鉴权与访问控制
  • 所有 MCP 工具调用(除 register_agent 外)均需 Bearer Token 认证,Token 在注册时通过 register_agent 返回
  • MCP HTTP 客户端必须在请求头中携带 Authorization: Bearer <token>
  • 4 级 RBAC 权限矩阵严格隔离操作范围:public(仅注册) → member(通信/记忆) → group_admin(编排) → admin(系统管理)
  • 建议:将 Hub 部署在受信网络内,不要暴露到公网;生产环境启用 CORS 白名单
⚠️ 高风险操作确认

以下操作建议要求人工确认(可通过 quality_gate 实现):

  • revoke_token / set_trust_score / set_agent_role(admin 级)
  • approve_strategy / veto_strategy(策略审批)
  • delete_memory / archive_data(数据删除)
  • Task / Pipeline 中的破坏性操作
🛡️ 记忆与数据安全
  • 建议默认使用 scope=private 存储记忆,仅必要时升级到 group/collective
  • 所有记忆和策略操作记录在审计日志中(SHA-256 哈希链防篡改)
  • Memory/Strategy 操作均关联 agent_id,支持溯源
  • 建议:定期审查共享记忆和策略内容,使用 list_memories / list_strategies 审计
📋 安全配置清单
配置项推荐值说明
HUB_AUTH_TOKEN必填stdio 模式认证 token,长度 ≥ 32 字符
CORS_ORIGINS明确指定域名不要留空或设为 *(生产环境)
DB_PATH非默认路径生产环境使用独立数据目录
trust_score首次验证后调整新 Agent 初始值 50,验证后上调
心跳超时30 秒超 5 次未心跳自动离线

踩坑经验速查

#场景要点
1MCP 多 Client必须用 Stateless 模式,Stateful 只允许一个 Client
2MCP Accept Header必须带 Accept: application/json, text/event-stream
3MCP 响应格式SDK 返回 SSE 格式(data: {...}),不是纯 JSON
4ESM 兼容不能用 require(),用 import() 动态导入
5UTF-8 块读取httpx resp.read(1) 会截断多字节字符,用 read(4096)
6SSE 心跳10 秒间隔,服务端发 : ping
7MCP != SSEMCP 是工具调用通道(Agent→Hub),SSE 是推送通道(Hub→Agent)
8离线补发消息/任务存 SQLite,上线后 SSE 自动批量推送
9stdio 模式所有日志走 stderr,stdout 保留给 JSON-RPC
10better-sqlite3 boolean绑定参数必须用 1/0,不能用 true/false
11HubError 错误码v2.4.0 统一用 mcpError()/mcpFail(),不要手动构造错误响应

环境变量

变量默认值说明
PORT3100Hub 监听端口(HTTP 模式)
HUB_URLhttp://localhost:3100Hub 地址(客户端用)
HUB_AUTH_TOKEN—stdio 模式认证 token(必填)
DB_PATH./comm_hub.dbSQLite 数据库路径
LOG_LEVELinfo日志级别:debug / info / warn / error
CORS_ORIGINS(空)CORS 白名单(逗号分隔),空=拒绝所有跨域

技术依赖

Hub 服务器:

  • Node.js 18+
  • @modelcontextprotocol/sdk ^1.10.2(支持 StdioServerTransport)
  • express ^4.19
  • better-sqlite3 ^11.9
  • zod ^3.23

Python 客户端(零外部依赖):

  • Python 3.9+(纯标准库:http.client / json / asyncio)

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 122 other files (scripts) in skills/agent-comm-hub of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • .clawhub/origin.json
  • API_REFERENCE.md
  • HERMES-SETUP.md
  • README.md
  • _meta.json
  • client-sdk/agent-client.d.ts
  • client-sdk/agent-client.js
  • client-sdk/agent-client.ts
  • client-sdk/hermes-integration.d.ts
  • client-sdk/hermes-integration.js
  • client-sdk/hermes-integration.ts
  • client-sdk/hub_client.py
  • client-sdk/workbuddy-integration.d.ts
  • client-sdk/workbuddy-integration.js
  • client-sdk/workbuddy-integration.ts
  • deploy/docker-compose.yml
  • deploy/grafana
  • … and 105 more

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Agent Comm Hub next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Comm Hub compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Comm Hub this skillLeoYeAI/openclaw-master-skills2.2k—~3kAutomated safety check: PassMIT
Kingdee MCP DevWaHaiLong/KingdeeMCP105—~853Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
LangBot Plugin Developmentlangbot-app/LangBot18k—~3.9kAutomated safety check: PassApache-2.0
Build Error AdapterArcadeAI/arcade-mcp1k—~2kAutomated safety check: PassMIT

Similar skills

  • Kingdee MCP Dev

    WaHaiLong/KingdeeMCP

    Knowledge base for the Kingdee MCP Dev Squad. An agent skill from WaHaiLong/KingdeeMCP.

    105 GitHub stars~853 tokensUpdated 2 mo ago
    Backend & APIsAuto-check passed
  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • LangBot Plugin Development

    langbot-app/LangBot

    Guides building, debugging and testing LangBot plugins: components, SDK calls, README and locale rules, SDK pitfalls and WebSocket-based testing.

    18k GitHub stars~3.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Build Error Adapter

    ArcadeAI/arcade-mcp

    Build new Arcade error adapters from scratch using public Arcade TDK patterns.

    1k GitHub stars~2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Tiger Brokers OpenAPI SDK

    qusong0627/QuantMind

    Covers the Tiger Brokers OpenAPI Python SDK for market data, stock, futures and options trading, push subscriptions, a CLI and an MCP server, defaulting to paper trading.

    1.7k GitHub stars~1.4k tokensUpdated today
    Business, Finance & HRAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Agent Comm Hub

What does Agent Comm Hub do?

多智能体协同通信基础设施——基于 MCP+SSE 的实时消息、任务调度、记忆共享与进化引擎。支持 WorkBuddy、Hermes、QClaw 及任意 MCP 兼容 Agent 接入。53 个 MCP 工具、4 级权限、零外部依赖 Python…. Agent Comm Hub is an agent skill from LeoYeAI/openclaw-master-skills.

When should I use Agent Comm Hub?

Agent Comm Hub fits situations like: tasks that involve MCP servers.

How do I install Agent Comm Hub in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a claude-code`. Or copy the skill folder (skills/agent-comm-hub in LeoYeAI/openclaw-master-skills) into .claude/skills/agent-comm-hub in your project. Claude Code loads it when a task matches its description.

How do I install Agent Comm Hub in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a codex`. Or copy the skill folder (skills/agent-comm-hub in LeoYeAI/openclaw-master-skills) into .agents/skills/agent-comm-hub in your project. Codex loads it when a task matches its description.

Can I use Agent Comm Hub in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-comm-hub, .gemini/skills/agent-comm-hub, .github/skills/agent-comm-hub and .opencode/skills/agent-comm-hub in your project.

What does Agent Comm Hub need to run?

Going by SKILL.md and its folder, Agent Comm Hub needs TypeScript, JavaScript and Python for the scripts in its folder, the command-line tools its instructions call (npm and git) and credentials named HUB_AUTH_TOKEN. Our summary lists: Python 3; Node.js; Docker; A credential in HUB_AUTH_TOKEN.

Does Agent Comm Hub access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Agent Comm Hub safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Agent Comm Hub use?

Agent Comm Hub is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Comm Hub use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Comm Hub?

Skills that share tags, products or a category with Agent Comm Hub: Kingdee MCP Dev (WaHaiLong/KingdeeMCP, 105 stars), MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars) and LangBot Plugin Development (langbot-app/LangBot, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Comm Hub?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.