Kingdee MCP Dev
WaHaiLong/KingdeeMCP
Knowledge base for the Kingdee MCP Dev Squad. An agent skill from WaHaiLong/KingdeeMCP.
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…
$ npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills agent-comm-hub --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-srcUse ~/.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/
Install the "agent-comm-hub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/agent-comm-hub into .claude/skills/agent-comm-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-comm-hub", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/agent-comm-hubType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills agent-comm-hub --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agent-comm-hub .agents/skills/agent-comm-hub && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-comm-hub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/agent-comm-hub into .agents/skills/agent-comm-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-comm-hub", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills agent-comm-hub --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agent-comm-hub .cursor/skills/agent-comm-hub && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-comm-hub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/agent-comm-hub into .cursor/skills/agent-comm-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-comm-hub", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/agent-comm-hub--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills agent-comm-hub --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agent-comm-hub .gemini/skills/agent-comm-hub && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-comm-hub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/agent-comm-hub into .gemini/skills/agent-comm-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-comm-hub", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills agent-comm-hubInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agent-comm-hub .github/skills/agent-comm-hub && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-comm-hub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/agent-comm-hub into .github/skills/agent-comm-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-comm-hub", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill agent-comm-hub -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills agent-comm-hub --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agent-comm-hub .opencode/skills/agent-comm-hub && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-comm-hub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/agent-comm-hub into .opencode/skills/agent-comm-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-comm-hub", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
agent-comm-hub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. 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.
2 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
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:
npmgitFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
HUB_AUTH_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
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.
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.
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.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 616 words, ~2,961 tokens.
.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.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。
┌──────────────┐ ┌──────────────────────────────┐ ┌──────────────┐
│ 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 |
| 工具 | 功能 |
|---|---|
register_agent | 注册新 Agent,获取 agent_id 和 API token(public,无需认证) |
heartbeat | Agent 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 |
| 工具 | 功能 |
|---|---|
send_message | Agent 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 |
| 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 |
| 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 |
| 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_memories | FTS5 全文搜索记忆,支持多关键词和短语搜索 |
| 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) |
| 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 |
| 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 |
| 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)。
| 端点 | 方法 | 功能 |
|---|---|---|
/health | GET | 健康检查(返回版本、内存、DB、大小、活跃 SSE 连接数) |
/metrics | GET | Prometheus 兼容指标(mcp_calls_total、message_delivery_total 等) |
inbox → assigned → [waiting] → in_progress → completed / failed / cancelledgit 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)方式 A:MCP stdio 模式(推荐,适用于本地 Agent)
{
"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)
{
"mcpServers": {
"agent-comm-hub": {
"url": "http://localhost:3100/mcp"
}
}
}方式 C:SDK 接入
TypeScript Agent:
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):
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()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| 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)。
| Phase | 内容 | 变更 |
|---|---|---|
| A | tools.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% |
| C | CI/CD | GitHub 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 |
register_agent 返回Authorization: Bearer <token>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)list_memories / list_strategies 审计| 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 |
| # | 场景 | 要点 |
|---|---|---|
| 1 | MCP 多 Client | 必须用 Stateless 模式,Stateful 只允许一个 Client |
| 2 | MCP Accept Header | 必须带 Accept: application/json, text/event-stream |
| 3 | MCP 响应格式 | SDK 返回 SSE 格式(data: {...}),不是纯 JSON |
| 4 | ESM 兼容 | 不能用 require(),用 import() 动态导入 |
| 5 | UTF-8 块读取 | httpx resp.read(1) 会截断多字节字符,用 read(4096) |
| 6 | SSE 心跳 | 10 秒间隔,服务端发 : ping |
| 7 | MCP != SSE | MCP 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 |
| 9 | stdio 模式 | 所有日志走 stderr,stdout 保留给 JSON-RPC |
| 10 | better-sqlite3 boolean | 绑定参数必须用 1/0,不能用 true/false |
| 11 | HubError 错误码 | v2.4.0 统一用 mcpError()/mcpFail(),不要手动构造错误响应 |
| 变量 | 默认值 | 说明 |
|---|---|---|
PORT | 3100 | Hub 监听端口(HTTP 模式) |
HUB_URL | http://localhost:3100 | Hub 地址(客户端用) |
HUB_AUTH_TOKEN | — | stdio 模式认证 token(必填) |
DB_PATH | ./comm_hub.db | SQLite 数据库路径 |
LOG_LEVEL | info | 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 |
Hub 服务器:
Python 客户端(零外部依赖):
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 122 other files (scripts) in skills/agent-comm-hub of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Comm Hub this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~3k | Automated safety check: Pass | MIT | |
| Kingdee MCP DevWaHaiLong/KingdeeMCP | 105 | — | ~853 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| LangBot Plugin Developmentlangbot-app/LangBot | 18k | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | |
| Build Error AdapterArcadeAI/arcade-mcp | 1k | — | ~2k | Automated safety check: Pass | MIT |
WaHaiLong/KingdeeMCP
Knowledge base for the Kingdee MCP Dev Squad. An agent skill from WaHaiLong/KingdeeMCP.
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
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.
langbot-app/LangBot
Guides building, debugging and testing LangBot plugins: components, SDK calls, README and locale rules, SDK pitfalls and WebSocket-based testing.
ArcadeAI/arcade-mcp
Build new Arcade error adapters from scratch using public Arcade TDK patterns.
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.
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.
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.
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.
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.
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.
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.
Works with
Categories
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.
Agent Comm Hub fits situations like: tasks that involve MCP servers.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.