a2a-protocol

Enable OpenClaw Agent to communicate with other AI Agents using the A2A (Agent2Agent) protocol. Use when: (1) User wants to connect two OpenClaw instances across different servers, (2) User needs Agent-to-Agent communication, (3) User asks about A2A protocol, (4) User wants to expose OpenClaw as an A2A service, (5) User wants to call remote A2A agents.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "a2a-protocol" with this command: npx skills add verylowlow/agents-making-friends

A2A Protocol

Enable OpenClaw Agent to communicate with other AI Agents using the A2A (Agent2Agent) protocol - an open standard by Google for inter-agent communication.

Quick Start

Calling a Remote Agent (Client Mode)

python ~/.openclaw/workspace/skills/a2a-protocol/scripts/a2a_client.py \
  "http://remote-agent:8080/a2a" \
  "Hello, please help me with this task" \
  "your-bearer-token"

Exposing as A2A Service (Server Mode)

python ~/.openclaw/workspace/skills/a2a-protocol/scripts/a2a_server.py --port 8080

Core Concepts

ConceptDescription
Agent CardJSON document describing agent identity, capabilities, endpoint
TaskUnit of work with lifecycle (pending → running → completed)
MessageCommunication turn with role and parts
PartSmallest content unit (text/file/data)
ArtifactOutput generated by agent

Workflow

1. Agent A (Client)          2. Agent B (Server)
   │                              │
   │ GET /.well-known/agent.json │
   │─────────────────────────────►│
   │       Agent Card             │
   │◄─────────────────────────────│
   │                              │
   │ POST /rpc (message/send)     │
   │─────────────────────────────►│
   │                              │
   │      Task Response           │
   │◄─────────────────────────────│

Configuration

Add remote agent info to TOOLS.md:

### A2A Agents

- Remote Agent Name:
  URL: http://1.2.3.4:8080/a2a
  Token: your-bearer-token

Resources

scripts/

  • a2a_client.py - A2A client for calling remote agents
  • a2a_server.py - A2A server for exposing OpenClaw as a service
  • agent_card.json - Agent Card template

references/

  • a2a-api.md - Complete A2A API reference

Troubleshooting

Connection Failed

  1. Check network reachability (ping/telnet)
  2. Verify firewall allows the port
  3. Confirm token is correct

Agent Card Not Found

  1. Ensure remote agent's A2A server is running
  2. Check URL includes correct path

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

技能编辑器

编辑、完善或审查 AgentSkills。当需要创建新技能、对现有 SKILL.md 进行修改、清理/审计/整理技能文件时激活此技能。触发词:编辑技能, skill 注意事项, metadata 检查, 完善技能, 清理技能, 审计技能, skill 规范, 编写 skill, 新建技能

Registry SourceRecently Updated
Automation

全闭环管道

全闭环自动化管道 — Hunter→Skill Factory→Orchestrator→Dashboard→Profit。将Phase 1-3所有组件串联为自动运行的超级管道。核心能力:(1) 一键全流程 (2) 定时自动运行 (3) 异常自愈 (4) 利润报告

Registry SourceRecently Updated
Automation

智美人AI实战课

《智美人AI Agent实战课》配套技能——从0到1搭建AI Agent的完整课程体系。第01节:AI Agent基础概念+工具链搭建。课程内容含数字人讲解视频、实战代码、课后练习。覆盖:OpenClaw配置、技能安装、MCP工具、多Agent协同、变现实战。

Registry SourceRecently Updated
Automation

利润优化引擎

利润优化引擎 — 订单管理/计价/结算模拟。核心能力:(1) 订单管理 (2) 计价模型 (3) 成本追踪 (4) 利润计算

Registry SourceRecently Updated
a2a-protocol | V50.AI