skills/cross-instance-comm/SKILL.md
Use when sending messages or tasks between multiple OpenClaw instances over Tailscale Gateway, such as asking another machine to execute work or sync context.
npx skillsauth add aaaaqwq/agi-super-team cross-instance-commInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
通过 Tailscale 网络向其他 OpenClaw 实例发送消息,实现跨机器 Agent 通信。
| 实例 | 域名 | 端口 | Token | |------|------|------|-------| | 小m (Mac Mini M2) | daniellimac-mini.tail0db0a3.ts.net | 18789 | $(pass show api/xiaom-gateway-token) | | 本机 (Linux) | 127.0.0.1 | 18789 | (本地) |
# 给小m的主agent发消息
curl -s -X POST "http://daniellimac-mini.tail0db0a3.ts.net:18789/api/message" \
-H "Authorization: Bearer <token>" \
-H "Content-Type: application/json" \
-d '{"message": "你的消息内容"}'
如果当前 OpenClaw 配置了远程 Gateway,可直接用 sessions_send:
# 在代码中通过 Gateway API
import httpx
def send_to_instance(host, port, token, message, session_key=None):
url = f"http://{host}:{port}/api/message"
headers = {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
data = {"message": message}
if session_key:
data["sessionKey"] = session_key
resp = httpx.post(url, headers=headers, json=data, timeout=30)
return resp.json()
# 发到小m
send_to_instance(
"daniellimac-mini.tail0db0a3.ts.net", 18789,
"$(pass show api/xiaom-gateway-token)",
"帮XX公司做GEO,行业是云计算"
)
# scripts/send-to-m2.sh
#!/bin/bash
MSG="${1:?用法: send-to-m2.sh '消息内容'}"
curl -s -X POST "http://daniellimac-mini.tail0db0a3.ts.net:18789/api/message" \
-H "Authorization: Bearer $(pass show api/xiaom-gateway-token)" \
-H "Content-Type: application/json" \
-d "{\"message\": \"$MSG\"}"
development
Technology-agnostic prompt generator that creates customizable AI prompts for scanning codebases and identifying high-quality code exemplars. Supports multiple programming languages (.NET, Java, JavaScript, TypeScript, React, Angular, Python) with configurable analysis depth, categorization methods, and documentation formats to establish coding standards and maintain consistency across development teams.
tools
Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.
data-ai
Prompt for creating detailed feature implementation plans, following Epoch monorepo structure.
tools
Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never writes code. Requires the Joyride extension.