Weixin Multi-Agent Router｜微信多 Agent 路由

Design or implement single-entry multi-agent routing for OpenClaw Weixin setups. Use when one Weixin account should route between any number of backend agent...

This skill is a documentation/design guide, not executable code; it asks for nothing sensitive and appears internally consistent. Before implementing or deploying: 1) Decide where router state (session keys, recentHistory, handoff summaries) will be stored and apply access controls, encryption, and retention policies so conversation data isn't exposed. 2) Ensure handoff summaries are intentionally compact and scrub PII; follow the guide's explicit advice to avoid sending full transcripts between agents. 3) Make agent lists, aliases, and timeouts configurable (the docs recommend this) and check defaults to avoid publishing private team names. 4) Test isolation thoroughly (the validation steps provided are good) to prevent context leakage. 5) If you adapt this into runnable code, review any added install steps, external URLs, or required env vars for proportionality and security before enabling it in production.

Type: OpenClaw Skill Name: weixin-multi-agent-router Version: 1.0.0 The skill bundle provides architectural guidance and instructions for an AI agent to implement a multi-agent router for WeChat. It focuses on session isolation, state management, and command parsing to prevent context leakage between different backend agents. No malicious code, data exfiltration, or harmful prompt injection attempts were found across the files, including SKILL.md and the references directory.