Weixin Multi-Agent Router|微信多 Agent 路由
v1.0.0Design or implement single-entry multi-agent routing for OpenClaw Weixin setups. Use when one Weixin account should route between any number of backend agent...
⭐ 5· 74·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (Weixin multi-agent routing) matches the SKILL.md and reference files: all content focuses on routing, session keys, per-contact state, command maps, handoff summaries, and validation. There are no unrelated environment variables, binaries, or install steps requested.
Instruction Scope
Runtime instructions stay within the stated purpose: they describe parsing commands, maintaining per-contact router state, building session keys, summary-based handoff, and validation tests. The skill explicitly warns against sharing raw transcripts and against core-level changes. It does instruct state persistence (session keys, recentHistory, summaries)—which is expected for a router—but does not tell the agent to read arbitrary system files, environment variables, or post data to unknown endpoints.
Install Mechanism
No install specification or code distribution is present (instruction-only). That minimizes disk-write or download risk; nothing is pulled from external URLs or third-party package registries.
Credentials
The skill declares no required environment variables, credentials, or config paths. The guidance about state, configs, and timeouts is proportional to the skill's goal. There are no unrelated credential requests.
Persistence & Privilege
always is false and the skill is user-invocable; there is no request to persist or modify other skills or system-wide settings. The SKILL.md recommends persisting router state (normal for this feature) and advises configuration separation from long-lived config—appropriate for its purpose.
Assessment
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.Like a lobster shell, security has layers — review code before you run it.
latestvk97873hz7zy1asm40xtgrx5d8n83ht6jmulti-agentvk97873hz7zy1asm40xtgrx5d8n83ht6jroutingvk97873hz7zy1asm40xtgrx5d8n83ht6jsession-routingvk97873hz7zy1asm40xtgrx5d8n83ht6jwechatvk97873hz7zy1asm40xtgrx5d8n83ht6jweixinvk97873hz7zy1asm40xtgrx5d8n83ht6j
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
