Guanxi
v1.0.0The only AI skill built specifically for WeChat communication in China. Drafts messages calibrated to Chinese business etiquette and relationship hierarchy....
⭐ 0· 246·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The skill's name/description claim to produce WeChat-calibrated messages and Moments content, which matches the SKILL.md instructions to draft messages. However the skill also uses wording like “manages group chat dynamics” and “posted at optimal engagement times,” which implies platform integration or scheduling that this instruction-only skill does not request credentials for and cannot perform automatically. The mismatch is modest (drafting vs. automated posting) but worth noting.
Instruction Scope
SKILL.md instructs the agent to generate ready-to-send messages tailored to relationship/context. It does not instruct the agent to read system files, environment variables, or external config, nor to exfiltrate data. The instructions are focused on composing text and examples.
Install Mechanism
No install spec and no code files; nothing is written to disk or installed. This is the lowest-risk install approach for a drafting skill.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is proportionate for a drafting-only skill. If the skill were to claim posting or account access, credentials would be expected — none are requested.
Persistence & Privilege
Defaults are used (not always:true). The skill does not request persistent system privileges or attempt to modify other skills or global configs.
Assessment
This skill is instruction-only and appears to only draft WeChat-style messages — it cannot log into WeChat, access your contacts, or post automatically because it requests no credentials. Consider these points before using:
- Origin/provenance: there is no homepage or clear author info; if you need guarantees about quality or safety, ask for source code or documentation.
- Manual review: always read and edit generated messages before sending, especially for sensitive or high-stakes communications (to avoid accidental tone/relationship errors or unintended content).
- Privacy: do not paste highly sensitive personal data or credentials into prompts; the skill will craft text from whatever you provide.
- Automation expectations: if you expect the skill to schedule or post Moments or manage chats, it currently cannot do so without additional integration (which would require credentials and review).
If you want higher assurance, request the skill’s provenance (author, source repo, or sample prompts/output tests) before enabling it for automated use.Like a lobster shell, security has layers — review code before you run it.
businessvk97592rf0tg2me05p4mbmms5p982j6a0chinavk97592rf0tg2me05p4mbmms5p982j6a0communicationvk97592rf0tg2me05p4mbmms5p982j6a0guanxivk97592rf0tg2me05p4mbmms5p982j6a0latestvk97592rf0tg2me05p4mbmms5p982j6a0wechatvk97592rf0tg2me05p4mbmms5p982j6a0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
