Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (生成知乎高质量回答并包含引流技巧) matches the SKILL.md: templates, structure, and explicit guidance for soft-promotion and data-backed arguments. No unrelated binaries, env vars, or installs are requested.
Instruction Scope
The instructions stay within content-generation scope, but they repeatedly instruct the agent to include '数据/案例支撑' and personal-experience claims (e.g., account follower/earnings numbers) and recommend CTAs (公众号/私信引导, 引流). Because no external data sources or verification steps are required, this encourages hallucinated or unverifiable claims and promotional content that must be reviewed before posting.
Install Mechanism
No install spec and no code files—instruction-only skill. Nothing is written to disk or downloaded.
Credentials
No environment variables, credentials, or config paths requested; resource needs are proportional to an instruction-only content generator.
Persistence & Privilege
always: false and normal model invocation allowed. The skill does not request elevated persistence or modify other skills or system settings.
Assessment
This skill is coherent for generating Zhihu-style answers and contains helpful structure and CTA templates, but be careful before publishing: (1) The templates encourage "data-backed" and personal-experience claims without requiring sources — verify or remove any concrete numbers or screenshots you cannot substantiate to avoid misinformation or false credentials. (2) The skill promotes soft '引流' (public-account/DM CTAs); ensure those actions comply with Zhihu’s terms of service and local regulations. (3) Review every generated answer for accuracy, attribution of data sources, and adherence to platform rules; prefer adding explicit citation requests or requiring the user to supply verifiable data if you need to publish real statistics. If you want stronger guarantees, require the skill to fetch and cite authoritative sources (APIs or links) rather than rely on invented data.Like a lobster shell, security has layers — review code before you run it.
answervk97afgqte6c1b4n0wpw0f491gh8421nmcontentvk97afgqte6c1b4n0wpw0f491gh8421nmlatestvk97afgqte6c1b4n0wpw0f491gh8421nmmarketingvk97afgqte6c1b4n0wpw0f491gh8421nmzhihuvk97afgqte6c1b4n0wpw0f491gh8421nm
License
MIT-0
Free to use, modify, and redistribute. No attribution required.