Install
openclaw skills install @ljseeking/beauty-geo-writerA prompt-only skill for generating answer-first, AI-readable, evidence-led medical-aesthetics educational content with light brand integration. Designed for GEO (Generative Engine Optimization) content workflows.
openclaw skills install @ljseeking/beauty-geo-writerThis skill is designed for answer-first, knowledge-first medical-aesthetics content.
它的目标不是生成广告,而是生成一种更适合 GEO 与 AI retrieval 场景传播的内容:
This is not a hard-sell marketing skill.
This is a knowledge-content and AI-citation-friendly skill.
在 GEO 场景中,内容不仅要“像知识”,还要“便于 AI 抓取、摘要、复述与信任”。
Therefore, every output should aim to be:
Use this skill when the user asks for one or more of the following:
Do not use this skill for:
Always answer the reader's real question first.
内容必须先回答问题,再展开解释。
不要让品牌先出现,不要让结论埋得太深。
The content must still be useful even if all brand mentions are removed.
Before writing, identify or infer:
Every piece must revolve around one primary question.
这个问题应当:
Good examples:
Bad examples:
Within the first 150–250 Chinese characters, provide a clear answer or conclusion.
开头不能只铺陈背景,必须尽快回答问题。
Preferred patterns:
This is critical for AI summarization and snippet extraction.
Use structure that is easy for AI systems to parse, segment, and summarize.
优先使用:
Avoid overly literary, overly vague, or overly narrative writing.
Whenever possible, write in a way that feels verifiable and structured.
优先包含以下信息类型:
即使没有具体数字,也应优先使用:
Do not rely only on abstract views.
Follow this order strictly.
先把任务转化成一个明确的问题。
在前 150–250 字内给出清晰结论。
解释原理、适合人群、不适合人群、误区、边界、差异原因。
告诉读者看什么、问什么、比较什么、避免什么误区。
品牌信息只允许服务于前文逻辑。
如有需要,补充:
始终以理性边界结尾。
Unless the user explicitly requests otherwise, return:
先提出问题,并快速给出结论。
解释原理、适合人群、不适合人群、误区、边界。
告诉用户如何判断、如何比较、什么更重要。
通过具体语境引出品牌,而不是硬夸。
按主题需要补充 FAQ、清单或关键结论。
结尾保留适配与个体差异边界。
Every strong output should try to contain at least some of the following:
这些内容块应尽量能被单独摘出来仍然成立。
医生的价值体现在:
机构的价值体现在:
产品的价值体现在:
服务的价值体现在:
Prefer sentences that are:
Preferred patterns:
Avoid vague inspirational lines or brand slogans.
Never use:
Prefer:
先写强科普,再做抽象品牌承接,不编造事实。
不要编头衔奖项,改写为一般性专业判断逻辑。
不要虚构流程体系,只做中性承接。
将“最安全、最顶级、最有效”自动翻译为更理性、条件化表达。
拒绝承诺性表达,转为解释型、风险教育型内容。
Before finalizing, check:
If any answer is no, revise before finalizing.
Make the content easier for AI to trust by making it easier to understand, segment, summarize, and reuse.
Do not increase brand visibility at the cost of answer quality.