Short video audience insight
Agent Skills workflow for Chinese talking-head video operations, scripting, production, publishing preparation, and review.
npx -y skills add slalomboy/talking-head-video-suite --skill short-video-audience-insightAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 21 days oldThe repository was created 21 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when content needs evidence-backed user situations, jobs, concerns, decision criteria, comment-question patterns, or original customer language.
SKILL.md
1.6 KB, 533 tokens by cl100k_base, as published. Nobody here has run it
Short Video Audience Insight
核心原则
受众不是人口标签，而是处境中的任务、期望、障碍与判断标准。
触发与边界
用于用户处境、顾虑、判断标准、评论问题、客服问法和搜索语言的提炼。边界例：“定位给宝妈，但不知道她们具体担心什么”应先确认 business，再分析不同处境下的真实顾虑，不能假设同一身份需求一致。
不用于决定业务承诺，不把少量评论自动升级为市场结论。
输入
business、访谈、评论、客服记录、搜索词、成交与流失原因。来源不足时标记样本限制。
方法
- 按
situation和阶段分组，不按偏见分组。 - 提炼用户要完成的
job与desiredResult。 - 记录
concerns和decisionCriteria，区分高频、强烈和高价值问题。 - 保留
verbatimLanguage原话及evidence source，不把改写后的营销词冒充原话。 - 评论问题只能形成候选洞察；用更多行为或经营证据交叉核验。
输出契约
只写 audience：situation、job、desiredResult、concerns、decisionCriteria、verbatimLanguage、sources、confidence。输出可用于选题的问句，但不直接写完整文案。
常见错误
把“所有宝妈/老板/年轻人”视为同一人群；只摘支持既有判断的评论；忽略未成交与退款语言；把互动热度当需求强度。