Self media trend radar
Skill yanhua1010/self-media-content-workflow/skills/self-media-trend-radar
安全追踪热点、研究关键词和拆解竞品内容，并将结果转成原创选题和证据包。用于用户要求找热点、看趋势、分析爆款、研究竞品账号、拆标题或开头、比较内容结构、发现评论需求和判断时效窗口。只做公开信息研究和只读采集，不自动互动、发布或使用主账号登录态抓取竞品。From its SKILL.md
npx -y skills add yanhua1010/self-media-content-workflow --skill self-media-trend-radarAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.4 KB, 770 tokens by cl100k_base, as published. Nobody here has run it
热点与竞品雷达
目标
识别用户需求、表达结构和时效机会，不复制竞品观点或文案。
数据源优先级
- 用户提供的链接、截图、导出文件和素材。
- 官方文档、原始发布、论文、公告和作者原帖。
- 平台公开搜索、热榜、竞品主页和公开互动数据。
- 可信二手资料，用于补充背景，不替代一手事实。
近期产品、人物、价格、版本、新闻和平台规则必须联网核验。技术事实优先使用官方来源。
研究流程
1. 定义研究问题
确认要回答的是热点窗口、关键词需求、竞品结构、账号定位还是内容机会。先限定平台、时间范围和样本数量。
2. 收集有限样本
只收集能回答问题的样本。记录链接、发布时间、标题、内容形态、公开互动和观察备注。不要把一次高表现直接叫作规律。
3. 拆解结构
逐条检查：
- 标题使用了什么承诺、身份、冲突或信息差。
- 开头 3 秒或第一屏如何建立停留。
- 内容如何组织证据、故事、步骤和转折。
- 封面或首图承担什么任务。
- 行动、标签、合集和发布时间如何配合目标。
- 评论区暴露了哪些真实问题和反对意见。
4. 判断机会
区分：
- 可以直接核验的事实。
- 多个样本重复出现的模式。
- 可能由热点、投流或账号体量造成的现象。
- 用户能加入的一手经验、反证和独立判断。
5. 转成原创选题
每个候选写明：一句话判断、目标受众、时效窗口、一手证据、差异化角度、适合平台、仍缺证据和风险。
输出
交付：
- 研究范围和样本说明。
- 3 到 5 条结构性发现。
- 不能下结论的内容。
- 3 到 5 个原创选题。
- 最推荐选题和下一步验证动作。
读取 research-safety.md 并遵守账号隔离、只读、控频、遇阻即停和凭证保护规则。
What ships with it: 2 files
1.5 KB alongside SKILL.md
agents/
- openai.yaml268 B
references/
- research-safety.md1.2 KB
Gives 0 of the 12 instructions most media documents skills give in 770 tokens
Counted across 99 of the 124 authors here whose files we hold, read 2026-09-06
- Define three to five content pillarsin 7 of 99, across 5 files
- Tag every finding as verified, medium, or assumedin 5 of 99, across 3 files
- Respond to comments within one hourin 5 of 99
- Adapt content format to each platformin 5 of 99
- Choose platforms where the audience already spends timein 4 of 99, across 2 files
- Cap promotional content at ten percentin 4 of 99, across 2 files
- Answer product questions within two hoursin 4 of 99, across 2 files
- Acknowledge complaints publicly, resolve them privatelyin 4 of 99, across 2 files
- Batch-create posts to keep cadence consistentin 4 of 99, across 2 files
- Fan out across free media sources in one queryin 3 of 99, across 1 file
- Use Pexels or Pixabay for modern short clipsin 3 of 99, across 1 file
- Extract historical shots from archival filmsin 3 of 99, across 1 file
Said here and by no other author read
- Define platform, timeframe, and sample size first
- Use user-provided sources before other sources
- Verify recent facts online
- Prefer official sources for technical facts
- Collect only samples that answer the question
- Record link, time, title, engagement per sample
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.