agentleFS
Serennity007Serennity007/uzi-skill/skills/trap-detector/SKILL.md

trap-detector

Skill0 starsChanged 3 months agoMITView on GitHub

杀猪盘检测器。当用户提到"朋友推荐"、"群里说"、"老师带"、"内幕消息"、"小红书 / 抖音看到推荐"等关键词,或显式要求"看看是不是杀猪盘 / 检测一下风险 / 这只票安全吗"时使用。扫描 8 个信号给出风险评级 🟢🟡🟠🔴。

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 1

    1. wbh604/UZI-Skill★ 7.6k100% same

    Edited · 0

    None found.

    Wrote their own version · 1

    1. hegu-1/claude-cognition-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

Files
SKILL.md

Trap Detector · 杀猪盘检测器

触发场景

  • 用户输入含关键词:朋友推荐、群里、老师带、内幕、必涨、翻倍、暴涨、稳赚、跟单
  • 显式要求:检测一下、是不是杀猪盘、安不安全、被套路了吗
  • /scan-trap 命令

8 信号扫描清单

  1. 大量低质量账号同时推荐 — web search 该股名 + "推荐",看是否有同质化的低互动账号
  2. 推荐话术模板化 — 搜 "{name} 即将爆发"、"主力建仓完毕"、"目标翻倍" 等关键词
  3. 付费社群 / VIP 直播间引流 — 搜 "{name} 微信群"、"{name} 直播间"、"{name} VIP"
  4. 基本面与热度脱节 — 调用 fetch_financials + fetch_sentiment 对比
  5. K 线异常配合 — 调用 fetch_kline,看是否在推荐密集期前已大幅拉升
  6. 老师 / 股神人设推广 — 搜 "{name} 老师"、"{name} 股神"
  7. 跨平台联动推广 — 搜小红书 / 抖音 / B 站 / 知乎多个平台
  8. 虚假研报 / 伪造消息 — 搜 "{name} 谣言"、"{name} 辟谣"、"{name} 虚假"

风险评级

命中信号数评级建议
0-1🟢 安全数据正常,未发现被异常推广迹象
2-3🟡 注意有少量推广,建议核实信息源
4-5🟠 警惕多个推广信号,强烈建议谨慎
6+🔴 高度可疑强烈建议回避,疑似杀猪盘特征

用户关键词加权

如果用户提到下列词,信号严重程度自动 +1 级:

  • "朋友推荐我" / "群里有人说" / "老师带我" → +1
  • "内幕消息" / "稳赚不赔" → +2
  • "必涨" / "翻倍" / "暴涨" → +1

输出格式

{
  "ticker": "...",
  "trap_score": 1-10,           // 反向,越高越安全
  "trap_level": "🟢 安全",
  "signals_hit": [
    {
      "id": 3,
      "name": "付费社群引流",
      "evidence": "搜索发现 5 个公众号同期推送 VIP 群入口",
      "severity": "high",
      "sources": ["url1", "url2"]
    }
  ],
  "user_keyword_boost": 1,
  "recommendation": "🟢 未发现明显推广痕迹,可正常分析。但任何投资都需自己判断。",
  "warning_phrases": ["..."]    // 给用户的明确警告(如有)
}

完成检查

  • 8 个信号每个都给出"命中 / 未命中 / 数据不足"
  • 至少有 1 条具体证据 URL(除非全部安全)
  • recommendation 必须有,不能空
  • 如果 ≥ 4 信号,必须用 "强烈建议谨慎" 或 "强烈建议回避" 开头

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.