Agent skill

Stock Tip Scam Detector

Scans eight warning signs behind a stock tip from a friend, chat group or online teacher and returns a four-level risk rating with evidence.

MITAuto-check passedBusiness, Finance & HR

SKILL.md written in Chinese; this summary is our English description.

Install Stock Tip Scam Detector

skills CLI

$ npx skills add wbh604/UZI-Skill --skill trap-detector -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install wbh604/UZI-Skill trap-detector --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/wbh604/UZI-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/trap-detector .claude/skills/trap-detector && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "trap-detector" agent skill from https://github.com/wbh604/UZI-Skill/tree/main/skills/trap-detector into .claude/skills/trap-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trap-detector", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/wbh604/UZI-Skill/tree/main/skills/trap-detector

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add wbh604/UZI-Skill --skill trap-detector -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install wbh604/UZI-Skill trap-detector --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wbh604/UZI-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/trap-detector .agents/skills/trap-detector && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "trap-detector" agent skill from https://github.com/wbh604/UZI-Skill/tree/main/skills/trap-detector into .agents/skills/trap-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trap-detector", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wbh604/UZI-Skill --skill trap-detector -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install wbh604/UZI-Skill trap-detector --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wbh604/UZI-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/trap-detector .cursor/skills/trap-detector && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "trap-detector" agent skill from https://github.com/wbh604/UZI-Skill/tree/main/skills/trap-detector into .cursor/skills/trap-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trap-detector", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/wbh604/UZI-Skill.git --path skills/trap-detector

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add wbh604/UZI-Skill --skill trap-detector -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install wbh604/UZI-Skill trap-detector --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wbh604/UZI-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/trap-detector .gemini/skills/trap-detector && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "trap-detector" agent skill from https://github.com/wbh604/UZI-Skill/tree/main/skills/trap-detector into .gemini/skills/trap-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trap-detector", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install wbh604/UZI-Skill trap-detector

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add wbh604/UZI-Skill --skill trap-detector -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/wbh604/UZI-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/trap-detector .github/skills/trap-detector && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "trap-detector" agent skill from https://github.com/wbh604/UZI-Skill/tree/main/skills/trap-detector into .github/skills/trap-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trap-detector", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wbh604/UZI-Skill --skill trap-detector -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install wbh604/UZI-Skill trap-detector --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wbh604/UZI-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/trap-detector .opencode/skills/trap-detector && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "trap-detector" agent skill from https://github.com/wbh604/UZI-Skill/tree/main/skills/trap-detector into .opencode/skills/trap-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trap-detector", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: trap-detector
GitHub stars: 7.1k
Token cost: ~450 tokens
SKILL.md length: 114 words
Files: 2 (incl. references)
Skills in repo: 5
Repo updated: Sep 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Scans eight warning signs behind a stock tip from a friend, chat group or online teacher and returns a four-level risk rating with evidence.

Works in 8 steps: 大量低质量账号同时推荐 — web search 该股名 +… → 推荐话术模板化 — 搜 "{name}… → 付费社群 / VIP 直播间引流 — 搜 "{name}… → …
A friend or chat group is pushing a specific stock
SKILL.md covers 触发场景, 8 信号扫描清单, 风险评级 and 用户关键词加权, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Written in Chinese, this skill checks whether a stock recommendation looks like a pig-butchering scam, the investment fraud in which victims are steered into a stock by a friend, a chat group, a self-styled teacher or insider claims. It triggers on phrases such as a friend's recommendation, a group chat tip or guaranteed profit, and on direct requests to check whether a stock is safe.

The agent works through eight signals: many low-quality accounts recommending the stock, templated sales language, funnels into paid groups or VIP livestreams, hype that does not match the fundamentals, suspicious price moves before the recommendations, a guru persona, coordinated promotion across several platforms, and fake research reports or rumors. Several checks use web search and the repository's financial, sentiment and price-history fetch tools.

The number of signals hit sets a rating from green through yellow and orange to red, and certain phrases from the user raise the severity. Output is structured JSON with a safety score. The agent must mark each signal as hit, missed or lacking data, cite at least one evidence URL unless everything is clear, and open with a strong caution when four or more signals fire.

When your agent uses it

A friend or chat group is pushing a specific stock
Someone calling themselves a teacher offers to lead your trades
Checking whether the hype around a ticker looks coordinated
Screening a tip that promises guaranteed or doubled returns

Example prompts

“A teacher in my investing group keeps urging everyone to buy one particular stock. Scan it for scam signals.”
“Run a scam check on this stock tip I saw on Xiaohongshu.”
“Is this ticker safe, or am I being set up?”

Requirements

Web search access
The repository's fetch_financials, fetch_sentiment and fetch_kline tools

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

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
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
付费社群 / VIP 直播间引流 — 搜 "{name} 微信群"、"{name} 直播间"、"{name} VIP"
基本面与热度脱节 — 调用 fetch_financials + fetch_sentiment 对比
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
老师 / 股神人设推广 — 搜 "{name} 老师"、"{name} 股神"
跨平台联动推广 — 搜小红书 / 抖音 / B 站 / 知乎多个平台
虚假研报 / 伪造消息 — 搜 "{name} 谣言"、"{name} 辟谣"、"{name} 虚假"

What it can do on your machine

Read from SKILL.md and the folder at commit 650788c. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Stock Tip Scam Detector loads about 450 tokens when it runs, and up to ~1.1k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 114 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~33
When it runs · the whole SKILL.md, loaded when a task matches: ~450
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wbh604/UZI-Skill at commit 650788c, republished under its MIT licence (© wbh604). 114 words, ~450 tokens.

Download SKILL.mdSave it as .claude/skills/trap-detector/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: trap-detector
description: 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 🟢🟡🟠🔴。
version: 3.9.4
author: FloatFu-true
license: MIT

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

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
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
付费社群 / VIP 直播间引流 — 搜 "{name} 微信群"、"{name} 直播间"、"{name} VIP"
基本面与热度脱节 — 调用 fetch_financials + fetch_sentiment 对比
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
老师 / 股神人设推广 — 搜 "{name} 老师"、"{name} 股神"
跨平台联动推广 — 搜小红书 / 抖音 / B 站 / 知乎多个平台
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

json

{
  "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

Files

SKILL.md and 1 other file (references) in skills/trap-detector of wbh604/UZI-Skill.

SKILL.md
references/eight-signals.md

Open the folder on GitHubat commit 650788c

Compare with similar skills

Stock Tip Scam Detector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Stock Tip Scam Detector compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Stock Tip Scam Detector this skillwbh604/UZI-Skill	7.1k	—	~450	Automated safety check: Pass	MIT	1 mo ago
Pay Via Agent Walletcirclefin/skills	155	—	~3.9k	Automated safety check: Pass	Apache-2.0	23 days ago
Finance ReportAojdevStudio/Finance-Guru	322	—	~1.7k	Automated safety check: Pass	Custom licence	yesterday
Westock Datainfometa/workbuddyskills	346	—	~1.6k	Automated safety check: Pass	None	today
Web Searchheypinchy/pinchy	182	—	~765	Automated safety check: Pass	AGPL-3.0	18 days ago
Multi-Symbol Market Scannertradesdontlie/tradingview-mcp	6.8k	2 repos	~447	Automated safety check: Pass	Custom licence	2 mo ago

Similar skills

Pay Via Agent Wallet
circlefin/skills
A skill your agent uses when the user wants to call a paid API, look something up online, search for data, get prices, odds, or stats, or use any paid service with automatic USDC payment.
155 GitHub stars~3.9k tokensUpdated 23 days ago
Business, Finance & HRAuto-check passed
Finance Report
AojdevStudio/Finance-Guru
Generate institutional-quality PDF analysis reports for stocks and ETFs.
322 GitHub stars~1.7k tokensUpdated yesterday
Business, Finance & HRAuto-check passed
Westock Data
infometa/workbuddyskills
金融市场结构化数据查询的权威入口。支持股票（A股/港股/美股/日韩股）、ETF、指数、板块、期货、外汇、可转债的行情、财报、研报、新闻、公告、事件、股东、分红、ETF持仓、热搜榜、新股/投资日历、龙虎榜等数据查询；同时支持产业链图谱、行业经营数据、申万行业估值/盈利预测/财务、全球宏观经济等数据查询；不同标的与市场支持的维度不同，具体命令与能力差异见…
346 GitHub stars~1.6k tokensUpdated today
Productivity & AutomationAuto-check passed
Web Search
heypinchy/pinchy
Search the public web for current information and fetch full pages.
182 GitHub stars~765 tokensUpdated 18 days ago
Productivity & AutomationAuto-check passed
Multi-Symbol Market Scanner
tradesdontlie/tradingview-mcp
Scans a list of trading symbols in TradingView for setups, patterns or strategy results and reports them as a ranked comparison table.
6.8k GitHub starsUsed in 2 repos~447 tokens
Business, Finance & HRAuto-check passed
Serenity Supply-Chain Research
muxuuu/serenity-skill
Researches technology and advanced-manufacturing stocks by tracing supply-chain bottlenecks, with dated evidence, profit implications and conditions that would change the view.
4.1k GitHub stars~1.9k tokensUpdated 23 days ago
Business, Finance & HRAuto-check passed

Questions about Stock Tip Scam Detector

What does Stock Tip Scam Detector do?

Scans eight warning signs behind a stock tip from a friend, chat group or online teacher and returns a four-level risk rating with evidence. Written in Chinese, this skill checks whether a stock recommendation looks like a pig-butchering scam, the investment fraud in which victims are steered into a stock by a friend, a chat group, a self-styled teacher or insider claims. It triggers on phrases such as a friend's recommendation, a group chat tip or guaranteed profit, and on direct requests to check whether a stock is safe.

When should I use Stock Tip Scam Detector?

Stock Tip Scam Detector fits situations like: A friend or chat group is pushing a specific stock; someone calling themselves a teacher offers to lead your trades; checking whether the hype around a ticker looks coordinated; screening a tip that promises guaranteed or doubled returns.

How do I install Stock Tip Scam Detector in Claude Code?

Run `npx skills add wbh604/UZI-Skill --skill trap-detector -a claude-code`. Or copy the skill folder (skills/trap-detector in wbh604/UZI-Skill) into .claude/skills/trap-detector in your project. Claude Code loads it when a task matches its description.

How do I install Stock Tip Scam Detector in Codex?

Run `npx skills add wbh604/UZI-Skill --skill trap-detector -a codex`. Or copy the skill folder (skills/trap-detector in wbh604/UZI-Skill) into .agents/skills/trap-detector in your project. Codex loads it when a task matches its description.

Can I use Stock Tip Scam Detector in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wbh604/UZI-Skill --skill trap-detector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/trap-detector, .gemini/skills/trap-detector, .github/skills/trap-detector and .opencode/skills/trap-detector in your project.

What does Stock Tip Scam Detector need to run?

SKILL.md names no scripts, command-line tools or credentials: Stock Tip Scam Detector is instructions for the agent only. Our summary lists: Web search access; The repository's fetch_financials, fetch_sentiment and fetch_kline tools.

Does Stock Tip Scam Detector access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Stock Tip Scam Detector safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Stock Tip Scam Detector use?

Stock Tip Scam Detector is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Stock Tip Scam Detector use?

About 450 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 637 tokens, read only when the agent opens those files.

What are the alternatives to Stock Tip Scam Detector?

Skills that share tags, products or a category with Stock Tip Scam Detector: Pay Via Agent Wallet (circlefin/skills, 155 stars), Finance Report (AojdevStudio/Finance-Guru, 322 stars), Westock Data (infometa/workbuddyskills, 346 stars) and Web Search (heypinchy/pinchy, 182 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Stock Tip Scam Detector?

wbh604 (a GitHub user) maintains it in wbh604/UZI-Skill, which has 7,130 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 5, 2026.

Source: wbh604/UZI-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Stock Tip Scam Detector

Install Stock Tip Scam Detector

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Trap Detector · 杀猪盘检测器

触发场景

8 信号扫描清单

风险评级

用户关键词加权

输出格式

完成检查

Files

Compare with similar skills

Similar skills

Pay Via Agent Wallet

Finance Report

Westock Data

Web Search

Multi-Symbol Market Scanner

Serenity Supply-Chain Research

More from wbh604/UZI-Skill

Stock Deep Analysis Workflow

Investor Panel Stock Review

Dragon Tiger List Analyzer

UZI Stock Analysis

Questions about Stock Tip Scam Detector

Install Stock Tip Scam Detector

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Trap Detector · 杀猪盘检测器

触发场景

8 信号扫描清单

风险评级

用户关键词加权

输出格式

完成检查

Files

Compare with similar skills

Similar skills

More from wbh604/UZI-Skill

Related

Questions about Stock Tip Scam Detector