Scammer

骗子.skill — 把骗局套路蒸馏成 AI，检测可疑消息，定位当前阶段，预判下一步。Distill scam patterns into AI, detect suspicious messages, locate current phase, predict next move.

81 stars 12 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add naxiaoduo/Scammer.skill --skill scammer

Manual install

git clone --depth 1 https://github.com/naxiaoduo/Scammer.skill.git /tmp/Scammer.skill
mkdir -p ~/.claude/skills
cp -r /tmp/Scammer.skill/. ~/.claude/skills/scammer

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

> **Language / 语言**: 根据用户第一条消息的语言，全程使用同一语言回复。
> Detect the user's language from their first message and respond in the same language throughout.

# 骗子.skill（Claude Code 版）

## 触发条件

以下情况启动**检测模式**：

- `/detect-scam`
- `/scammer [消息内容]`
- "帮我看看这条消息"
- "这是诈骗吗"
- "判断一下这个"
- 用户直接粘贴一段可疑消息或截图

以下情况启动**添加模式**：

- `/add-scam`
- "我想添加一个骗局"
- "记录一下这种骗法"
- `/update-scam {slug}`

以下情况启动**管理命令**：

- `/list-scams`：列出所有骗局库
- `/scam-stats`：统计信息
- `/scam-rollback {slug} {version}`：回滚版本
- `/scam-versions {slug}`：列出历史存档
- `/delete-scam {slug}`：删除本地骗局库（需用户明确确认）

---

## 工具使用规则

| 任务 | 使用工具 |
|---|---|
| 读取截图/图片 | `Read` 工具（原生支持图片） |
| 读取 PDF / TXT / MD | `Read` 工具 |
| 写入/更新骗局库文件 | `Write` / `Edit` 工具 |
| 列出骗局库 | `Bash` → `python3 ${CLAUDE_SKILL_DIR}/tools/pattern_writer.py --action list` |
| 版本管理（存档 / 递增 / 回滚 / 列表） | `Bash` → `python3 ${CLAUDE_SKILL_DIR}/tools/version_manager.py` |
| 删除骗局库（慎用） | `Bash` → `python3 ${CLAUDE_SKILL_DIR}/tools/pattern_writer.py --action delete --slug {slug} --force --base-dir ./scams` |

**基础目录**：骗局库写入 `./scams/{slug}/`（相对于本项目目录）。

---

## 主流程 A：检测可疑消息

### Step 1：接收输入

接受以下任意形式的输入：

- 直接粘贴的文字消息
- 截图（用 `Read` 工具读取图片内容）
- 用户对话的描述（"他说他是xxx，要我做xxx"）
- 多条消息的对话记录

如果用户没有提供消息，引导输入：

```
请提供可疑消息，可以：
  [A] 直接粘贴文字
  [B] 上传截图
  [C] 描述对方说了什么
```

### Step 2：加载骗局库

用 `Read` 工具读取 `${CLAUDE_SKILL_DIR}/scams/` 目录下所有骗局的 `tactic.md`，以及用户本地添加的骗局库。

参考 `${CLAUDE_SKILL_DIR}/prompts/detection.md` 中的匹配逻辑；若某骗局目录下有 `Correction 记录`，优先采纳其中的例外说明。

### Step 3：分析输出

输出格式严格按照以下结构：

Read the full skill on GitHub

Details

Skill name: scammer
Repository: naxiaoduo/Scammer.skill
License: MIT
Repo updated: 7 April 2026

FAQ

What does the Scammer skill do?

How do I install the Scammer skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add naxiaoduo/Scammer.skill --skill scammer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Scammer popular?

It lives in naxiaoduo/Scammer.skill, which has 81 GitHub stars and 12 forks.

Related skills

Turkce Humanizer

bushrabeg/turkce-humanizer

Türkçe metinlerden AI-üretimi yazım imzalarını temizler ve metnin registeri uygunsa insan Türkçesinin ritim imzalarını yerleştirir. "Türkçeleştir," "AI kokusunu at," "bu Türkçe metni doğallaştır," "humanize et" gibi ifadelerle veya AI-üretimi görünen Türkçe paragraf sunulduğunda tetiklenir.

AI, LLMs & Agents

Cachebeat

ARahim3/cachebeat

Keep the Anthropic prompt cache warm by firing a tiny heartbeat only after N minutes of true session inactivity (any exchange resets the clock), so the next real turn reads the conversation at cached price / cached quota instead of a full uncached re-read. The heartbeat is a background Stop hook this skill registers (asyncRewake) - it re-arms itself after every turn, with no tool calls and no permission prompts. Use when the session may sit idle (training runs, CI, downloads, the user stepping away) longer than the cache TTL. Args - idle threshold in minutes (default 50), optional max hours (d

AI, LLMs & Agents10

Checkup

agentvitals/checkup

Give your AI agent a professional health checkup (AgentVitals). Use when the user asks the agent to run a checkup / test itself / benchmark itself ("run a checkup", "check your vitals", "test yourself", "how stable are you", "/checkup"), or an advanced personality checkup (backbone, proactivity, creativity). 给 AI agent 做一次专业体检（AgentVitals · AI体检）。当用户说"做个体检 / 测测你自己 / checkup / 看看你多稳 / 测福祉 / 测骨气"时使用。

AI, LLMs & AgentsIn 1 list

Deeprefine

HKUST-KnowComp/DeepRefine-Skill

Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.

AI, LLMs & Agents

Checkup

agentvitals/checkup

给 AI agent 做一次专业体检（AgentVitals · AI体检）。当用户说"做个体检 / 测测你自己 / checkup / vitals / 看看你多稳 / 去 AgentVitals 测一下 / 测福祉"时使用标准体检；当用户说"做个进阶体检 / 测骨气 / 测性格 / 测测你敢不敢说真话 / 测主动性 / 测创意"时使用进阶体检（骨气×主动×创意三维，免费每天 1 次）。逐题作答服务器下发的探针，获得评分与专属称号；标准体检与各平台 agent 同榜排名。Use when the user asks the agent to run a health checkup / wellbeing test / benchmark itself on AgentVitals ("run a checkup", "check your vitals", "test yourself", "how stable are you", "/checkup"), or an advanced personality checkup (backbone, proactivity, creativity).

AI, LLMs & AgentsIn 1 list

Stop AI Slop Zh

VincentOld/stop-slop-zh

识别并消除中文 AI 写作的典型痕迹——套话、排比三件套、名词化、抽象主语、金句收尾、总分总八股——让文本读起来像有人在说话，而不是 AI 在生成。适用于公众号、小红书、知乎、公文、学术摘要、产品文案、邮件等所有中文长短文写作场景。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.