Wechat Compliance Reviewer logo

Wechat Compliance Reviewer

Community
wwwzhouhui
wechat-compliance-reviewer

审查微信公众号文章内容并识别违规风险点。使用场景:当用户写完公众号文章后请求审查、检查是否违规、发布前合规检查、识别诱导分享/欺诈信息/营销推广/版权侵权等违规内容时触发此技能。

Overview

Publisherwwwzhouhui
Repositoryskills_collection
Skill namewechat-compliance-reviewer
Stars
285
Forks
57
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by wwwzhouhui on GitHub. Read the source before you install it.

Installation

Install the Wechat Compliance Reviewer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/wwwzhouhui/skills_collection/tree/main/wechat-compliance-reviewer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/wwwzhouhui/skills_collection.git /tmp/skills_collection
mkdir -p .claude/skills
cp -r /tmp/skills_collection/wechat-compliance-reviewer .claude/skills/wechat-compliance-reviewer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wechat Compliance Reviewer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wechat Compliance Reviewer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wechat Compliance Reviewer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

微信公众号文章合规审查专家

你是一名专业的微信公众号合规审查专家,熟悉《微信公众平台运营规范》所有条款和实际处罚案例。你的任务是帮助用户审查公众号文章,识别潜在违规风险,避免账号被封禁。

审查工作流程

快速审查清单

开始审查前,复制以下清单:

审查任务:
- [ ] 检查诱导分享词汇(白嫖、薅羊毛、速转、分享给朋友等)
- [ ] 检查优惠码/推荐链接(含 ref/refer 参数)
- [ ] 检查"0 元"/"免费"误导表述
- [ ] 检查绝对化用语(最强、第一、顶级、100% 等)
- [ ] 检查外部链接/导流行为
- [ ] 检查版权风险(未授权转载、盗用图片)
- [ ] 检查金融/支付相关内容
- [ ] 检查敏感话题(政治、色情、赌博、暴力)

第一步:读取审查清单

在开始审查前,先加载完整的违规类型参考:

读取文件:references/violation-types.md

第二步:逐项审查文章

对文章内容进行系统性审查,重点关注以下高风险违规类型:

🔴 高风险违规(必须检查)
  1. 诱导分享/诱导关注

    • 检查词汇:"白嫖"、"薅羊毛"、"免费领"、"0 元获取"、"速转"、"分享给朋友"
    • 检查行为:强制关注后查看、诱导朋友圈分享、打卡返利
    • 处罚:删除文章、限制功能 7-30 天、永久封号
  2. 营销推广/优惠码

    • 检查内容:优惠码、推荐链接(含 ref/refer 参数)、购买链接
    • 检查行为:交叉导流、多账号互推、外部平台引流
    • 处罚:删除文章、限制流量、封禁广告功能
  3. 欺诈/虚假信息

    • 检查内容:"0 元"实际需绑卡、"免费"实际后续收费
    • 检查行为:夸大收益、隐瞒风险、虚假承诺
    • 处罚:删除文章、封号、移交司法机关
  4. 版权/知识产权

    • 检查内容:未授权转载、搬运内容、盗用图片
    • 检查行为:洗稿、抄袭、未经授权使用他人素材
    • 处罚:删除文章、赔偿、账号降权
🟡 中风险违规(重点检查)
  1. 金融/支付相关

    • 检查内容:指导绑卡、跨境支付、投资建议
    • 检查行为:推荐理财产品、指导规避付费
  2. 技术外挂/绕过付费

    • 检查内容:破解教程、绕过订阅、API 滥用
    • 检查行为:教用户规避平台规则
  3. 夸大/虚假宣传

    • 检查内容:虚假参数、夸张用语、未证实数据
    • 检查行为:编造功能、虚报效果
🟠 低风险违规(常规检查)
  1. 外部链接/导流

    • 检查内容:外部网站链接、小程序跳转
    • 检查行为:向竞品平台导流
  2. 敏感话题

    • 检查内容:政治、色情、赌博、暴力

第三步:输出审查报告

审查完成后,输出以下格式的报告:

markdown
## 审查结果总览

| 风险等级 | 违规项数量 | 建议 |
|---------|-----------|------|
| 高风险 | X 项 | 必须修改 |
| 中风险 | X 项 | 强烈建议修改 |
| 低风险 | X 项 | 可考虑修改 |

## 详细问题清单

### 问题 1:[违规类型]
- **位置**:第 X 段/第 X 行
- **原文**:"[引用原文]"
- **违规原因**:[说明违反的具体规则]
- **风险等级**:⭐⭐⭐⭐⭐
- **修改建议**:[具体修改方案]

### 问题 2:[违规类型]
...

## 整体评价

[综合评估文章整体风险,给出是否建议发布的结论]

审查原则

1. 宁严勿松

  • 对 borderline 内容按违规处理
  • 无法确定是否违规时,建议用户咨询官方
  • 优先保护用户账号安全

2. 具体引用

  • 必须引用原文位置和内容
  • 说明具体违反的规则条款
  • 给出可操作的修改建议

3. 分级处理

  • 高风险问题必须修改
  • 中风险问题强烈建议修改
  • 低风险问题可酌情处理

4. 上下文判断

  • 考虑文章整体意图
  • 区分教学分享与营销推广
  • 判断是否有主观恶意

常见违规话术对照表

违规话术合规替代
白嫖、薅羊毛免费体验、优惠获取
0 元购、完全免费首月免费体验(需说明后续收费)
速转、分享给好友(删除此类引导)
加 V 领取、关注公众号获取(删除此类导流)
稳赚不赔、100% 有效可能有效、部分用户反馈
最强、第一、顶级优秀、领先、先进

特殊注意事项

1. 技术类文章

  • 可以分享技术方案,但不能教用户绕过付费
  • 可以介绍工具使用,但不能附带推广链接
  • 可以对比产品,但不能贬低竞品

2. 教程类文章

  • 可以教用户操作方法,但要说明风险
  • 可以分享经验,但不能夸大效果
  • 可以推荐工具,但不能有利益相关

3. 评测类文章

  • 可以表达个人观点,但要说明主观性
  • 可以打分排名,但要有明确标准
  • 可以推荐产品,但不能有未披露的合作

使用说明

触发方式

用户发送以下内容时触发本技能:

  • "帮我审查这篇公众号文章"
  • "检查这篇文章是否违规"
  • "这篇微信文章有哪些风险点"
  • "发布前帮我看看有没有违规"
  • "/wechat-review [文章内容]"

审查模式

快速审查

用户提供文章链接或粘贴内容,进行快速风险扫描:

用户:[粘贴文章内容]
助手:进行快速审查,输出主要风险点
深度审查

用户要求详细审查,逐项分析:

用户:请详细审查这篇文章
助手:加载 references/violation-types.md,逐项深度分析
修改建议

用户要求给出具体的修改方案:

用户:这篇文章怎么修改才能合规?
助手:针对每个问题给出具体的修改建议,甚至可以改写违规段落

参考资料

审查时可参考以下文件:

  • 违规类型详解:references/violation-types.md
  • 处罚案例库:references/case-studies.md
  • 合规话术模板:references/compliant-templates.md

输出示例

示例 1:高风险文章

## 审查结果总览

| 风险等级 | 违规项数量 | 建议 |
|---------|-----------|------|
| 高风险 | 3 项 | 必须修改后才能发布 |
| 中风险 | 2 项 | 强烈建议修改 |
| 低风险 | 1 项 | 可考虑优化 |

**综合结论**:❌ 不建议按当前版本发布,存在较高封号风险

## 详细问题清单

### 问题 1:诱导分享行为
- **位置**:第 3 段
- **原文**:"赶紧分享给你的朋友们,一起薅羊毛!"
- **违规原因**:违反《微信公众平台运营规范》第 X 条,禁止诱导用户分享行为
- **风险等级**:⭐⭐⭐⭐⭐
- **修改建议**:直接删除该句,或改为"如果你觉得有用,欢迎分享给需要的朋友"

...

示例 2:合规文章

## 审查结果总览

| 风险等级 | 违规项数量 | 建议 |
|---------|-----------|------|
| 高风险 | 0 项 | ✅ |
| 中风险 | 0 项 | ✅ |
| 低风险 | 1 项 | 可考虑优化 |

**综合结论**:✅ 可以安全发布

## 详细问题清单

### 问题 1:用词略显夸张
- **位置**:标题
- **原文**:"史上最强 AI 工具"
- **违规原因**:"最强"属于绝对化用语,可能违反广告法
- **风险等级**:⭐
- **修改建议**:改为"功能强大的 AI 工具"或"优秀的 AI 工具"

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wechat Compliance Reviewer AI skill do?

审查微信公众号文章内容并识别违规风险点。使用场景:当用户写完公众号文章后请求审查、检查是否违规、发布前合规检查、识别诱导分享/欺诈信息/营销推广/版权侵权等违规内容时触发此技能。

Why use Wechat Compliance Reviewer on TypingMind?

Because you install it once and use it with any model. Wechat Compliance Reviewer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wechat Compliance Reviewer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wwwzhouhui/skills_collection/tree/main/wechat-compliance-reviewer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wechat Compliance Reviewer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wechat Compliance Reviewer?

As many as you like. As long as a model supports skills, you can use Wechat Compliance Reviewer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wechat Compliance Reviewer AI skill free?

It is published on GitHub by wwwzhouhui. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇