According to AlphaMoat, as of 2026-09, 微信公众号文章深度重写 has 2,938 downloads and 11 stars — ranked #3,775 of 5,078 AI skills overall, and #249 of 362 in Content.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| SkillHub ↗ | 243 | 2.9K | 11 | — |
Platforms count differently and update at different times.
Runs a six-step workflow: fetch the article with web_fetch → analyze its structure → deep rewrite (restructure, strip AI high-frequency words and empty endings sentence by sentence, rewrite the title and opening, keep code blocks intact but complete truncated examples) → save Markdown with frontmatter → generate fully inline-styled HTML → report file paths and key changes. Because the WeChat editor restricts CSS, the HTML must use inline styles and no <style> tag; articles are suggested to stay within 2000-4000 characters. All rewrites are for learning and reference only; comply with copyright law.
Profile published 2026-10-27
mp.weixin.qq.com link with a rewrite intentGenerated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 2.9K | — | 11 |
| 2026-08 | 2.1K | +25.0% | 11 |
| 2026-07 | 1.7K | +55.4% | 8 |
| 2026-06 | 1.1K | +43.3% | 3 |
| 2026-05 | 767 | — | 2 |
| 2026-03 | 310 | — | - |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
--- name: wechat-rewrite description: "微信公众号文章深度改写工具 — 输入文章URL,自动抓取原文、AI深度改写去除AI痕迹、生成可直接粘贴到微信公众号编辑器的富文本HTML。当用户说「改写公众号文章」「洗稿」「把这篇文章原创化」「生成公众号版本」时使用。" --- # ✍️ 微信公众号文章深度改写 (wechat-rewrite) **一句话用法**:给我一篇公众号文章的链接,我抓取内容 → 深度改写 → 输出可直接粘贴进公众号编辑器的富文本版本。 ---
## 触发场景
用户说以下任意一种时,加载本 Skill:
- "帮我改写/洗稿这篇公众号文章"
- "把这篇文章原创化"
- "生成公众号直接粘贴的版本"
- 给了一个 `mp.weixin.qq.com` 链接 + 改写/洗稿意图
---
## 完整工作流(必须按顺序执行)
### Step 1 — 抓取原文
使用 `web_fetch` 工具获取文章内容:
```
web_fetch(url="<用户提供的链接>", fetchInfo="获取文章完整内容,包括标题、所有正文段落、代码块、小标题")
```
如果 web_fetch 返回内容不完整(只有摘要),尝试用下载器:
```bash
cd C:\Users\CNKI\.workbuddy\skills\wechat-toolkit\scripts\downloader
npm install # 首次使用才需要
node download.js "<文章URL>" --output "d:/workbuddy/wechat-articles"
```
---
### Step 2 — 分析文章结构
读取原文后,识别:
1. **文章类型**:技术教程 / 观点评论 / 新闻资讯 / 产品介绍 / 故事叙事
2. **核心主题**:一句话概括文章讲什么
3. **段落结构**:几个主要板块,各板块讲什么
4. **特殊内容**:有无代码块、表格、数据图
---
### Step 3 — 深度改写
#### 必须执行的改写策略
**A. 结构重组(首要任务)**
- 调整段落顺序,使逻辑线不同于原文
- 将长段拆短,或合并碎片段落
- 叙事角度转换:`教程型` → `踩坑型`;`列表型` → `叙述型`;`说明型` → `对比型`
**B. 语言去AI痕迹(逐句检查)**
必须删除以下词汇和句式:
- 意义膨胀词:标志性、里程碑、深远影响、历史性
- 虚假权威:专家认为、业内普遍认为、有数据显示(没有来源的)
- 伪深度动词:赋能、赋予、加持、赋予力量、提升能力
- 广告语气:卓越、极致体验、全方位、颠覆式
- AI高频词(直接删除替换):**赋能、闭环、生态、抓手、底层逻辑、范式、沉淀、势能、护城河、降维打击**
- 填充短语(直接删除):值得注意的是、事实上、不难发现、总体来说、综合来看
- 空洞结尾(改为实际结论):未来可期、值得期待、相信XXX会带来更多可能性
**C. 标题重写**
生成 3 个备选标题,要求覆盖不同风格:
- 疑问型:"为什么XXX大多数人都答不全?"
- 数字+痛点型:"这X个XXX细节,大多数人都搞错了"
- 悬念型:"XXX的真相,做了3年才搞清楚"
**D. 开头重写**
将原文开头改为以下风格之一:
- **痛点引入**:直击读者最头疼的问题
- **场景引入**:用具体工作场景切入
- **数据引入**:用一个有趣的数字开头
- **反问引入**:抛出反直觉的问题
**E. 代码块处理**(如有)
- 代码不删改,但要补全被截断的示例
- 代码上方加一句说明这段代码解决什么问题
- 代码下方加一句说明运行效果或注意事项
#### AI痕迹检查清单(改写完执行)
| # | 检查项 | 要求 |
|---|--------|------|
| 1 | 读起来像真人说话,可以直接朗读 | ✅ |
| 2 | 无空洞句、模板段 | ✅ |
| 3 | 信息密度高,每句话有具体内容 | ✅ |
| 4 | 结构与原文明显不同 | ✅ |
| 5 | 保留核心信息 | ✅ |
| 6 | 无AI高频词 | ✅ |
---
### Step 4 — 保存改写版本(Markdown)
保存路径:`d:/workbuddy/wechat-articles/<文章主题简名>.md`
文件必须包含 frontmatter:
```markdown
---
title: <改写后的标题>
cover: https://picsum.photos/seed/<随机词>/1080/864
---
# <标题>
> <一句话引导语,说明本文价值>
---
<正文...>
```
---
### Step 5 — 生成公众号富文本HTML
这是最关键一步。生成一个**全部内联样式**的 HTML 文件,可以直接 Ctrl+A → Ctrl+C → 粘贴进微信公众号编辑器。
保存路径:`d:/workbuddy/wechat-articles/wechat-ready.html`
#### HTML模板规范
```html
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>文章标题</title>
</head>
<body style="max-width:677px;margin:0 auto;font-family:-apple-system,BlinkMacSystemFont,'PingFang SC','Microsoft YaHei',sans-serif;font-size:15px;line-height:1.8;color:#333;background:#fff;padding:20px;">
<!-- 一级标题 -->
<h1 style="font-size:22px;font-weight:700;color:#1a1a1a;line-height:1.4;margin:20px 0 10px;padding-left:12px;border-left:4px solid #1677ff;">标题文字</h1>
<!-- 二级标题(分节) -->
<h2 style="font-size:17px;font-weight:700;color:#fff;background:#1677ff;padding:8px 16px;border-radius:4px;margin:28px 0 14px;">分节标题</h2>
<!-- 三级标题 -->
<h3 style="font-size:16px;font-weight:700;color:#1677ff;margin:20px 0 8px;padding-left:10px;border-left:3px solid #1677ff;">小标题</h3>
<!-- 正文段落 -->
<p style="margin:0 0 12px;text-indent:0;">段落文字</p>
<!-- 引用块 -->
<blockquote style="margin:16px 0;padding:12px 16px;background:#f0f7ff;border-left:4px solid #1677ff;border-radius:0 4px 4px 0;color:#555;">
<p style="margin:0;">引用内容</p>
</blockquote>
<!-- 代码块(深色背景) -->
<pre style="background:#1e1e2e;color:#cdd6f4;padding:16px;border-radius:8px;overflow-x:auto;margin:16px 0;font-size:13px;line-height:1.6;"><code>代码内容</code></pre>
<!-- 行内代码 -->
<code style="background:#f0f0f0;color:#d32f2f;padding:2px 6px;border-radius:3px;font-size:13px;font-family:monospace;">inline code</code>
<!-- 表格 -->
<table style="width:100%;border-collapse:collapse;margin:16px 0;font-size:14px;">
<thead>
<tr style="background:#1677ff;color:#fff;">
<th style="padding:10px 12px;text-align:left;border:1px solid #ddd;">表头</th>
</tr>
</thead>
<tbody>
<tr style="background:#fff;">
<td style="padding:8px 12px;border:1px solid #ddd;">内容</td>
</tr>
<tr style="background:#f8f9fa;">
<td style="padding:8px 12px;border:1px solid #ddd;">内容</td>
</tr>
</tbody>
</table>
<!-- 无序列表 -->
<ul style="padding-left:20px;margin:8px 0;">
<li style="margin:4px 0;">列表项</li>
</ul>
<!-- 有序列表 -->
<ol style="padding-left:20px;margin:8px 0;">
<li style="margin:4px 0;">列表项</li>
</ol>
<!-- 分割线 -->
<hr style="border:none;border-top:1px solid #eee;margin:24px 0;">
<!-- 强调(加粗) -->
<strong style="font-weight:700;color:#1a1a1a;">重要文字</strong>
</body>
</html>
```
#### 颜色主题规范
| 元素 | 颜色值 |
|------|--------|
| 主色调(标题边框、标签背景)| `#1677ff` |
| 正文文字 | `#333333` |
| 代码块背景 | `#1e1e2e` |
| 代码块文字 | `#cdd6f4` |
| 行内代码文字 | `#d32f2f` |
| 行内代码背景 | `#f0f0f0` |
| 引用块背景 | `#f0f7ff` |
---
### Step 6 — 输出结果
完成后告知用户:
1. Markdown 文件路径
2. HTML 文件路径
3. 使用方法:浏览器打开 HTML → Ctrl+A → Ctrl+C → 粘贴进公众号编辑器
4. 简要说明改动要点(标题、结构、去掉了哪些AI痕迹)
---
## 注意事项
- 微信公众号编辑器对CSS有限制,**必须使用内联样式**,不要用 `<style>` 标签
- 代码块背景色有时公众号会覆盖掉,建议告知用户这是平台限制
- 文章字数建议控制在 **2000-4000字**,过长公众号阅读体验差
- 所有改写仅供学习参考,请遵守版权法规
Detects and removes AI writing traces so text reads more like a person wrote it.
A writing-editor skill that finds the usual marks of AI-generated text and rewrites them into more natural prose without losing the meaning.
A Chinese copy-editing skill that spots and removes the traces of AI-generated text.
wechat-search finds popular WeChat articles and organizes results by relevance, popularity and recency.
Extracts titles, descriptions, and spoken scripts from public short-video share links, with rewritten versions.
humanizer guides natural expression and style editing for Chinese and English text.
Writes web-novel chapters into files and replies in chat with summaries and pointers only.
Bundle a set of marketing playbooks into one skill and route each request to the module that fits.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.