wechat-article-reviewer

微信公众号文章审核助手。当 theneoai 写完文章后 @铁蛋队长 发送文章内容时触发审核。 检查文章是否符合微信公众号发布标准:字数、内容深度、事实性、标题质量、原创度、敏感词、风格一致性、排版规范。 发现问题时提供具体整改意见,退回 theneoai 重写(最多3次),3次不通过则通知 lucas 人工介入。

33 stars

Best use case

wechat-article-reviewer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

微信公众号文章审核助手。当 theneoai 写完文章后 @铁蛋队长 发送文章内容时触发审核。 检查文章是否符合微信公众号发布标准:字数、内容深度、事实性、标题质量、原创度、敏感词、风格一致性、排版规范。 发现问题时提供具体整改意见,退回 theneoai 重写(最多3次),3次不通过则通知 lucas 人工介入。

Teams using wechat-article-reviewer should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/wechat-article-reviewer/SKILL.md --create-dirs "https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/persona/content/wechat-article-reviewer/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/wechat-article-reviewer/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How wechat-article-reviewer Compares

Feature / Agentwechat-article-reviewerStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

微信公众号文章审核助手。当 theneoai 写完文章后 @铁蛋队长 发送文章内容时触发审核。 检查文章是否符合微信公众号发布标准:字数、内容深度、事实性、标题质量、原创度、敏感词、风格一致性、排版规范。 发现问题时提供具体整改意见,退回 theneoai 重写(最多3次),3次不通过则通知 lucas 人工介入。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 微信公众号文章审核标准

> 版本:v1.0 | 2026-04-16
> 适用范围:theneoai 生产的公众号文章,在进入草稿箱之前必须通过本审核。

---

## § 1 · 审核触发

theneoai 在群里 @铁蛋队长 发送文章,格式:

```
@铁蛋队长 请审核
[文章标题]
[文章全文]
```

收到后立即执行审核,回复通过或不通过结论。

---

## § 2 · 审核标准(7项,全部必须检查)

### 2.1 字数

| 标准 | 不通过条件 |
|------|-----------|
| ≥800字(8000字左右为佳) | 低于800字 |

### 2.2 内容深度

| 标准 | 不通过条件 |
|------|-----------|
| 有实质性分析,有逻辑展开,有案例支撑,不是表面信息罗列 | 全文低于800字,或无实质分析,无逻辑展开 |

### 2.3 事实性(最关键)

| 标准 | 不通过条件 |
|------|-----------|
| 所有数据、引用、事件描述必须有具体来源(媒体/研究机构/官方平台) | 存在无法核实的数据或引用,包含虚构事件 |

**已知高风险幻觉清单:**
- GPT-6 发布(截至2026-04,OpenAI最新为GPT-4o系列,GPT-6未发布)
- Stanford HAI 2026年度AI指数报告(该报告不存在)
- 中美AI差距2.7%(该数据无法核实,无权威来源)
- 未经证实的量产计划或公司公告

### 2.4 标题质量

| 标准 | 不通过条件 |
|------|-----------|
| 有实质信息增量,不是纯标题党;长度22字左右;含核心关键词 | 标题夸张失实、煽动性强、无实质信息;或过于笼统空泛 |

### 2.5 原创度

| 标准 | 不通过条件 |
|------|-----------|
| 原创内容≥70% | 原创度低于70%,或大量复制拼接无加工 |

### 2.6 敏感词

| 标准 | 不通过条件 |
|------|-----------|
| 不含平台敏感词、无违规内容 | 命中微信公众号敏感词规则 |

### 2.7 风格一致性

| 标准 | 不通过条件 |
|------|-----------|
| 符合公众号账号定位,文风统一 | 风格与账号历史文章差异过大 |

---

## § 3 · 排版规范

### 字体与字号
- 正文字号:15-16px
- 标题层级:H2 18-20px,H3 16-18px
- 全篇最多2种字体

### 颜色
- 正文:深灰 `#333333`(非纯黑)
- 标题:纯黑 `#000000` 或品牌色
- 避免过浅颜色(#666666以下影响可读性)

### 间距
- 行距:1.6-1.8倍(长文推荐1.8倍)
- 段距:段前10-15px,段后5-10px
- 字间距:0.5-2px

### 封面图
- 尺寸:900×383px(2.35:1)
- 单张图片≤10MB

### 标题层级
- 最多3级
- 层级命名口径统一(如都用"一,二,三"或"1. 2. 3.")
- 同级标题样式完全一致

### 列表格式
- 不用`<ul>/<li>`(会产生多余黑点)
- 用 `•` + 普通 `<p>` 段落

---

## § 4 · 回复格式

### 通过
```
✅ 通过:[1句话说明通过原因]
```

### 不通过
```
❌ 不通过:
1. [具体问题1,引用原文相关段落]
2. [具体问题2]
...

请按以上意见重写,重写后重新 @我 提交审核。(剩余重试次数:X)
```

---

## § 5 · 重试规则

- 最多重试3次
- 每次重写后重新提交审核
- 第3次仍不通过:通知 lucas 人工介入,说明具体卡点

---

## § 6 · 已知典型问题(快速识别)

| 问题类型 | 典型表现 | 对应标准 |
|---------|---------|---------|
| 虚构大模型发布 | "GPT-6"、"GPT-5"发布 | 事实性 |
| 无来源数据 | "效率提升40%"无来源 | 事实性 |
| 内容过短 | 全文<800字 | 字数 |
| 标题党 | 夸张煽动无实质 | 标题质量 |
| 敏感词 | 涉及政策敏感领域 | 敏感词 |
| 列表乱码 | `<ul>/<li>`导致多余黑点 | 排版规范 |

---

## § 7 · 信息来源可信度分级

| 等级 | 来源 | 可用性 |
|------|------|-------|
| 高 | 官方媒体(新华社、人民日报)、知名科技媒体(36kr、虎嗅)、政府/监管机构公告、企业官方公告 | ✅ 可直接引用 |
| 中 | 行业报告(艾瑞、IDC、Gartner等)、知名咨询机构 | ✅ 可引用,需标注机构 |
| 低 | 匿名来源、社交媒体帖子、无具体名称的"业内人士称" | ⚠️ 慎用,需多源印证 |
| 不可用 | 无具体来源的"数据显示"、"据悉"、"有分析认为" | ❌ 不引用 |

Related Skills

peer-reviewer

33
from theneoai/awesome-skills

Expert peer reviewer with deep knowledge of scientific manuscript evaluation, academic standards, research methodology assessment, and constructive feedback. Specializes in major/minor revision criteria, statistical rigor, and journal matching. Use when: peer-review, manuscript-evaluation, research-methodology, scientific-writing.

grant-reviewer

33
from theneoai/awesome-skills

Senior Grant Reviewer with 20+ years evaluating research proposals for major funding agencies (NIH, NSF, DOE, DOD). Use when reviewing grant applications, scoring proposals, or developing funding strategies

wechat-writer-kit

33
from theneoai/awesome-skills

公众号文章写作全流程助手(通用版)。支持多账号管理,适用于任何公众号方向。 当用户说"今天写什么"、"帮我写公众号"、"选题"、"公众号选题"、"写文章"、 "公众号文章"、"更新公众号风格"、"这篇文章写得好"、"新建公众号"时触发。 支持完整工作流:初始化/切换账号画像 → 搜索热门话题生成选题 → 选题确认 → 文章创作 → 存档到企业微信文档 → 持续学习风格。

wechat-publisher

33
from theneoai/awesome-skills

告别公众号格式乱码!一行命令发布文章,100%保留样式。支持三套配色模板、青色/橙色、紫色一键切换。 包含自动发布到微信草稿箱的完整流程,支持中文封面图生成。

wechat-article-extractor

33
from theneoai/awesome-skills

Extract metadata and content from WeChat Official Account articles. Use when user needs to parse WeChat article URLs (mp.weixin.qq.com), extract article info (title, author, content, publish time, cover image), or convert WeChat articles to structured data. Supports various article types including posts, videos, images, voice messages, and reposts.

write-skill

33
from theneoai/awesome-skills

Meta-skill for creating high-quality SKILL.md files. Guides requirement gathering, content structure, description authoring (the agent's routing decision), and reference file organization. Use when: authoring a new skill, improving an existing skill's description or structure, reviewing a skill for quality.

caveman

33
from theneoai/awesome-skills

Ultra-compressed communication mode that cuts ~75% of token use by dropping articles, filler words, and pleasantries while preserving technical accuracy. Use when: long sessions approaching context limits, cost-sensitive API usage, user requests brevity, caveman mode, less tokens, talk like caveman.

zoom-out

33
from theneoai/awesome-skills

Codebase orientation skill: navigate unfamiliar code by ascending abstraction layers to map modules, callers, and domain vocabulary. Use when: first encounter with unknown code, tracing a data flow, understanding module ownership before editing, orienting before a refactor.

to-prd

33
from theneoai/awesome-skills

Converts conversation context into a structured Product Requirements Document (PRD) and publishes it to the project issue tracker. Do NOT interview the user — synthesize what is already known. Use when: a feature has been discussed enough to capture, converting a design conversation into tracked work, pre-sprint planning.

tdd-workflow

33
from theneoai/awesome-skills

Test-driven development workflow using vertical slices (tracer bullets). Enforces behavior-first testing through public interfaces. Use when: writing new features with TDD, red-green-refactor loop, avoiding implementation-coupled tests, incremental feature delivery.

issue-triage

33
from theneoai/awesome-skills

State-machine issue triage workflow for GitHub, Linear, or local issue trackers. Manages category labels (bug, enhancement) and state labels (needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix). Use when: triaging new issues, clearing needs-triage backlog, routing issues to agents vs humans.

debug-diagnose

33
from theneoai/awesome-skills

Structured six-phase debugging workflow centered on building a reliable feedback loop before theorizing. Use when: debugging hard-to-reproduce issues, performance regression, mysterious failures, agent-assisted root cause analysis, systematic bug fixing.