Skip to content

aiworkskills/wechat-article-skills / skills/aws-wechat-article-review

aws-wechat-article-review

Verified

公众号审稿|公众号校对|敏感词检测|内容合规 — 公众号发布前合规审查:敏感词扫描、错别字检测、政治合规、平台规范校验,一次性输出修改清单。面向公众号编辑、自媒体作者、合规岗。触发词:「审稿」「审核」「校对」「合规」「敏感词」「错别字」「稿子检查一下」「稿子帮我看看」「稿子写完了」「文章检查一下」「检查下有没有问题」「能不能发」「发布前检查」。需要多环节串联(写+审+排+配图+发)请走 aws-wechat-article-main。

FileKindSize
SKILL.mdskill md10.2 KB
references/ai-flavor-check-samples.mdmarkdown3.8 KB
references/ai-flavor-check.mdmarkdown8.3 KB
references/branches.mdmarkdown4.3 KB
references/checklist.mdmarkdown4.1 KB
references/output-format.mdmarkdown3.2 KB
skill.jsonconfig467 B

references/checklist.md

View on GitHub
# 审稿检查清单

## 内容审检查项(writing 之后)

### 机器自检(先跑,再人工过下面各项)

```bash
{python} {baseDir}/../aws-wechat-article-writing/scripts/write.py check <本篇 draft.md>
```

- [ ] 脚本退出码为 0(硬性项 → 🔴,提醒项 → 🟡)
- [ ] **读一遍它打印的加粗串**:像不像一份能独立看懂的提要?像词云或像把段落重念一遍,都是挑错了——这一条脚本量不出来

覆盖的是产出配额里能数出来的部分:`>` 导语、加粗密度与长度、关键数字覆盖、`- **标签**:说明` 列表、带出处的金句恰好一处。与 [writing 第 7 步](../../aws-wechat-article-writing/SKILL.md) 同一套判据。

### 标题

- [ ] 字数不超过 `title_max_length`
- [ ] 不含 `forbidden_title_phrases` 中的套路
- [ ] 与正文内容一致,不做标题党
- [ ] 有吸引力,能让读者想点进来

### 摘要

- [ ] 字数在 `summary_length` 范围内
- [ ] 能概括文章核心价值
- [ ] 与正文内容一致
- [ ] 不是正文第一段的复制
- [ ] **与正文首个 `>` 导语不是同一句话**(实测 7 篇逐字相同——摘要在后台列表里出现一次、导语在正文开头再出现一次,读者等于同一段读两遍)

### 正文内容

- [ ] 不含 `custom_sensitive_words` 和 `forbidden_words`
- [ ] 无明显错别字和语病
- [ ] 事实与数据有出处(如适用)
- [ ] 原创/转载标注按 `original_attribution` 处理
- [ ] 开头 2-3 句有吸引力

### 写作规范合规

对照 `.aws-article/writing-spec.md` 检查(如有):

- [ ] 用词规范:标点、中英文间距、数字格式
- [ ] 句式偏好:句长、主动语态、无套话
- [ ] 段落规范:段长、核心观点位置
- [ ] 禁止事项:无夸张承诺、无未验证数据(AI 味单列,见下「AI 味自检」节)
- [ ] 品牌调性:与规范中的调性描述一致

### AI 味自检

对照 [ai-flavor-check.md](ai-flavor-check.md) 的指纹库逐处诊断,命中处引用原句并标注信号强度(强/中/弱):

- [ ] 句式:无工整三段式排比扎堆、无「不是 X 是 Y」滥用(800 字内 ≥3 次才算)、无翻译腔
- [ ] 观点:有取舍重点,非面面俱到;无反复让步两头讨好
- [ ] 收尾:无「你值得 / 愿你」式空洞祝福、无强行拔高升华、无「总而言之」八股
- [ ] 开头:无「随着…的发展」「在当今时代」等万能套话
- [ ] 质感:无命名仪式感、无模板化假故事、无概念名词扎堆缺具体

> **判级**:本节命中**默认 🟡 建议修改,只诊断不强制改、不阻断定稿**。先判体裁(长文/短文案/标题宽严不同),尊重 writing-spec 鼓励的口语对话与生活化类比(不算 AI 味)。拿不准宁可不报。

### 配图标记

- [ ] 封面标记存在(`![封面:...]`)
- [ ] 配图数量与 `image_density` 配置匹配
- [ ] 每个标记的描述清晰、有具体内容(不是泛泛的「配图」)
- [ ] 标记类型合理(信息图/氛围/实证等与段落内容匹配)
- [ ] 实证类标记注明了需用户提供

### 结构

- [ ] 小标题密度符合 `heading_density`
- [ ] 结尾有力(总结/金句/行动号召)
- [ ] 文末引导区块按 `closing_block` 处理
- [ ] 若 config 中配置了 `target_word_count`,篇幅应在该范围内

---

## 终审检查项(publish 之前)

在内容审的基础上,额外检查:

### 排版

- [ ] `article.html` 存在且内容完整
- [ ] HTML 中无乱码或格式异常

### 图片

- [ ] `imgs/` 目录存在
- [ ] 封面图已生成,在**文章目录下**(`cover.png` / `.jpg` / `.jpeg` / `.webp`)——**不在 `imgs/` 里**,`publish.py upload-thumb` 也是按这个位置找
- [ ] 所有 `placeholder` 已替换为实际图片路径
- [ ] 图片文件实际存在

### 发布要素

- [ ] 标题、摘要、作者已最终确认
- [ ] 正文无未替换的占位符或草稿标记
- [ ] 如需开启评论/仅粉丝可评,已确认设置

---

## 自定义规则

`.aws-article/presets/review-rules.yaml` 中的规则追加在标准项之后执行。
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall