Skills for Real Engineers. Straight from my .agents directory.
aws-wechat-article-review
Agent skill fromaiworkskills/wechat-article-skills
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。
How to install aws-wechat-article-review
npx skills add aiworkskills/wechat-article-skills# or add only this skill to Claude Code: copy the folder
skills/aws-wechat-article-review/
# into
~/.claude/skills/aws-wechat-article-review/ (all projects)
.claude/skills/aws-wechat-article-review/ (one project)
1# 审稿与合规23**公众号发布前合规守门员** —— 敏感词、错别字、平台规范一次性筛查,输出可执行修改清单。45> **套件说明** · 本 skill 属 `aws-wechat-article-*` 一条龙套件(共 9 个 slug,入口 `aws-wechat-article-main`)。跨 skill 的相对引用依赖同一 `skills/` 目录,建议一并 `clawhub install` 全套。源码:<https://github.com/aiworkskills/wechat-article-skills>67## 能力披露(Capabilities)89本 skill 为**纯本地规则/清单审稿**,零网络、零凭证。1011- **凭证**:无12- **网络**:无13- **文件读**:`.aws-article/config.yaml`、`.aws-article/writing-spec.md`(如有)、`.aws-article/presets/review-rules.yaml`(如有)、本篇 `draft.md` / `article.html` / `article.yaml` / `imgs/`14- **文件写**:本篇 `draft-stripped.md`(中间产物)、`article.md`(定稿)、`review.md`15- **shell**:只在第 5 步调 `{python} .../aws-wechat-article-writing/scripts/write.py strip-citations`,第 2 步调同一脚本的 `check` 子命令。**两者都是纯本地正则/计数,不联网、不读凭证、不调 LLM。**1617> 往期推荐链接的**自动补齐**由 [publish skill](../aws-wechat-article-publish/SKILL.md) 处理(那里才有微信 API 凭证与 `getdraft.py`);本 skill 只按已有 `manual` 排占位符,**不直接调任何网络脚本**。1819## 路由2021「能不能发」若含代为发布、或从稿到发出整条收尾 → [aws-wechat-article-main](../aws-wechat-article-main/SKILL.md)。2223## 两种审稿模式2425| 模式 | 时机 | 检查重点 |26|------|------|---------|27| **内容审** | writing 之后、formatting 之前 | 内容质量、写作规范、敏感词、配图标记 |28| **终审** | publish 之前 | 排版完整性、图片就位、发布要素齐全 |2930自动识别:有 `article.html` → 终审模式,否则 → 内容审模式。3132## 工作流3334```35审稿进度:36- [ ] 第1步:环境检查 + 本篇约束与规范37- [ ] 第2步:逐项检查(含机器自检)38- [ ] 第3步:输出审稿结果39- [ ] 第4步:修改循环 🔄40- [ ] 第5步:⛔ 剥离引用标注 → 文末 embed → 保存 article.md 定稿41```4243### 智能体行为约束 ⛔4445- **禁止**在未完成第 5 步「文末 embed」的情况下,把稿件称为「已定稿」、写入 `article.md`、或进入排版(`format.py`)。46…
Excerpt shown under the repository's Apache-2.0 license.
More skills in wechat-article-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
