Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-formattinggit clone --depth 1 https://github.com/aiworkskills/wechat-article-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aiworkskills/wechat-article-skills/aws-wechat-article-formatting)<a href="https://agentmods.dev/skills/aiworkskills/wechat-article-skills/aws-wechat-article-formatting"><img src="https://agentmods.dev/badge/skills/aiworkskills/wechat-article-skills/aws-wechat-article-formatting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aiworkskills/wechat-article-skills/aws-wechat-article-formatting"><img src="https://agentmods.dev/badge/skills/aiworkskills/wechat-article-skills/aws-wechat-article-formatting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00168 | $0.03000 |
| Opus 5 | $0.00084 | $0.01500 |
| Sonnet 5 | $0.00034 | $0.00600 |
| Haiku 4.5 | $0.00017 | $0.00300 |
Grade A, and why
aws-wechat-article-formatting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
排版
公众号一键排版 —— Markdown 转微信后台可粘贴 HTML，多主题、多字号、所见即所得。
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
能力披露（Capabilities）
本 skill 为纯本地 Markdown → HTML 转换，零网络、零凭证。
- 凭证：无
- 网络：无
- 文件读（仓库内）：
.aws-article/config.yaml、本篇article.yaml、article.md、可选closing.md、.aws-article/presets/formatting/<名>.yaml - 文件读（仓库外）：
~/.aws-article/presets/formatting/（跨项目共享的自定义主题；只读预设文件，不读凭证） - 文件写：本篇
article.html - shell：仅
{python} {baseDir}/scripts/format.py
单独安装可直接使用：format.py 零依赖、纯本地，无跨 skill 脚本调用。文档里指向 ../aws-wechat-article-main/references/*.md 的链接在套件未装齐时会断，但排版功能本身可用。
路由
一键发文且未明确只要排版 → aws-wechat-article-main。
配置检查 ⛔
任何操作前先按 首次引导 · 检测顺序 执行，通过后才继续（或用户明确书面确认「本次不检查」）。单独启用本 skill 时同样。
内置模版
排版 = 模版（骨架：标题装饰、导语、金句卡、图片处理、分隔、文末）× 配色（一组主色/次色，派生色自动重算）。名字即用途，选之前先看「适合」：
| 模版 | 适合 | 不适合 | 配色（第一个是默认） |
|---|---|---|---|
亲和 |
教程、职场、面向新手的解释性长文 | 严肃议题、极简冷硬的品牌 | 黛紫 / 松绿 / 靛蓝 |
资讯 |
快讯、评测、行业观察 | 抒情散文、碎片化短段 | 墨绿 / 绛红 / 藏青 |
书卷 |
人文、读书、历史、深度长文 | 工程文档、数据密集的评测 | 朱砂 / 黛蓝 / 苍绿 |
杂志 |
品牌故事、人物访谈、生活方式 | 没有配图的稿子、信息型短文 | 石青 / 驼褐 / 铁锈 |
不传 --theme 时的内置默认是 亲和。
另外四套不随 skill 内置，在 aiworkskills.cn 选好模版和配色后随 .aws 预设包下发到 .aws-article/presets/formatting/（见 assets skill）：活力（产品发布、增长复盘）、手账（个人笔记、复盘）、硬朗（观点、宣言）、技术（工程实践、代码讲解）。网站上选的配色会烘进 YAML 顶层 variables，落地后不需要额外配置。
选之前先跑一次，判据、色值、每套配色的口径都在输出里，别只按名字猜：
{python} {baseDir}/scripts/format.py --list-themes
说不清就看：--preview 把样张渲成并列对照页（每栏 375px，与真机同宽），用浏览器打开。
{python} {baseDir}/scripts/format.py --preview 亲和 -o preview.html # 该模版的每套配色并列
{python} {baseDir}/scripts/format.py --preview -o preview.html # 所有模版的默认色并列
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/branches.md 6.6 KB
- references/components/bao/article-end.yaml 149 B
- references/components/bao/checklist.yaml 1.0 KB
- references/components/bao/lead.yaml 211 B
- references/components/bao/li-label.yaml 200 B
- references/components/bao/quote-card.yaml 379 B
- references/components/cai/article-end.yaml 200 B
- references/components/cai/checklist.yaml 1.0 KB
- references/components/cai/h2-deco.yaml 160 B
- references/components/cai/img-deco.yaml 223 B
- references/components/cai/lead.yaml 317 B
- references/components/cai/li-label.yaml 202 B
- references/components/cai/quote-card.yaml 392 B
- references/components/checklist.yaml 2.1 KB
- references/components/closing.yaml 1.7 KB
- references/components/compare.yaml 2.0 KB
- references/components/gou/article-end.yaml 512 B
- references/components/gou/checklist.yaml 1012 B
- references/components/gou/h2-deco.yaml 459 B
- references/components/gou/hr-deco.yaml 353 B
- references/components/gou/img-deco.yaml 298 B
- references/components/gou/lead.yaml 589 B
- references/components/gou/li-label.yaml 196 B
- references/components/gou/quote-card.yaml 727 B
- references/components/kuai/article-end.yaml 270 B
- references/components/kuai/checklist.yaml 1.0 KB
- references/components/kuai/lead.yaml 218 B
- references/components/kuai/li-label.yaml 202 B
- references/components/kuai/quote-card.yaml 332 B
- references/components/layers.yaml 1.5 KB
- references/components/lead.yaml 1.4 KB
- references/components/ma/article-end.yaml 307 B
- references/components/ma/checklist.yaml 1.0 KB
- references/components/ma/h2-deco.yaml 322 B
- references/components/ma/lead.yaml 426 B
- references/components/ma/li-label.yaml 197 B
- references/components/ma/quote-card.yaml 422 B
- references/components/quote-card.yaml 1.5 KB
- references/components/section-title.yaml 1.5 KB
- references/components/shou/article-end.yaml 488 B
- references/components/shou/checklist.yaml 1.0 KB
- references/components/shou/h2-deco.yaml 526 B
- references/components/shou/hr-deco.yaml 678 B
- references/components/shou/img-deco.yaml 508 B
- references/components/shou/lead.yaml 313 B
- references/components/shou/li-label.yaml 265 B
- references/components/shou/quote-card.yaml 559 B
- references/components/shu/article-end.yaml 188 B
- references/components/shu/checklist.yaml 1.0 KB
- references/components/shu/h2-deco.yaml 360 B
- references/components/shu/hr-deco.yaml 183 B
- references/components/shu/img-deco.yaml 265 B
- references/components/shu/lead.yaml 301 B
- references/components/shu/li-label.yaml 195 B
- references/components/shu/quote-card.yaml 609 B
- references/components/stat.yaml 2.0 KB
- references/components/steps.yaml 2.2 KB
- references/components/yi/article-end.yaml 403 B
- references/components/yi/checklist.yaml 1.0 KB
- references/components/yi/h2-deco.yaml 377 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · -94 lines 01876ea04b72
- yesterday Changed · +2 lines 8aab27b699d9
- 4d ago Changed · +21 lines 475f34ee4408
- 5d ago Changed · +44 lines 079b86c3e019
- 6d ago Changed · +45 lines 7e2a48f3a902
- 7d ago Changed · +7 lines e8c258ea6e63
- 12d ago First seen · 144 lines · 168 tokens per session scan A 6f56b1d98f2a
aws-wechat-article-formatting is a skill published in the GitHub repository aiworkskills/wechat-article-skills (595 stars, last pushed today), licensed Apache-2.0. It adds 168 tokens to every session and 3,000 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
shuorenhua
A writing and editing guide for making Chinese and English text sound natural and less machine-generated, with special attention to Taiwan Traditional Chinese usage. It preserves technical terms, facts, and the responsible subject.
humanize-chinese
A Chinese-language writing guide and editing workflow for producing more natural prose and reducing formulaic AI wording.
write-cn
A set of instructions for drafting natural-sounding Chinese without common AI writing patterns. It is the first stage of a six-stage Chinese writing process.
OwnPen
A set of 45 Chinese writing rules for making text sound less machine-written while keeping its original formatting unchanged.
asc-localize-metadata
Automatically translate and sync App Store metadata (description, keywords, what's new, subtitle) to multiple languages using LLM translation and asc CLI. Use when asked to localize an app's App Store listing, translate app descriptions, or add new languages to App Store Connect.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.