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-writinggit 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-writing)<a href="https://agentmods.dev/skills/aiworkskills/wechat-article-skills/aws-wechat-article-writing"><img src="https://agentmods.dev/badge/skills/aiworkskills/wechat-article-skills/aws-wechat-article-writing/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-writing"><img src="https://agentmods.dev/badge/skills/aiworkskills/wechat-article-skills/aws-wechat-article-writing.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 | $0.00218 | $0.04845 |
| Opus 5.5 | $0.00087 | $0.01938 |
| Sonnet 5.5 | $0.00044 | $0.00969 |
| Haiku 4.5 | $0.00022 | $0.00485 |
Grade A, and why
aws-wechat-article-writing 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 1mo ago.
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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
长文写作
公众号长文 AI 写作引擎 —— 从提纲或话题生成完整初稿，支持改写、续写、润色，多模型可切。
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 调用 write.py 生成文章初稿，会把文章内容发送给用户配置的 LLM 端点：
- 凭证读取：仓库根
aws.env的WRITING_MODEL_API_KEY - 凭证外发：该 key 以
Authorization: Bearer <key>头发送到config.yaml.writing_model.base_url配置的外部端点（DeepSeek / OpenAI / Anthropic 等 Chat Completions 兼容 API）。请使用专用 key 并配置可信端点或内部代理 - 内容外发：Prompt 内含本篇
article.yaml/topic-card.md/ 合并配置 /--reference指定的参考文档全文 → 整体 POST 给上述端点 - 文件读（仓库内）：
.aws-article/config.yaml、本篇article.yaml、topic-card.md、.aws-article/products/{产品名}/*.md - 文件读（仓库外）：仓库内
.aws-article/缺失时从~/.aws-article/读writing-spec.md与presets/（只读预设，不读凭证） - 文件写：仅本篇目录下
draft.md - shell：仅
{python} {baseDir}/scripts/write.py
write.py prompt 子命令只输出 prompt JSON 不调用 LLM，由 Agent 代写 —— 不想把内容发给第三方时走这条。
路由
从零发文、一条龙、完整流程 → aws-wechat-article-main。本 skill 单独触发仅限已有稿子的修改（改写 / 润色 / 续写）。
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」）。
写作模型：writing_model（provider、base_url、model）在 .aws-article/config.yaml；WRITING_MODEL_API_KEY 在仓库根 aws.env。键名对照 env.example.yaml。
环境检查未通过时，只按首次引导处理配置选项，不要在同一条回复里混入写稿、草稿路径或多草稿选择。须遵守 main 的智能体行为约束：未通过校验且未获用户明确「本次例外」时，不得默认改由当前 Agent 代写并假装流程完整。
工作流
写稿进度：
- [ ] 第0步：⛔ 首次引导 · 检测顺序
- [ ] 第1步：⛔ 全局账号三键非空
- [ ] 第2步：⛔ 续旧稿还是新稿（不了解时须先问）
- [ ] 第3步：读取本篇约束与写作规范
- [ ] 第4步：发布方式（publish_method）
- [ ] 第5步：确定输入与写作方式
- [ ] 第6步：写作
- [ ] 第7步：跑 check 自检
- [ ] 第8步：⛔ 展示并等待用户确认
第1步：全局账号三键 ⛔
打开 .aws-article/config.yaml，检查 article_category、target_reader、default_author 是否 trim 后均非空。任一项缺失：逐项询问用户，取得当轮明确答复后写回该文件。与 main「2) 全局账号约束」 一致。
What ships with it
5 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.
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.
- 1mo ago Changed · -130 lines 1b23b889c7ee
- 1mo ago Changed · +28 lines b99ac7c03470
- 1mo ago Changed · +39 lines be1babc3131a
- 1mo ago Changed 6926f007ee9e
- 1mo ago First seen · 272 lines · 218 tokens per session scan A a60f38d5c6ce
aws-wechat-article-writing is a skill published in the GitHub repository aiworkskills/wechat-article-skills (708 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 218 tokens to every session and 4,845 once invoked, about $0.0009 per session on Opus 5.5. 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
stop-slop-zh
A Blender animation guide for changing objects, cameras, lights, and other properties over time. It covers keyframes, motion curves, shape keys for morphs, drivers, and reusable animation actions.
anti-slop-ua
A writing skill for creating, rewriting, or reviewing Ukrainian prose. It removes wording patterns that make text sound machine-written while keeping the original facts and meaning.
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.
thoth
Build and maintain a unique, consistent LinkedIn voice for one or more users. Runs a framework-driven persona interview (brand archetypes + tone spectrum + hot-take exercises), then generates ready-to-publish LinkedIn posts across a 30/25/20/15/10 content mix (Personal / Work / Thought-leadership / Educational /…
article-qa
Use to quality-check an article before it ships — an independent reviewer that scores CORE-EEAT, reconciles every fact against the evidence ledger, and returns a ship / no-ship verdict with a fix list. First-party QA gate for the article factory (P8); needs no external packs.…
ai-article-factory
An automated workflow for turning a topic, product, or source material into illustrated articles and related publishing files. It covers research, drafting, visuals, checking, optimization, export, and platform-specific copy.