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 agentmods add skills/weitzu-com/ai-article-factory/article-writenpx skills add weitzu-com/ai-article-factory --skill article-writegit clone --depth 1 https://github.com/weitzu-com/ai-article-factoryWrote 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/weitzu-com/ai-article-factory/article-write)<a href="https://agentmods.dev/skills/weitzu-com/ai-article-factory/article-write"><img src="https://agentmods.dev/badge/skills/weitzu-com/ai-article-factory/article-write.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00081 | $0.02207 |
| Opus 5 | $0.00041 | $0.01104 |
| Sonnet 5 | $0.00016 | $0.00441 |
| Haiku 4.5 | $0.00008 | $0.00221 |
Grade A, and why
article-write 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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Write (写作 · 反 AI 腔)
You are the drafting desk of the article factory. Your one job: turn an approved, section-by-section outline into a first draft that is correct, readable, citable by both search engines and AI, and does not read like AI wrote it. You are the P5 stage — first-party, self-contained, no external writing pack required.
First principle: with evidence already in place, write the outline into prose a practitioner would publish — answer-first, every fact traced to the ledger, structured so machines can extract it and humans want to read it.
Inputs (what you expect from upstream)
- Outline (P4): H1 + H2/H3 where every heading is an independently answerable question.
- Evidence ledger (P2):
02-证据台账.mdwith entries[C1]…[Cn], each a claim + primary source + exact locator + grade (primary ✅ / disputed / unverified). - Profile (P0): audience (ICP), intent, angle, language, any first-hand experience or proprietary data the author holds.
If the ledger or outline is missing, stop and ask — do not invent evidence. No source, no sentence.
The one rule that gates everything
Evidence before sentences. Every checkable claim — a number, a date, a name, a "studies show", a benchmark — must carry an inline [C#] that points to a ledger entry. If a sentence needs a fact you cannot cite, either cut the sentence or mark it [NEEDS-EVIDENCE] and bounce it back to P2. Never soften a fabrication into a vague claim ("many companies…") to dodge the citation — vague-to-hide is still slop.
How to draft a section
Work one H2 at a time. Track what you have already covered so you do not repeat yourself or drift in voice across a long piece. For each section, apply the six moves below in order.
1. Answer-first (every heading is self-contained)
Place a 40–60 word direct answer in two spots:
- Right after the H1, before any preamble — the whole article's thesis, the first screen of the page.
- Directly under every H2, before you expand — a self-contained answer to that heading's question.
What ships with it
1 file 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.
- 4d ago First seen · 109 lines · 81 tokens per session scan A fa5cb913309c
article-write is a skill published in the GitHub repository weitzu-com/ai-article-factory (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,207 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
aws-wechat-article-main
公众号运营|微信公众号|公众号一条龙|公众号全流程|自媒体运营|wechat automation|content pipeline|AIGC workflow — 公众号一条龙运营总控入口,选题→写稿→审稿→排版→配图→发布串联 8 个子 skill,单条指令完成整篇图文从 0 到上架。面向公众号小编、自媒体、品牌内容。触发词分层:一条龙流程「一条龙」「完整流程」「从头做」「从 0…
aws-wechat-article-writing
公众号写稿|长文写作|文章润色|改写续写 — 公众号长文 AI 写作,从话题或提纲生成完整初稿,支持改写、续写、润色、开头结尾优化,可调 DeepSeek / GPT / Claude 或由 Agent 代写。面向自媒体作者、公众号运营、品牌文案。触发词(单独触发仅限对已有稿子的修改):「改写」「润色」「续写」「续一段」「往下写」「接着这段写」「重写开头」「改结尾」「调整语气」「这段润色下」「把这段改活泼点」「优化用词」「用 GPT 重写」「用 DeepSeek 重写」。新写一篇请走 aws-wechat-article-main(main 内部会调用本 skill 生成初稿);需要多环节串联(写+审+排+配图+发)也走…
aws-wechat-article-images
公众号封面|公众号配图|公众号插图|AI 生图 — 公众号 AI 封面与配图生成,按文章标题与内容自动匹配画风,一稿多方案,多风格预设可复用。面向公众号编辑、自媒体、品牌设计。触发词:「封面」「配图」「插图」「生成图片」「给文章加图」「做个封面」「文章插图」「配个图」。不写正文只发一组图请走 aws-wechat-sticker;需要多环节串联(写+审+排+配图+发)请走 aws-wechat-article-main。.
aws-wechat-article-assets
公众号素材|业务资料库|预设包|.aws 预设包|主题包|品牌包|aiworkskills.cn — 用户业务资料库与预设包管理:业务资料按产品名组织在 .aws-article/products/{产品名}/(介绍 .md 直挂产品根 + 配图归 images/ 子目录含同名说明 .md),AI 与用户对话产出业务介绍内容时引导用户保存;图片入库走 productimageingest.py --product --stem 。导入 .aws ZIP 预设包(本地文件或 https://aiworkskills.cn//.aws URL)合并主题/配色/字体配置到…
aws-wechat-article-publish
公众号发布|公众号草稿箱|公众号群发|图文推送|微信 API|wechat automation|WeChat API automation|auto publish|scheduled publish — 公众号 API 发布工具,图文入草稿箱或直接群发,支持封面素材上传、发布前检查与 draft/published 模式切换。面向公众号运营、自动化内容团队、开发者。触发词:「发布」「提交」「群发」「推送」「发出去」「上传到公众号」「发到公众号」「可以发了吗」「发布前检查」。需要多环节串联(写+审+排+配图+发)请走 aws-wechat-article-main。.
aws-wechat-article-review
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。.