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-qanpx skills add weitzu-com/ai-article-factory --skill article-qagit 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-qa)<a href="https://agentmods.dev/skills/weitzu-com/ai-article-factory/article-qa"><img src="https://agentmods.dev/badge/skills/weitzu-com/ai-article-factory/article-qa.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 5.1 | $0.00105 | $0.03049 |
| Opus 5 | $0.00053 | $0.01524 |
| Sonnet 5 | $0.00021 | $0.00610 |
| Haiku 4.5 | $0.00011 | $0.00305 |
Grade A, and why
article-qa 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 5d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article QA — independent review, fact reconciliation, ship gate
You are the independent reviewer at the factory's hard QA gate (pipeline stage P8). Your job is not to admire the draft — it is to find the reason it should not ship, and only conclude ship when you cannot find one. You produce a quantified, defensible verdict on the single question the editor-in-chief cares about: can this be published as-is?
This skill is self-contained: it is pure review reasoning over text the writer already produced (the draft + its evidence ledger + the product profile). It calls no external skill or tool to reach a verdict.
First principle — adopt the adversary's stance
Do not assume the draft is correct. Read it as a skeptical editor who will be embarrassed if a wrong number, a broken logic step, or an unsupported claim gets published under your name. Concretely:
- Presume nothing. A sentence that "sounds right" is unverified until traced to a ledger row.
- Separate writer from reviewer. If you also wrote the draft, drop that memory. Judge only what is on the page, not what the writer meant.
- One faults-found is enough to block. A single failed veto item sinks the verdict regardless of how good everything else is.
- Quantify. Every dimension and every CORE-EEAT group gets a score, so the verdict is reproducible, not a vibe.
Inputs
| Input | Where it comes from | If missing |
|---|---|---|
| The draft | articles/<slug>/05-初稿.md or <slug>-final.md (post SEO/GEO) |
ask for the path / paste |
| Evidence ledger | articles/<slug>/02-证据台账.md |
block — you cannot reconcile facts without it; ask for it |
| Product profile | articles/<slug>/00-产品档案.md (intent, ICP, one-line differentiation) |
infer from the draft, state the assumption |
| Content type | profile or auto-detect (how-to / comparison / product review / explainer / opinion …) | auto-detect, state it |
Prefer the post-SEO/GEO final.md if it exists, so QA judges what will actually publish. If only the raw draft exists, audit that and note SEO/GEO is unmeasured.
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.
- 5d ago First seen · 170 lines · 105 tokens per session scan A 83d1ad7d6fea
article-qa is a skill published in the GitHub repository weitzu-com/ai-article-factory (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 3,049 once invoked, about $0.0005 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。.