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 weitzu-com/ai-article-factory --skill article-optimizegit 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-optimize)<a href="https://agentmods.dev/skills/weitzu-com/ai-article-factory/article-optimize"><img src="https://agentmods.dev/badge/skills/weitzu-com/ai-article-factory/article-optimize/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/weitzu-com/ai-article-factory/article-optimize"><img src="https://agentmods.dev/badge/skills/weitzu-com/ai-article-factory/article-optimize.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.02407 |
| Opus 5.5 | $0.00025 | $0.00963 |
| Sonnet 5.5 | $0.00012 | $0.00481 |
| Haiku 4.5 | $0.00006 | $0.00241 |
Grade A, and why
article-optimize 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Optimize (SEO + GEO + Structured Data)
The factory's P7 stage, made first-party. You take an article that is already correct (P8 QA territory, not yours) and tune it so one piece does two jobs at once: gets indexed and ranked by search engines, and gets quoted by AI answer engines.
First principle
A single well-structured passage that fully answers one question — placed first, sourced, and entity-consistent — is the shared optimum for both a long-tail ranking and an AI citation. Optimize the passage, not the page chrome.
Everything below is pure on-page logic. No crawler, no keyword tool, no external skill pack is required — if those are connected the work gets sharper, but the stage runs standalone on the draft text alone.
Guardrails (read first)
- Right before optimized. If the content is wrong, thin, or unsourced, stop and hand back to QA. Do not paper over weak content with markup.
- Markup mirrors visible content. Never put a claim, rating, FAQ answer, or step in JSON-LD that a reader cannot see on the page. Mismatched schema gets the page demoted, not promoted.
- No invented facts. The "exclusive information" and any statistic must already exist in the draft (sourced via the claim ledger
[C#]). You restructure and surface; you never fabricate. - One edit, one reason. Each change you make maps to a checklist item below so the human can review it.
Workflow (8 steps)
Run in order. After each step, note what changed and why.
1. Lock the target
Identify the primary query (the one phrase the article must own) and 2–4 secondary/long-tail queries. Identify the canonical entity (brand / product / person / concept) and its one canonical name. If the entity name varies across the draft, normalize to one spelling everywhere — AI disambiguation depends on it.
2. SEO — on-page signals
Produce these artifacts (see the SEO checklist for pass bars):
- Title tag: contains the primary query + an information-gain hook (a number, year, outcome, or angle the SERP doesn't already have). ≤ 60 Latin chars / ≤ 30 CJK chars. Do not duplicate the H1 verbatim if a sharper title wins more clicks.
- H1: one per page, contains the primary query, reads naturally.
- Meta description: ≤ 155 chars (≤ 80 for CJK), front-loads the answer, ends with a reason to click. Never keyword-stuff.
- Slug: short, hyphenated, lowercase, primary keyword, no stop-word filler, no dates that will rot.
- Internal links: ≥ 2 contextual links to related articles, descriptive anchors (no "click here"), exact-match anchors kept to 10–20% of the article's anchor mix.
- Image alt text: every image gets descriptive alt; the cover/lead image alt includes the primary query naturally.
- Heading structure: H2/H3 in a logical hierarchy, no skipped levels.
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.
- 1mo ago First seen · 127 lines · 62 tokens per session scan A da6847738166
article-optimize is a skill published in the GitHub repository weitzu-com/ai-article-factory (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 2,407 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
aws-wechat-article-writing
A writing tool for Chinese WeChat public-account articles, creating a first draft from a topic or outline and revising existing text. It can use a configured language-model service, such as DeepSeek, OpenAI, or Anthropic.
aws-wechat-article-images
An image-generation tool for Chinese WeChat public-account articles, making covers and illustrations based on an article’s title and content. It can create several visual options and reuse configured style presets.
aws-wechat-article-main
A coordinator for running a complete Chinese WeChat public-account publishing workflow. It connects separate steps such as choosing a topic, writing, reviewing, formatting, adding images, and publishing.
aws-wechat-article-assets
A local library for storing business descriptions, product images, and reusable writing or design presets for WeChat articles. It organizes these materials by product so other article tools can reuse them.