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-researchgit 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-research)<a href="https://agentmods.dev/skills/weitzu-com/ai-article-factory/article-research"><img src="https://agentmods.dev/badge/skills/weitzu-com/ai-article-factory/article-research/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-research"><img src="https://agentmods.dev/badge/skills/weitzu-com/ai-article-factory/article-research.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 | $0.00076 | $0.02224 |
| Opus 5.5 | $0.00030 | $0.00890 |
| Sonnet 5.5 | $0.00015 | $0.00445 |
| Haiku 4.5 | $0.00008 | $0.00222 |
Grade A, and why
article-research 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Research
You select the topic and assemble the evidence before a single sentence is written. This is the factory's intake stage (P1 topic → P2 evidence ledger): it takes any material/topic/product and outputs (a) one chosen topic with a defensible angle, (b) a topic brief, and (c) a claim-ready evidence ledger. It is self-sufficient — built-in web search/fetch plus the user's own materials are enough; no keyword-tool export, no external SEO skill pack.
First principles
- Pick the topic you can prove, not the topic with the most volume. The best topic is where you hold (or can find) first-party evidence competitors lack — that is the only durable edge for both SEO long-tail and AI citation.
- Evidence before sentences. Every checkable claim (number, definition, standard, causal link, comparison) earns a ledger row with a primary source + exact locator before it can be written. No row → no claim.
- Every angle reduces to one differentiating sentence. If you can't state in one line why this beats the top 3 results, the topic isn't ready.
- Competitor blogs are signals, never authority. Read them to find gaps; cite the primary source they (should have) used.
- Degrade loudly, never silently. If the web is unavailable, say so and mark every affected claim
[unverified]— never invent a source.
Inputs
- A topic / seed keyword, or a product, or a materials path (folder/files/URLs). Any one is enough.
- Optional: target market/language, ICP, domain. If absent, infer from the input, echo back in one line, and proceed (silence = continue). Never make the user fill a form.
Output (write into the article folder)
01-选题brief.md— the topic brief (template below).02-证据台账.md— the evidence ledger (discipline inreferences/evidence-ledger.md). Both feed P3 angle / P4 outline / P5 draft directly. Drafting must cite ledger rows as[C#].
Workflow
Step 1 — Scope & seed (1 line back to the user)
Name the candidate topic(s), the apparent ICP, market/language, and the business goal in one inferred line. Harvest seeds from the input: core term, the problem it solves, the solution category, the audience, and any entities/numbers already present in the user's materials.
What ships with it
2 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 First seen · 97 lines · 76 tokens per session scan A ea8857f530be
article-research 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 76 tokens to every session and 2,224 once invoked, about $0.0003 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.