Guide · Agent skill
How to use the Article Structured Data Audit agent skill
Updated · written with AI from the project's own documentation and checked against our catalogue data
The Article Structured Data Audit skill (skill name: article) teaches an AI agent to review a web page for Article structured data, the hidden machine-readable labels that tell search engines what a post or news story is, who wrote it, and when it was published. It is aimed at website and blog owners, front-end developers reviewing article templates, and SEO specialists checking metadata on content sites. After this guide you will know how to install the skill, ask for an audit in plain language, and read what the agent checks.
Article Structured Data Auditthedaviddias/Front-End-Checklist · MIT Download the skill Quick start
- 1Download the ZIP. Get the article skill ZIP from the skill's page on the directory.
- 2Unzip into a skills folder. Extract it to ~/.claude/skills/ for all projects, or to .claude/skills/ inside a project for one project only.
- 3Or upload in the Claude apps. Go to Settings → Capabilities → Skills and upload the skill there.
- 4Ask for an audit. Describe the page or template and ask the agent to check Article structured data.
- 5Provide the rendered output. Paste the rendered HTML or HTTP response headers so the agent can compare them with the source.
- 6Fix and re-verify. Apply the JSON-LD changes the agent suggests, then check the final page output again.
What the skill makes the agent do
Agent skills are folders of instructions that an AI agent loads when a task matches them. This one covers the Article structured data rule from the Front-End Checklist project. When it applies, the agent checks that the page contains valid Article markup with the required properties, and it advises checking the rendered HTML and HTTP response rather than relying only on source files.
The skill names three Schema.org types for content: Article, NewsArticle and BlogPosting. It lists headline, image, datePublished and author as required properties, and recommends writing the data as JSON-LD. For fixes, it describes adding a JSON-LD script block with the Article schema for the current page.
- Checks the markup uses Article, NewsArticle or BlogPosting
- Checks required properties such as headline, image, datePublished and author
- Checks the data is written as JSON-LD
- Flags exact routes or templates where search-facing output violates the rule
- Explains how Article schema affects Google Discover, News and standard search results
Install the Article skill
Download the ZIP for the skill from the directory page and unzip it. For Claude Code, place the unzipped folder in ~/.claude/skills/ to make it available everywhere, or in a project's .claude/skills/ folder to limit it to that project. The folder should contain SKILL.md and a references folder holding rule.md.
In the Claude apps, you can instead upload the skill under Settings → Capabilities → Skills.
- Personal install: ~/.claude/skills/ (available across projects)
- Project install: .claude/skills/ inside your project
- Claude apps: Settings → Capabilities → Skills, then upload
Trigger the skill with natural requests
You do not need a special command. The skill's description covers auditing metadata, crawlability, structured data and indexability for Article markup, so ask for that in ordinary language and mention the page or template you care about. Naming the page type helps the agent pick the skill up.
- Audit the Article structured data on this blog post and tell me what is missing.
- Check whether our news article template outputs valid NewsArticle JSON-LD.
- Review our article page template for headline, image, datePublished and author fields.
- Does this post's structured data match what the rendered HTML shows?
What the audit looks at and what you get back
The skill asks the agent to compare the source files with the rendered HTML and the HTTP response, because a template can look correct in code while the live page outputs something different. The guidance also covers how to verify the final page output.
The skill is based on its text files. It does not test a live URL itself, so for a real check of a published page you should still use the search engine's own testing tools.
- Missing or wrong @type (Article, NewsArticle or BlogPosting)
- Missing required properties such as headline, image, datePublished or author
- Markup that is not JSON-LD
- Differences between source templates and the rendered page
Safety notes: scripts and network
According to the listing, this skill does not run scripts and does not use the network. It requires nothing beyond the skill files themselves. That means the agent works from the text in SKILL.md and references/rule.md, and it cannot fetch your live page on its own. If you want the agent to see the rendered output, paste the HTML or response headers into the conversation.
- Runs scripts: no
- Uses network: no
- Requirements listed: none
What people use it for
- Reviewing a blog post template for headline, image, datePublished and author fields
- Checking that a news section outputs NewsArticle rather than a generic type
- Comparing source templates with rendered HTML to find markup that differs on the live page
- Drafting a JSON-LD Article block for a page that has none
Frequently asked questions
Is the Article Structured Data Audit skill free?
The skill is released under the MIT licence, according to its listing. The listing does not mention any price, so check the source repository for the licence terms that apply to you.
What do I need to run this skill?
The listing says it requires nothing beyond the skill files. It does not run scripts and does not use the network, so the agent works from the included text files.
Where do I install an agent skill?
Unzip the skill folder into ~/.claude/skills/ for personal use or into a project's .claude/skills/ folder. In the Claude apps you can upload it under Settings → Capabilities → Skills.
Will this skill make my pages rank higher?
No. Structured data helps your content become eligible for rich results, but it does not guarantee visibility in search. The skill makes no promise of rankings.
Can the skill test my live URL in Google Search Console?
No. The skill is based on its text files and does not test a live URL or connect to search consoles. Use the search engine's own tools for live verification.
Which schema types does the skill check?
It checks Schema.org Article, NewsArticle and BlogPosting, with headline, image, datePublished and author as required properties, written as JSON-LD.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
Use this skill if you run a blog or news site, maintain article templates, or audit SEO metadata on content pages and want an agent to check Article JSON-LD against the required fields. Pick something else if your site has no article content, since Article markup does not apply, or if you need the tool to test a live URL in a search console, because this skill works from its text files alone.
Download the skill