Guide · Agent skill
How to use the BreadcrumbList Schema Auditor agent skill
Updated · written with AI from the project's own documentation and checked against our catalogue data
The breadcrumb agent skill is a set of instructions that lets an AI agent audit whether a website's breadcrumb navigation is marked up correctly for search engines. It is for front-end developers, SEO staff and teams reviewing templates before launch. After reading this guide you will know how to install the skill, how to ask for an audit in plain language, and how to read what the agent reports back.
BreadcrumbList Schema Auditorthedaviddias/Front-End-Checklist · MIT Download the skill Quick start
- 1Download the ZIP. Get the breadcrumb skill ZIP from this page.
- 2Unzip the folder. Confirm it contains SKILL.md and references/rule.md.
- 3Place or upload the skill. Put it in ~/.claude/skills/ or a project's .claude/skills/, or upload it under Settings → Capabilities → Skills in the Claude apps.
- 4Ask a breadcrumb question. Describe the pages to audit using words like breadcrumbs, BreadcrumbList or structured data.
- 5Review the findings. Check each flagged route or template against the visible breadcrumb trail.
- 6Apply and re-check. Make the suggested fix, then ask the agent to verify the rendered page and HTTP response again.
What are agent skills, and what does this one do?
An agent skill is a folder of instructions that an AI agent loads when your request matches the skill's description. This one is based on the rule 'Implement valid BreadcrumbList schema' from the Front-End Checklist project.
Once installed, the agent checks that the JSON-LD BreadcrumbList data matches the breadcrumb trail visitors actually see. It also checks that the rendered HTML and HTTP responses are consistent with the source files, and it can point out which routes or templates have problems and explain how to fix them.
- Confirms the page has a visible, meaningful breadcrumb trail before expecting BreadcrumbList data
- Compares the breadcrumb path with the site's logical hierarchy
- Checks each level with ListItem properties in JSON-LD
- Flags exact routes or templates where search-facing output breaks the rule
Install the breadcrumb skill
Download the ZIP for the breadcrumb skill from this page and unzip it. The skill is made of two files: SKILL.md and references/rule.md.
For a personal install, place the unzipped folder in ~/.claude/skills/. To limit it to one project, place it in that project's .claude/skills/ folder instead.
If you use the Claude apps, you can instead upload the skill under Settings → Capabilities → Skills.
- Personal: ~/.claude/skills/
- Single project: .claude/skills/ inside the project
- Claude apps: Settings → Capabilities → Skills, then upload
How to trigger the skill with natural requests
You do not need a special command. Describe what you want audited in ordinary words that mention breadcrumbs, structured data or indexability, because the skill's description focuses on those topics.
Give the agent access to the rendered page or its HTTP response where you can. The skill asks the agent to verify the rendered HTML and HTTP response rather than relying only on source files.
- "Check the breadcrumb structured data on our product templates."
- "Does the BreadcrumbList JSON-LD match the visible breadcrumbs on the blog pages?"
- "Audit breadcrumb schema for crawlability and indexability issues before launch."
- "Tell me which routes output BreadcrumbList data that doesn't match the trail."
Example: what a correct BreadcrumbList looks like
The rule reference includes this example. Each ListItem has a position, a name and an item URL. The example shows a two-level trail: Blog, then SEO Tips.
When the agent reviews a page, it compares output like this with the breadcrumb links visitors see on screen. If the names, order or URLs differ, it reports the mismatch.
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "BreadcrumbList",
"itemListElement": [{
"@type": "ListItem",
"position": 1,
"name": "Blog",
"item": "https://example.com/blog"
},{
"@type": "ListItem",
"position": 2,
"name": "SEO Tips",
"item": "https://example.com/blog/seo-tips"
}]
}
</script>What the skill will not do
The skill covers only the breadcrumb rule. It does not run a full SEO audit. It also advises against adding BreadcrumbList data to a site without a visible breadcrumb trail. It only describes how markup should be structured, so do not expect it to guarantee any change in rankings.
- Sites without a visible breadcrumb trail: the skill advises against adding this markup
- Full SEO audits beyond breadcrumbs: out of scope
- Guaranteed ranking changes: not promised
Safety notes and requirements
The skill lists no requirements. It does not run scripts and does not use the network, according to its listing. It is a set of instructions the agent reads, so it does not install software or make web requests on its own. Whatever the agent does to fetch your pages depends on the tools your agent environment gives it.
Read SKILL.md and references/rule.md before installing any skill, as with any file you add to an agent.
- Requirements: none listed
- Runs scripts: no
- Uses network: no
Tips for better audits
Name the specific routes or templates you care about. The skill is designed to flag exact routes, so a list of URLs or template names gives more useful output than a general request.
Check the visible page before trusting the markup. The skill's first question is whether the breadcrumb trail is visible and meaningful.
- Give a list of example URLs for each template type
- Ask for the fix as well as the problem
- Re-run the audit after you change the template and compare the final rendered output
What people use it for
- Checking that product pages output a BreadcrumbList matching their category trail
- Reviewing blog templates before launch for crawlability and indexability problems
- Confirming that breadcrumb markup matches the rendered HTML rather than only the source files
- Finding routes where structured data exists but no visible breadcrumb trail is shown
Frequently asked questions
How do I install the breadcrumb agent skill?
Download the ZIP from this page and unzip it. Place the folder in ~/.claude/skills/ for personal use or in a project's .claude/skills/ folder, or upload it in the Claude apps under Settings → Capabilities → Skills.
Does the breadcrumb skill require anything else to run?
The skill lists no requirements. Its listing says it runs no scripts and uses no network, so it is a set of instructions for the agent.
Is the breadcrumb skill free?
The skill is released under the MIT licence, as listed on this page. Check the licence file in the source repository for the full terms.
Does the skill add breadcrumbs to my site?
No. It audits existing markup and describes how BreadcrumbList data should be structured. It advises against adding this markup to sites without a visible breadcrumb trail.
Will fixing breadcrumb schema improve my rankings?
The skill does not promise ranking changes. It explains that breadcrumbs help search engines understand site structure and can appear in search results in a more readable form.
What if the agent's findings do not match my site?
Check the rendered page and HTTP response yourself, since the skill asks the agent to verify those rather than relying only on source files. Share the exact URL and template so the agent can recheck.
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 are a front-end developer or SEO practitioner who wants a focused check that breadcrumb JSON-LD matches the trail visitors see. Pick a broader SEO audit tool if you need coverage beyond breadcrumbs or guaranteed ranking guidance.
Download the skill