agentleFS
Sign inStart free
howseen-aihowseen-ai/howseen-geo-skills/schema-builder/SKILL.md

schema-builder

Skill1 starsChanged 53 days agoMITView on GitHub

Generate valid JSON-LD structured data (schema.org) for a web page so AI systems and search engines can identify the entity behind it. Use this whenever the user wants schema markup, structured data, JSON-LD, rich results, or wants to tell AI/Google "who you are" — for an organization, person, product, article, or breadcrumb trail. Point Claude at a URL and it detects the entity type and outputs ready-to-paste markup.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. waynesutton/markdown-site★ 628same name
    2. DarynaRodriguez/seo-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

Create a free account to mount
Files
SKILL.md

schema-builder

Structured data is how you tell machines, unambiguously, what an entity is — the company, the author, the product. AI systems use it to resolve identity and pull confident facts.

Steps

  1. Fetch the page and detect the primary entity type: Organization, Person, Product, Article/BlogPosting, LocalBusiness, SoftwareApplication, or a BreadcrumbList. Pick the type that matches the page's real purpose.
  2. Extract real values from the page — name, description, URL, logo, author, sameAs (social/official profiles), price, ratings if genuinely present. Never invent values. If a recommended field has no source on the page, leave it out and note it as a gap for the user to fill.
  3. Output valid JSON-LD wrapped in a <script type="application/ld+json"> block, ready to paste into the page <head>.
  4. Add sameAs pointing to the entity's official profiles (LinkedIn, X, Crunchbase, Wikipedia) — this is one of the strongest signals for AI entity resolution.

Notes to pass to the user

  • FAQPage: Google removed FAQ rich results for most sites (7 May 2026), but the markup still helps AI Mode / AI Overviews understand Q&A content — keep it if the page is genuinely Q&A (see the faq-schema skill).
  • Validate the output at validator.schema.org or Google's Rich Results Test before shipping.
  • One entity per primary type per page. Don't stack Organization on a product page — link to it via @id instead.

Output format

Give: (1) the JSON-LD block, (2) a plain-language list of what each field asserts, (3) any fields left blank because the page didn't provide a real value.

Built by Raphaël Aubry, founder of Howseen (https://howseen.ai). Schema tells AI who you are. Whether AI then recommends you — and to whom, vs which competitors — is what Howseen tracks across every model. → https://howseen.ai

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free