Seo Schema logo

Seo Schema

Community
Littlpinguin
seo-schema

Détecter, valider et générer des données structurées Schema.org (JSON-LD) pour {{COMPANY_NAME}} — Organization, Article, FAQ (si éligible), Event, Person, etc. Connaît les types actifs, restreints et dépréciés par Google. Utiliser quand l'utilisateur dit « schema », « données structurées », « rich results », « JSON-LD », « balisage » ou après publication d'un article/d'une page.

Overview

PublisherLittlpinguin
Repositorymarketing-cockpit-template
Skill nameseo-schema
Stars
9
Forks
0
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Littlpinguin on GitHub. Read the source before you install it.

Installation

Install the Seo Schema AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Littlpinguin/marketing-cockpit-template/tree/main/.claude/skills/seo-schema
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Littlpinguin/marketing-cockpit-template.git /tmp/marketing-cockpit-template
mkdir -p .claude/skills
cp -r /tmp/marketing-cockpit-template/.claude/skills/seo-schema .claude/skills/seo-schema
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Seo Schema in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Seo Schema on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Seo Schema is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

seo-schema — données structurées

Skill d'analyse et de génération technique (pas de copy — pas de doctrine de marque requise, mais les données injectées doivent venir de sources réelles : site, 01-brand/messaging-framework.md). Adapté du plugin claude-seo (AgriciDaniel, MIT) — voir docs/vendored-seo.md.

Détection

  1. Scanner la source de la page : JSON-LD <script type="application/ld+json"> (format à privilégier — préférence déclarée de Google), Microdata (itemscope/itemprop), RDFa.
  2. Valider : @context présent, @type valide, propriétés requises par type, URLs absolues, formats de date ISO, aucun texte placeholder résiduel.
  3. Signaler les types dépréciés ou restreints (liste ci-dessous).

Statut des types (état février 2026 — re-vérifier à chaque re-sync)

ACTIFS (recommander librement) : Organization, LocalBusiness, SoftwareApplication, WebApplication, Product, Offer, Service, Article, BlogPosting, NewsArticle, Review, AggregateRating, BreadcrumbList, WebSite, WebPage, Person, ProfilePage, ContactPage, VideoObject, ImageObject, Event, JobPosting, Course, DiscussionForumPosting.

RESTREINTS :

  • FAQPage : rich results réservés aux sites gouvernementaux et de santé faisant autorité (restriction août 2023). Le balisage reste utile pour la compréhension machine (GEO), mais ne pas promettre de rich result.

DÉPRÉCIÉS (ne jamais recommander) :

  • HowTo (rich results supprimés sept. 2023), SpecialAnnouncement (juil. 2025), ClaimReview, VehicleListing, CourseInfo, EstimatedSalary, LearningVideo (retirés 2025).

Rendu JavaScript : du JSON-LD injecté en JS peut être traité avec retard. Pour un balisage sensible au temps (Event, Offer), l'inclure dans le HTML servi côté serveur.

Génération

  1. Identifier le type de page (article, événement, page entreprise, offre…).
  2. Choisir le(s) type(s) de schema appropriés.
  3. Générer un JSON-LD valide avec propriétés requises + recommandées.
  4. Uniquement des données véridiques et vérifiables. Marquer clairement [À COMPLÉTER] ce qui manque — ne jamais inventer un téléphone, une adresse, une note.
  5. Valider avant de livrer (parse JSON + propriétés requises).

Gabarits usuels pour {{COMPANY_NAME}}

Organization (page d'accueil / à propos)

json
{
  "@context": "https://schema.org",
  "@type": "Organization",
  "name": "{{COMPANY_NAME}}",
  "url": "{{COMPANY_WEBSITE}}",
  "logo": "[URL logo]",
  "sameAs": ["[LinkedIn]", "[autres profils]"]
}

Article / BlogPosting (articles 09-seo/)

json
{
  "@context": "https://schema.org",
  "@type": "Article",
  "headline": "[Titre]",
  "author": { "@type": "Person", "name": "[Auteur]" },
  "datePublished": "[YYYY-MM-DD]",
  "dateModified": "[YYYY-MM-DD]",
  "image": "[URL image]",
  "publisher": {
    "@type": "Organization",
    "name": "{{COMPANY_NAME}}",
    "logo": { "@type": "ImageObject", "url": "[URL logo]" }
  }
}

Event (webinaires, événements 07-events/)

json
{
  "@context": "https://schema.org",
  "@type": "Event",
  "name": "[Nom]",
  "startDate": "[YYYY-MM-DDTHH:MM+01:00]",
  "eventAttendanceMode": "https://schema.org/OnlineEventAttendanceMode",
  "location": { "@type": "VirtualLocation", "url": "[URL]" },
  "organizer": { "@type": "Organization", "name": "{{COMPANY_NAME}}", "url": "{{COMPANY_WEBSITE}}" }
}

Sortie

  • Tableau de validation : | Schema | Type | Statut ✅/⚠️/❌ | Problèmes |
  • Opportunités manquantes par page
  • Snippets JSON-LD prêts à intégrer (fichier à côté du livrable concerné, ex. 09-seo/articles/… ou 05-web-content/…)

Gestion d'erreur

CasAction
Aucun balisage détectéLe dire, puis recommander les types adaptés au contenu de la page
JSON-LD invalidePointer l'erreur de syntaxe précise et fournir la version corrigée
Type déprécié détectéSignaler avec la date de retrait, proposer remplacement ou suppression

Frequently asked questions

What does the Seo Schema AI skill do?

Détecter, valider et générer des données structurées Schema.org (JSON-LD) pour {{COMPANY_NAME}} — Organization, Article, FAQ (si éligible), Event, Person, etc. Connaît les types actifs, restreints et dépréciés par Google. Utiliser quand l'utilisateur dit « schema », « données structurées », « rich results », « JSON-LD », « balisage » ou après publication d'un article/d'une page.

Why use Seo Schema on TypingMind?

Because you install it once and use it with any model. Seo Schema is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Seo Schema in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Littlpinguin/marketing-cockpit-template/tree/main/.claude/skills/seo-schema. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Seo Schema?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Seo Schema?

As many as you like. As long as a model supports skills, you can use Seo Schema with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Seo Schema AI skill free?

Yes. It is published on GitHub by Littlpinguin under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇