mcpField
S
seo-schema

seo-schema

github.com/agricidanielMarketing & growth89482 installsUpdated 2w ago
Repository

About seo-schema

seo-schema is a ChatGPT skill for reviewing structured data and planning sourced fixes. It separates syntax, Schema.org validity, Google eligibility, and agreement with visible page facts.

Key features

  1. 01Extracts JSON-LD, Microdata, and RDFa
  2. 02Checks structured data against page facts
  3. 03Separates validation and eligibility layers
  4. 04Drafts JSON-LD from established facts
  5. 05Lists outstanding eligibility checks

Use cases

  1. 01Reviewing markup for a page
  2. 02Drafting structured data from verified facts
  3. 03Checking rich-result eligibility gaps

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/agricidaniel/chatgpt-seo --skill seo-schema

After installing, type/seo-schemain Claude Code to confirm it loaded.

Details

From the project README

Structured data

Input

Page HTML or visible entity facts and the requested rich-result purpose.

Evidence and runtime

If a skill-resource reader fails to open a linked supporting file, try the available file or execution tool using the installed plugin root returned by the host or resolved from this skill's location. Do not hardcode a home folder, version, or working directory. Distinguish a failed reader call from an absent file, and files actually attempted from files not attempted. Report a resource as unavailable only after the supported access paths have failed. If no file or execution access is available, continue within the evidence you can read and state that limit.

Read the operating contract when this workflow is selected. Use runtime and data paths when choosing a tool or handling missing data. Recheck relevant search facts and primary sources before date-sensitive claims. For a quantitative diagnostic, read scoring; unavailable categories stay unknown.

Supporting resources

Read only the resources needed for the selected part of this task:

Workflow

  1. Extract JSON-LD, Microdata or RDFa when actual source is available. Use analyze_html.py for JSON-LD syntax and type detection, not full eligibility validation.
  2. Identify the page's real entity and open the current applicable Google feature documentation. Separate JSON syntax, Schema.org validity, Google eligibility and visible-content agreement.
  3. Check required and relevant recommended properties, graph identity, absolute URLs, date formats, price/availability currency and factual review provenance.
  4. Draft markup only from established facts. Omit unsupported optional properties. If a required fact is missing, list it or deliver a clearly labeled draft rather than fictional data.
  5. Apply current FAQ/HowTo rich-result guidance. Existing FAQPage does not need automatic removal. Ratings and reviews must be genuine, visible and eligible for the entity.
  6. Parse the output JSON when execution is available. Supply the next independent check in Google's relevant validator; do not label it passed unless it was actually run.

Deliverable

A validation table with separate layers, corrected or proposed JSON-LD, a visible-fact mapping and outstanding eligibility checks.

Boundary

A parsed JSON-LD block does not establish rich-result eligibility, display, ranking improvement or AI citation benefit.

Adapted from the public Claude SEO seo-schema workflow.

Comments

Markdown supported