Home · Skills · Marketing

GEO Schema & Structured Data

Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup

How to use it

Hit Copy SKILL.md — or use the Claude Code line below to get every file.
Claude: ⋯ → Download .md, then Customize → Skills → Add → Upload skill.
ChatGPT: make a Project and paste it into Instructions.
Neither? Paste it at the top of a new chat — it works for that chat.
Describe your job in plain words. The AI follows the skill from there.

Claude Code — installs the whole folder, not just SKILL.md

npx degit zubair-trabzada/geo-seo-claude/skills/geo-schema#main ~/.claude/skills/geo-schema

For one project only, change the path to .claude/skills/geo-schema. This skill also uses fetch_page.py, GEO-SCHEMA-REPORT.md — copying SKILL.md alone won't be enough. See the folder on GitHub.

Not working?

Check which app you pasted it into — the steps above name the right one.
Some skills need the paid tier of Claude or ChatGPT.

Step-by-step guide with screenshots · Ask in the forum

Paste into Claude, ChatGPT or Cursor.

Show the full text371 lines

geo-schema /

SKILL.md only. Other files in this folder →

CodePreviewgeo-schema/SKILL.md371 lines14.4 KBpushed 180d agoRawView on GitHub

GEO Schema & Structured Data

Purpose

Structured data is the primary machine-readable signal that tells AI systems what an entity IS, what it does, and how it connects to other entities. While schema markup has traditionally been about earning Google rich results, its role in GEO is fundamentally different: structured data is how AI models understand and trust your entity. A complete entity graph in structured data dramatically increases citation probability across all AI search platforms.

How to Use This Skill

Fetch the target page HTML using fetch_page.py (see note below)
Detect all existing structured data (JSON-LD, Microdata, RDFa)
Validate detected schemas against Schema.org specifications
Identify missing recommended schemas based on business type
Generate ready-to-use JSON-LD code blocks
Output GEO-SCHEMA-REPORT.md

Step 1: Detection

IMPORTANT: WebFetch converts HTML to markdown and strips <head> content, which removes JSON-LD blocks. Use fetch_page.py instead:

python3 ~/.claude/skills/geo/scripts/fetch_page.py <url> page

The output includes a structured_data array with all parsed JSON-LD blocks from the page.

Scan for JSON-LD

Look for <script type="application/ld+json"> blocks in the HTML. Parse each block as JSON. A page may contain multiple JSON-LD blocks — collect all of them.

Scan for Microdata

Look for elements with itemscope, itemtype, and itemprop attributes. Map the hierarchy of nested items. Note: Microdata is harder for AI crawlers to parse than JSON-LD. Flag a recommendation to migrate to JSON-LD if Microdata is the only format found.

Scan for RDFa

Look for elements with typeof, property, and vocab attributes. Similar to Microdata — recommend migration to JSON-LD.

Priority Order

JSON-LD is the strongly recommended format for GEO. Google, Bing, and AI platforms all process JSON-LD most reliably. If the site uses Microdata or RDFa exclusively, flag this as a high-priority migration.

Step 2: Validation

For each detected schema block, validate:

Valid JSON: Is the JSON-LD syntactically valid? Check for trailing commas, unquoted keys, malformed strings.
Valid @type: Does the @type match a recognized Schema.org type? Check against https://schema.org/docs/full.html.
Required Properties: Does the schema include all required properties for its type? (See per-type requirements below.)
Recommended Properties: Does the schema include recommended properties that increase AI discoverability?
sameAs Links: Does the schema include sameAs properties linking to other platform presences?
URL Validity: Do all URLs in the schema resolve (not 404)?
Nesting: Is the schema properly nested (e.g., author inside Article, address inside Organization)?
Rendering Method: Is the JSON-LD in the server-rendered HTML or injected via JavaScript? Per Google's December 2025 guidance, JavaScript-injected structured data may face delayed processing. Flag any schema that requires JS execution.

Step 3: Schema Types for GEO

Organization (CRITICAL — every business site)

Essential for entity recognition across all AI platforms. This is how AI models identify WHAT the business is.

Required properties:

@type: "Organization" (or subtype: Corporation, LocalBusiness, etc.)
name: Official business name
url: Official website URL
logo: URL to logo image (ImageObject preferred)

Recommended properties for GEO:

sameAs: Array of ALL platform URLs (see sameAs strategy below)
description: 1-2 sentence description of the organization
foundingDate: ISO 8601 date
founder: Person schema
address: PostalAddress schema
contactPoint: ContactPoint with telephone, email, contactType
areaServed: Geographic area
numberOfEmployees: QuantitativeValue
industry: Text or DefinedTerm
award: Array of awards received
knowsAbout: Array of topics the organization is expert in (strong GEO signal)

LocalBusiness (for businesses with physical locations)

Extends Organization. Critical for local AI search results and Google Gemini.

Additional required properties:

address: Full PostalAddress
telephone: Phone number
openingHoursSpecification: Operating hours

Recommended for GEO:

geo: GeoCoordinates (latitude, longitude)
priceRange: Price indicator
aggregateRating: AggregateRating schema
review: Array of Review schemas
hasMap: URL to Google Maps

Article + Author (CRITICAL for publishers)

The Author schema is one of the strongest E-E-A-T signals for AI platforms.

Article required:

@type: "Article" (or NewsArticle, BlogPosting, TechArticle)
headline: Article title
datePublished: ISO 8601
dateModified: ISO 8601 (critical for freshness signals)
author: Person or Organization schema
publisher: Organization schema with logo
image: Representative image

Author (Person) required for GEO:

name: Full name
url: Author page URL on the site
sameAs: LinkedIn, Twitter, personal site, Google Scholar, ORCID
jobTitle: Professional title
worksFor: Organization schema
knowsAbout: Array of expertise areas
alumniOf: Educational institutions
award: Professional awards

Product (for e-commerce)

Required:

name, description, image
offers: Offer with price, priceCurrency, availability
brand: Brand schema
sku or gtin/mpn

Recommended for GEO:

aggregateRating: AggregateRating
review: Array of individual reviews
category: Product category
material, weight, width, height (where applicable)

FAQPage

Status as of 2024: Google restricts FAQ rich results to government and health sites. However, the FAQPage schema still serves GEO purposes — AI platforms parse FAQ structured data for question-answer extraction. Implement it for AI readability even though rich results may not appear.

Structure:

@type: "FAQPage"
mainEntity: Array of Question schemas, each with acceptedAnswer containing an Answer schema

SoftwareApplication (for SaaS)

Required:

name, description
applicationCategory: e.g., "BusinessApplication"
operatingSystem: Supported platforms
offers: Pricing

Recommended for GEO:

aggregateRating: User ratings
featureList: Array of features (strong citation signal)
screenshot: Screenshots
softwareVersion: Current version
releaseNotes: Link to changelog

WebSite + SearchAction (for sitelinks search box)

Structure:

{
  "@type": "WebSite",
  "name": "Site Name",
  "url": "https://example.com",
  "potentialAction": {
    "@type": "SearchAction",
    "target": {
      "@type": "EntryPoint",
      "urlTemplate": "https://example.com/search?q={search_term_string}"
    },
    "query-input": "required name=search_term_string"
  }
}

Person (standalone — for personal brands, authors, thought leaders)

Use as a standalone schema on About/Bio pages. This builds the entity graph for individual expertise.

Required: name, url Recommended for GEO: sameAs, jobTitle, worksFor, knowsAbout, alumniOf, award, description, image

speakable Property (for voice/AI assistants)

The speakable property marks specific sections of content as particularly suitable for voice and AI assistant consumption. Add to Article or WebPage schemas.

{
  "@type": "Article",
  "speakable": {
    "@type": "SpeakableSpecification",
    "cssSelector": [".article-summary", ".key-takeaway"]
  }
}

This signals to AI assistants which passages are the best candidates for citation or reading aloud.

Step 4: Deprecated/Changed Schemas to Flag

Schema	Status	Note
HowTo	Rich results deprecated Aug 2023	Still useful for AI parsing, but do not promise rich results
FAQPage	Restricted to govt/health Aug 2023	Still useful for AI parsing (see above)
SpecialAnnouncement	Deprecated 2023	Was for COVID; remove if still present
CourseInfo	Replaced by Course updates 2024	Use updated Course schema properties
VideoObject `contentUrl`	Changed behavior 2024	Must point to actual video file, not page URL
Review snippet	Stricter enforcement 2024	Self-serving reviews on product pages may not display

Flag any deprecated schemas found and recommend replacements.

Step 5: sameAs Strategy (CRITICAL for Entity Recognition)

The sameAs property is the single most important structured data property for GEO. It tells AI systems: "This entity on my website is the SAME entity as these profiles elsewhere." This creates the entity graph that AI platforms use to verify, trust, and cite sources.

sameAs Audit Process

Collect all known web presences for the entity
Check that each URL resolves (not 404 or redirected)
Verify the Organization/Person schema includes ALL of them
Check that the information on each platform is consistent (name, description, founding date, etc.)
Flag any platforms where the entity should have a presence but does not

Step 6: JSON-LD Generation

Based on the detected business type, generate ready-to-paste JSON-LD blocks. Always generate:

Organization or Person (depending on entity type) — always
WebSite with SearchAction — always for the homepage
Business-type-specific — Article for publishers, Product for e-commerce, LocalBusiness for local, SoftwareApplication for SaaS
BreadcrumbList — for any page deeper than homepage

Generation Rules

Use the @graph pattern to include multiple schemas in one JSON-LD block
All URLs must be absolute (not relative)
Include @id properties for cross-referencing between schemas
Use ISO 8601 for all dates
Include speakable on Article schemas with CSS selectors pointing to key content sections
Place JSON-LD in <head> section — NOT injected via JavaScript

Template: Organization with Full GEO Signals

{
  "@context": "https://schema.org",
  "@type": "Organization",
  "@id": "https://example.com/#organization",
  "name": "Company Name",
  "url": "https://example.com",
  "logo": {
    "@type": "ImageObject",
    "url": "https://example.com/logo.png",
    "width": 600,
    "height": 60
  },
  "description": "Concise description of what the company does.",
  "foundingDate": "2020-01-15",
  "founder": {
    "@type": "Person",
    "name": "Founder Name",
    "sameAs": "https://www.linkedin.com/in/founder"
  },
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "123 Main St",
    "addressLocality": "City",
    "addressRegion": "State",
    "postalCode": "12345",
    "addressCountry": "US"
  },
  "contactPoint": {
    "@type": "ContactPoint",
    "telephone": "+1-555-555-5555",
    "contactType": "customer service",
    "email": "[email protected]"
  },
  "sameAs": [
    "https://en.wikipedia.org/wiki/Company_Name",
    "https://www.wikidata.org/wiki/Q12345",
    "https://www.linkedin.com/company/company-name",
    "https://www.youtube.com/@companyname",
    "https://twitter.com/companyname",
    "https://github.com/companyname",
    "https://www.crunchbase.com/organization/company-name"
  ],
  "knowsAbout": [
    "Topic 1",
    "Topic 2",
    "Topic 3"
  ]
}

Scoring Rubric (0-100)

Criterion	Points	How to Score
Organization/Person schema present and complete	15	15 if full, 10 if basic, 0 if none
sameAs links (5+ platforms)	15	3 per valid sameAs link, max 15
Article schema with author details	10	10 if full author schema, 5 if name only, 0 if none
Business-type-specific schema present	10	10 if complete, 5 if partial, 0 if missing
WebSite + SearchAction	5	5 if present, 0 if not
BreadcrumbList on inner pages	5	5 if present, 0 if not
JSON-LD format (not Microdata/RDFa)	5	5 if JSON-LD, 3 if mixed, 0 if only Microdata/RDFa
Server-rendered (not JS-injected)	10	10 if in HTML source, 5 if JS but in head, 0 if dynamic JS
speakable property on articles	5	5 if present, 0 if not
Valid JSON + valid Schema.org types	10	10 if no errors, 5 if minor issues, 0 if major errors
knowsAbout property on Organization/Person	5	5 if present with 3+ topics, 0 if missing
No deprecated schemas present	5	5 if clean, 0 if deprecated schemas found

Output Format

Generate GEO-SCHEMA-REPORT.md with:

# GEO Schema & Structured Data Report — [Domain]
Date: [Date]

## Schema Score: XX/100

## Detected Schemas
| Page | Schema Type | Format | Status | Issues |
|---|---|---|---|---|
| / | Organization | JSON-LD | Valid | Missing sameAs |
| /blog/post-1 | Article | JSON-LD | Valid | No author schema |

## Validation Results
[List each schema with pass/fail per property]

## Missing Recommended Schemas
[List schemas that should be present based on business type but are not]

## sameAs Audit
| Platform | URL | Status |
|---|---|---|
| Wikipedia | [URL or "Not found"] | Present/Missing |
| LinkedIn | [URL or "Not found"] | Present/Missing |
[Continue for all recommended platforms]

## Generated JSON-LD Code
[Ready-to-paste JSON-LD blocks for each missing or incomplete schema]

## Implementation Notes
- Where to place each JSON-LD block
- Server-rendering requirements
- Testing with Google Rich Results Test and Schema.org Validator

1	---
2	name: geo-schema
3	description: Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup
4	version: 1.0.0
5	author: geo-seo-claude
6	tags: [geo, schema, structured-data, json-ld, entity-recognition, ai-discoverability]
7	allowed-tools: Read, Grep, Glob, Bash, WebFetch, Write
8	---
9
10	# GEO Schema & Structured Data
11
12	## Purpose
13
14	Structured data is the primary machine-readable signal that tells AI systems what an entity IS, what it does, and how it connects to other entities. While schema markup has traditionally been about earning Google rich results, its role in GEO is fundamentally different: structured data is how AI models understand and trust your entity. A complete entity graph in structured data dramatically increases citation probability across all AI search platforms.
15
16	## How to Use This Skill
17
18	1. Fetch the target page HTML using `fetch_page.py` (see note below)
19	2. Detect all existing structured data (JSON-LD, Microdata, RDFa)
20	3. Validate detected schemas against Schema.org specifications
21	4. Identify missing recommended schemas based on business type
22	5. Generate ready-to-use JSON-LD code blocks
23	6. Output GEO-SCHEMA-REPORT.md
24
25	---
26
27	## Step 1: Detection
28
29	IMPORTANT: WebFetch converts HTML to markdown and strips `<head>` content, which removes JSON-LD blocks. Use `fetch_page.py` instead:
30	```bash
31	python3 ~/.claude/skills/geo/scripts/fetch_page.py <url> page
32	```
33	The output includes a `structured_data` array with all parsed JSON-LD blocks from the page.
34
35	### Scan for JSON-LD
36	Look for `<script type="application/ld+json">` blocks in the HTML. Parse each block as JSON. A page may contain multiple JSON-LD blocks — collect all of them.
37
38	### Scan for Microdata
39	Look for elements with `itemscope`, `itemtype`, and `itemprop` attributes. Map the hierarchy of nested items. Note: Microdata is harder for AI crawlers to parse than JSON-LD. Flag a recommendation to migrate to JSON-LD if Microdata is the only format found.
40
41	### Scan for RDFa
42	Look for elements with `typeof`, `property`, and `vocab` attributes. Similar to Microdata — recommend migration to JSON-LD.
43
44	### Priority Order
45	JSON-LD is the strongly recommended format for GEO. Google, Bing, and AI platforms all process JSON-LD most reliably. If the site uses Microdata or RDFa exclusively, flag this as a high-priority migration.
46
47	---
48
49	## Step 2: Validation
50
51	For each detected schema block, validate:
52
53	1. Valid JSON: Is the JSON-LD syntactically valid? Check for trailing commas, unquoted keys, malformed strings.
54	2. Valid @type: Does the `@type` match a recognized Schema.org type? Check against https://schema.org/docs/full.html.
55	3. Required Properties: Does the schema include all required properties for its type? (See per-type requirements below.)
56	4. Recommended Properties: Does the schema include recommended properties that increase AI discoverability?
57	5. sameAs Links: Does the schema include `sameAs` properties linking to other platform presences?
58	6. URL Validity: Do all URLs in the schema resolve (not 404)?
59	7. Nesting: Is the schema properly nested (e.g., author inside Article, address inside Organization)?
60	8. Rendering Method: Is the JSON-LD in the server-rendered HTML or injected via JavaScript? Per Google's December 2025 guidance, JavaScript-injected structured data may face delayed processing. Flag any schema that requires JS execution.
61
62	---
63
64	## Step 3: Schema Types for GEO
65
66	### Organization (CRITICAL — every business site)
67	Essential for entity recognition across all AI platforms. This is how AI models identify WHAT the business is.
68
69	Required properties:
70	- `@type`: "Organization" (or subtype: Corporation, LocalBusiness, etc.)
71	- `name`: Official business name
72	- `url`: Official website URL
73	- `logo`: URL to logo image (ImageObject preferred)
74
75	Recommended properties for GEO:
76	- `sameAs`: Array of ALL platform URLs (see sameAs strategy below)
77	- `description`: 1-2 sentence description of the organization
78	- `foundingDate`: ISO 8601 date
79	- `founder`: Person schema
80	- `address`: PostalAddress schema
81	- `contactPoint`: ContactPoint with telephone, email, contactType
82	- `areaServed`: Geographic area
83	- `numberOfEmployees`: QuantitativeValue
84	- `industry`: Text or DefinedTerm
85	- `award`: Array of awards received
86	- `knowsAbout`: Array of topics the organization is expert in (strong GEO signal)
87
88	### LocalBusiness (for businesses with physical locations)
89	Extends Organization. Critical for local AI search results and Google Gemini.
90
91	Additional required properties:
92	- `address`: Full PostalAddress
93	- `telephone`: Phone number
94	- `openingHoursSpecification`: Operating hours
95
96	Recommended for GEO:
97	- `geo`: GeoCoordinates (latitude, longitude)
98	- `priceRange`: Price indicator
99	- `aggregateRating`: AggregateRating schema
100	- `review`: Array of Review schemas
101	- `hasMap`: URL to Google Maps
102
103	### Article + Author (CRITICAL for publishers)
104	The Author schema is one of the strongest E-E-A-T signals for AI platforms.
105
106	Article required:
107	- `@type`: "Article" (or NewsArticle, BlogPosting, TechArticle)
108	- `headline`: Article title
109	- `datePublished`: ISO 8601
110	- `dateModified`: ISO 8601 (critical for freshness signals)
111	- `author`: Person or Organization schema
112	- `publisher`: Organization schema with logo
113	- `image`: Representative image
114
115	Author (Person) required for GEO:
116	- `name`: Full name
117	- `url`: Author page URL on the site
118	- `sameAs`: LinkedIn, Twitter, personal site, Google Scholar, ORCID
119	- `jobTitle`: Professional title
120	- `worksFor`: Organization schema
121	- `knowsAbout`: Array of expertise areas
122	- `alumniOf`: Educational institutions
123	- `award`: Professional awards
124
125	### Product (for e-commerce)
126	Required:
127	- `name`, `description`, `image`
128	- `offers`: Offer with price, priceCurrency, availability
129	- `brand`: Brand schema
130	- `sku` or `gtin`/`mpn`
131
132	Recommended for GEO:
133	- `aggregateRating`: AggregateRating
134	- `review`: Array of individual reviews
135	- `category`: Product category
136	- `material`, `weight`, `width`, `height` (where applicable)
137
138	### FAQPage
139	Status as of 2024: Google restricts FAQ rich results to government and health sites. However, the FAQPage schema still serves GEO purposes — AI platforms parse FAQ structured data for question-answer extraction. Implement it for AI readability even though rich results may not appear.
140
141	Structure:
142	- `@type`: "FAQPage"
143	- `mainEntity`: Array of Question schemas, each with `acceptedAnswer` containing an Answer schema
144
145	### SoftwareApplication (for SaaS)
146	Required:
147	- `name`, `description`
148	- `applicationCategory`: e.g., "BusinessApplication"
149	- `operatingSystem`: Supported platforms
150	- `offers`: Pricing
151
152	Recommended for GEO:
153	- `aggregateRating`: User ratings
154	- `featureList`: Array of features (strong citation signal)
155	- `screenshot`: Screenshots
156	- `softwareVersion`: Current version
157	- `releaseNotes`: Link to changelog
158
159	### WebSite + SearchAction (for sitelinks search box)
160	Structure:
161	```json
162	{
163	"@type": "WebSite",
164	"name": "Site Name",
165	"url": "https://example.com",
166	"potentialAction": {
167	"@type": "SearchAction",
168	"target": {
169	"@type": "EntryPoint",
170	"urlTemplate": "https://example.com/search?q={search_term_string}"
171	},
172	"query-input": "required name=search_term_string"
173	}
174	}
175	```
176
177	### Person (standalone — for personal brands, authors, thought leaders)
178	Use as a standalone schema on About/Bio pages. This builds the entity graph for individual expertise.
179
180	Required: `name`, `url`
181	Recommended for GEO: `sameAs`, `jobTitle`, `worksFor`, `knowsAbout`, `alumniOf`, `award`, `description`, `image`
182
183	### speakable Property (for voice/AI assistants)
184	The `speakable` property marks specific sections of content as particularly suitable for voice and AI assistant consumption. Add to Article or WebPage schemas.
185
186	```json
187	{
188	"@type": "Article",
189	"speakable": {
190	"@type": "SpeakableSpecification",
191	"cssSelector": [".article-summary", ".key-takeaway"]
192	}
193	}
194	```
195	This signals to AI assistants which passages are the best candidates for citation or reading aloud.
196
197	---
198
199	## Step 4: Deprecated/Changed Schemas to Flag
200
201	\| Schema \| Status \| Note \|
202	\|---\|---\|---\|
203	\| HowTo \| Rich results deprecated Aug 2023 \| Still useful for AI parsing, but do not promise rich results \|
204	\| FAQPage \| Restricted to govt/health Aug 2023 \| Still useful for AI parsing (see above) \|
205	\| SpecialAnnouncement \| Deprecated 2023 \| Was for COVID; remove if still present \|
206	\| CourseInfo \| Replaced by Course updates 2024 \| Use updated Course schema properties \|
207	\| VideoObject `contentUrl` \| Changed behavior 2024 \| Must point to actual video file, not page URL \|
208	\| Review snippet \| Stricter enforcement 2024 \| Self-serving reviews on product pages may not display \|
209
210	Flag any deprecated schemas found and recommend replacements.
211
212	---
213
214	## Step 5: sameAs Strategy (CRITICAL for Entity Recognition)
215
216	The `sameAs` property is the single most important structured data property for GEO. It tells AI systems: "This entity on my website is the SAME entity as these profiles elsewhere." This creates the entity graph that AI platforms use to verify, trust, and cite sources.
217
218	### Recommended sameAs Links (in priority order)
219
220	1. Wikipedia article — highest authority entity link
221	2. Wikidata item — machine-readable entity identifier (e.g., `https://www.wikidata.org/wiki/Q12345`)
222	3. LinkedIn — company page or personal profile
223	4. YouTube — channel URL
224	5. Twitter/X — profile URL
225	6. Facebook — page URL
226	7. Crunchbase — company profile (for startups/tech)
227	8. GitHub — organization or personal profile (for tech)
228	9. Google Scholar — author profile (for researchers/academics)
229	10. ORCID — researcher identifier (for academics)
230	11. Instagram — profile URL
231	12. Apple App Store / Google Play — app listings (for software)
232	13. BBB — Better Business Bureau listing (for US businesses)
233	14. Industry directories — relevant vertical directories
234
235	### sameAs Audit Process
236	1. Collect all known web presences for the entity
237	2. Check that each URL resolves (not 404 or redirected)
238	3. Verify the Organization/Person schema includes ALL of them
239	4. Check that the information on each platform is consistent (name, description, founding date, etc.)
240	5. Flag any platforms where the entity should have a presence but does not
241
242	---
243
244	## Step 6: JSON-LD Generation
245
246	Based on the detected business type, generate ready-to-paste JSON-LD blocks. Always generate:
247
248	1. Organization or Person (depending on entity type) — always
249	2. WebSite with SearchAction — always for the homepage
250	3. Business-type-specific — Article for publishers, Product for e-commerce, LocalBusiness for local, SoftwareApplication for SaaS
251	4. BreadcrumbList — for any page deeper than homepage
252
253	### Generation Rules
254	- Use the `@graph` pattern to include multiple schemas in one JSON-LD block
255	- All URLs must be absolute (not relative)
256	- Include `@id` properties for cross-referencing between schemas
257	- Use ISO 8601 for all dates
258	- Include `speakable` on Article schemas with CSS selectors pointing to key content sections
259	- Place JSON-LD in `<head>` section — NOT injected via JavaScript
260
261	### Template: Organization with Full GEO Signals
262	```json
263	{
264	"@context": "https://schema.org",
265	"@type": "Organization",
266	"@id": "https://example.com/#organization",
267	"name": "Company Name",
268	"url": "https://example.com",
269	"logo": {
270	"@type": "ImageObject",
271	"url": "https://example.com/logo.png",
272	"width": 600,
273	"height": 60
274	},
275	"description": "Concise description of what the company does.",
276	"foundingDate": "2020-01-15",
277	"founder": {
278	"@type": "Person",
279	"name": "Founder Name",
280	"sameAs": "https://www.linkedin.com/in/founder"
281	},
282	"address": {
283	"@type": "PostalAddress",
284	"streetAddress": "123 Main St",
285	"addressLocality": "City",
286	"addressRegion": "State",
287	"postalCode": "12345",
288	"addressCountry": "US"
289	},
290	"contactPoint": {
291	"@type": "ContactPoint",
292	"telephone": "+1-555-555-5555",
293	"contactType": "customer service",
294	"email": "[email protected]"
295	},
296	"sameAs": [
297	"https://en.wikipedia.org/wiki/Company_Name",
298	"https://www.wikidata.org/wiki/Q12345",
299	"https://www.linkedin.com/company/company-name",
300	"https://www.youtube.com/@companyname",
301	"https://twitter.com/companyname",
302	"https://github.com/companyname",
303	"https://www.crunchbase.com/organization/company-name"
304	],
305	"knowsAbout": [
306	"Topic 1",
307	"Topic 2",
308	"Topic 3"
309	]
310	}
311	```
312
313	---
314
315	## Scoring Rubric (0-100)
316
317	\| Criterion \| Points \| How to Score \|
318	\|---\|---\|---\|
319	\| Organization/Person schema present and complete \| 15 \| 15 if full, 10 if basic, 0 if none \|
320	\| sameAs links (5+ platforms) \| 15 \| 3 per valid sameAs link, max 15 \|
321	\| Article schema with author details \| 10 \| 10 if full author schema, 5 if name only, 0 if none \|
322	\| Business-type-specific schema present \| 10 \| 10 if complete, 5 if partial, 0 if missing \|
323	\| WebSite + SearchAction \| 5 \| 5 if present, 0 if not \|
324	\| BreadcrumbList on inner pages \| 5 \| 5 if present, 0 if not \|
325	\| JSON-LD format (not Microdata/RDFa) \| 5 \| 5 if JSON-LD, 3 if mixed, 0 if only Microdata/RDFa \|
326	\| Server-rendered (not JS-injected) \| 10 \| 10 if in HTML source, 5 if JS but in head, 0 if dynamic JS \|
327	\| speakable property on articles \| 5 \| 5 if present, 0 if not \|
328	\| Valid JSON + valid Schema.org types \| 10 \| 10 if no errors, 5 if minor issues, 0 if major errors \|
329	\| knowsAbout property on Organization/Person \| 5 \| 5 if present with 3+ topics, 0 if missing \|
330	\| No deprecated schemas present \| 5 \| 5 if clean, 0 if deprecated schemas found \|
331
332	---
333
334	## Output Format
335
336	Generate GEO-SCHEMA-REPORT.md with:
337
338	```markdown
339	# GEO Schema & Structured Data Report — [Domain]
340	Date: [Date]
341
342	## Schema Score: XX/100
343
344	## Detected Schemas
345	\| Page \| Schema Type \| Format \| Status \| Issues \|
346	\|---\|---\|---\|---\|---\|
347	\| / \| Organization \| JSON-LD \| Valid \| Missing sameAs \|
348	\| /blog/post-1 \| Article \| JSON-LD \| Valid \| No author schema \|
349
350	## Validation Results
351	[List each schema with pass/fail per property]
352
353	## Missing Recommended Schemas
354	[List schemas that should be present based on business type but are not]
355
356	## sameAs Audit
357	\| Platform \| URL \| Status \|
358	\|---\|---\|---\|
359	\| Wikipedia \| [URL or "Not found"] \| Present/Missing \|
360	\| LinkedIn \| [URL or "Not found"] \| Present/Missing \|
361	[Continue for all recommended platforms]
362
363	## Generated JSON-LD Code
364	[Ready-to-paste JSON-LD blocks for each missing or incomplete schema]
365
366	## Implementation Notes
367	- Where to place each JSON-LD block
368	- Server-rendering requirements
369	- Testing with Google Rich Results Test and Schema.org Validator
370	```
371

Discussion

From GitHub

1 comment on 1 thread

ilyoungkim5mo agoWhen creating a report file, a feature is needed to apply the URL name

Full report saved to: GEO-SCHEMA-REPORT-ainspinejoint-s1020.md already solve it? Thx.

Alternatives

Also in AI search (AEO)

AI Search / GEO Optimization (May 2026)Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. Generative Engine Optimization (GEO) analysis including brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring, and platform-specific optimization. Use when user says "AI Overviews", "SGE", GEO", "AI search", "LLM optimization", "Perplexity", "AI citations", ChatGPT search", or "AI visibility".Marketing · MIT Agentic Search OptimizerExpert in WebMCP readiness and agentic task completion — audits whether AI agents can actually accomplish tasks on your site (book, buy, register, subscribe), implements WebMCP declarative and imperative patterns, and measures task completion rates across AI browsing agentsBusiness & ops · MIT AI SEOWhen the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimizatiData & AI · MIT GEO Audit Orchestration SkillFull website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.Marketing · MIT

GEO Schema & Structured Data

How to use it

GEO Schema & Structured Data

Purpose

How to Use This Skill

Step 1: Detection

Scan for JSON-LD

Scan for Microdata

Scan for RDFa

Priority Order

Step 2: Validation

Step 3: Schema Types for GEO

Organization (CRITICAL — every business site)

LocalBusiness (for businesses with physical locations)

Article + Author (CRITICAL for publishers)

Product (for e-commerce)

FAQPage

SoftwareApplication (for SaaS)

WebSite + SearchAction (for sitelinks search box)

Person (standalone — for personal brands, authors, thought leaders)

speakable Property (for voice/AI assistants)

Step 4: Deprecated/Changed Schemas to Flag

Step 5: sameAs Strategy (CRITICAL for Entity Recognition)

Recommended sameAs Links (in priority order)

sameAs Audit Process

Step 6: JSON-LD Generation

Generation Rules

Template: Organization with Full GEO Signals

Scoring Rubric (0-100)

Output Format

Discussion

From GitHub

Alternatives