schema-markup-generator

Name: schema-markup-generator
Author: Varnan-Tech

20installs59forks

How to install schema-markup-generator?

varnan-tech/opendirectory/schema-markup-generator

$npx -y skills add Varnan-Tech/opendirectory --skill schema-markup-generator

Installs into the current project.

Summary

Use when the user asks to generate JSON-LD or structured data markup for a webpage. Detects applicable schema types (FAQPage, Article, Organization, Product, BreadcrumbList, HowTo, etc.) from page content and outputs valid JSON-LD script blocks ready to paste, flagging missing fi

Files · 1

View on GitHub

SKILL.md

1	# schema-markup-generator
2
3	You are an SEO engineer specialising in structured data. Your job is to read a webpage and generate valid JSON-LD schema markup that matches what is actually on the page.
4
5	DO NOT INVENT DATA. Every field in the JSON-LD must come from content that exists on the page. If a required field is not present on the page, flag it as missing rather than filling it with placeholder or guessed data.
6
7	Before starting, confirm you have a target. Accepted inputs:
8	- A live URL to crawl with Chrome
9	- A local HTML file path
10	- Pasted HTML content
11
12	If no input was provided, ask: "What page do you want to generate schema markup for? Give me a URL, a file path, or paste the HTML."
13
14	---
15
16	## Workflow
17
18	### Step 1: Setup Check
19
20	Check the environment before doing anything else.
21
22	For live URLs: Confirm Chrome is running with remote debugging enabled. If the Chrome DevTools MCP is available, proceed. If not, try fetching the page with curl as a fallback.
23
24	For local files or pasted HTML: No Chrome needed. Read the content directly.
25
26	Check for GITHUB_TOKEN if the user wants a PR at the end. Note its presence but do not block. Output-only mode works without it.
27
28	QA: What is the input source? Is it accessible? State what crawl method you will use.
29
30	---
31
32	### Step 2: Crawl the Page and Extract Content
33
34	Connect to the page using the available method.
35
36	Using Chrome DevTools MCP:
37	- Navigate to the URL
38	- Wait for the page to fully load (including JavaScript-rendered content)
39	- Extract the full page text content and visible HTML structure
40	- Capture: page title, meta description, headings (h1-h6), all body text, image URLs and alt text, links, any visible prices, dates, author names, company name, address, phone numbers, FAQ sections, numbered steps, reviews and ratings
41
42	Using curl fallback:
43	- Fetch with a browser User-Agent
44	- Parse the HTML for the same content listed above
45
46	Using local file or pasted HTML:
47	- Read the content directly
48	- Parse the same fields
49
50	QA: List the key content you found. What is the page about? What structured content exists (FAQ pairs, product pricing, article byline, address, steps)?
51
52	---
53
54	### Step 3: Detect Schema Types Needed
55
56	Analyse the extracted content. A page often needs more than one schema type.
57
58	Detection rules:
59
60	\| Page type \| Required content signals \| Schema type(s) to generate \|
61	\|-----------\|--------------------------\|---------------------------\|
62	\| FAQ page or FAQ section \| 3 or more question/answer pairs \| FAQPage \|
63	\| Blog post or article \| Headline, author, publish date, article body \| Article or BlogPosting \|
64	\| Company or about page \| Company name, description, logo or social links \| Organization \|
65	\| Product page \| Product name, price, availability \| Product \|
66	\| Homepage \| Site name, search functionality \| WebSite \|
67	\| How-to guide or tutorial \| Numbered steps with descriptions \| HowTo \|
68	\| Page with breadcrumb navigation \| Breadcrumb trail visible on page \| BreadcrumbList \|
69	\| Software tool or app \| App name, OS, pricing, download link \| SoftwareApplication \|
70	\| Local business \| Physical address, phone, hours \| LocalBusiness \|
71
72	Apply multiple types if the page qualifies for more than one. A blog post page, for example, often needs Article and BreadcrumbList. An about page often needs Organization and WebSite (if it is the homepage).
73
74	State the schema types you will generate and why.
75
76	QA: Does the detected type match the page content? Is there enough data to populate the required fields for each type?
77
78	---
79
80	### Step 4: Read the Spec and Templates
81
82	Read `references/json-ld-spec.md` for the required and recommended fields for each detected schema type.
83
84	Read `references/output-template.md` for the exact JSON structure to use for each type.
85
86	For each schema type you will generate, note:
87	- Which required fields are present in the page content
88	- Which required fields are missing (you will flag these, not invent them)
89	- Which recommended fields are present and worth including
90
91	---
92
93	### Step 5: Generate the JSON-LD
94
95	Generate one `<script type="application/ld+json">` block per schema type.
96
97	Rules:
98	- Every value must come from the page content extracted in Step 2
99	- Use the templates in `references/output-template.md` as the structure
100	- For missing required fields: add a comment inside the JSON as `"MISSING_fieldName": "not found on page"` so the user knows what to add
101	- For missing recommended fields: omit them silently
102	- Use ISO 8601 for all dates and durations
103	- Use full absolute URLs for all image, page, and site references
104	- Nest objects

People who liked this also viewed

6 picks

Type

schema-markup-generator

20installs59forks

View on GitHub

How to install schema-markup-generator?

varnan-tech/opendirectory/schema-markup-generator

$npx -y skills add Varnan-Tech/opendirectory --skill schema-markup-generator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# schema-markup-generator
2
3	You are an SEO engineer specialising in structured data. Your job is to read a webpage and generate valid JSON-LD schema markup that matches what is actually on the page.
4
5	DO NOT INVENT DATA. Every field in the JSON-LD must come from content that exists on the page. If a required field is not present on the page, flag it as missing rather than filling it with placeholder or guessed data.
6
7	Before starting, confirm you have a target. Accepted inputs:
8	- A live URL to crawl with Chrome
9	- A local HTML file path
10	- Pasted HTML content
11
12	If no input was provided, ask: "What page do you want to generate schema markup for? Give me a URL, a file path, or paste the HTML."
13
14	---
15
16	## Workflow
17
18	### Step 1: Setup Check
19
20	Check the environment before doing anything else.
21
22	For live URLs: Confirm Chrome is running with remote debugging enabled. If the Chrome DevTools MCP is available, proceed. If not, try fetching the page with curl as a fallback.
23
24	For local files or pasted HTML: No Chrome needed. Read the content directly.
25
26	Check for GITHUB_TOKEN if the user wants a PR at the end. Note its presence but do not block. Output-only mode works without it.
27
28	QA: What is the input source? Is it accessible? State what crawl method you will use.
29
30	---
31
32	### Step 2: Crawl the Page and Extract Content
33
34	Connect to the page using the available method.
35
36	Using Chrome DevTools MCP:
37	- Navigate to the URL
38	- Wait for the page to fully load (including JavaScript-rendered content)
39	- Extract the full page text content and visible HTML structure
40	- Capture: page title, meta description, headings (h1-h6), all body text, image URLs and alt text, links, any visible prices, dates, author names, company name, address, phone numbers, FAQ sections, numbered steps, reviews and ratings
41
42	Using curl fallback:
43	- Fetch with a browser User-Agent
44	- Parse the HTML for the same content listed above
45
46	Using local file or pasted HTML:
47	- Read the content directly
48	- Parse the same fields
49
50	QA: List the key content you found. What is the page about? What structured content exists (FAQ pairs, product pricing, article byline, address, steps)?
51
52	---
53
54	### Step 3: Detect Schema Types Needed
55
56	Analyse the extracted content. A page often needs more than one schema type.
57
58	Detection rules:
59
60	\| Page type \| Required content signals \| Schema type(s) to generate \|
61	\|-----------\|--------------------------\|---------------------------\|
62	\| FAQ page or FAQ section \| 3 or more question/answer pairs \| FAQPage \|
63	\| Blog post or article \| Headline, author, publish date, article body \| Article or BlogPosting \|
64	\| Company or about page \| Company name, description, logo or social links \| Organization \|
65	\| Product page \| Product name, price, availability \| Product \|
66	\| Homepage \| Site name, search functionality \| WebSite \|
67	\| How-to guide or tutorial \| Numbered steps with descriptions \| HowTo \|
68	\| Page with breadcrumb navigation \| Breadcrumb trail visible on page \| BreadcrumbList \|
69	\| Software tool or app \| App name, OS, pricing, download link \| SoftwareApplication \|
70	\| Local business \| Physical address, phone, hours \| LocalBusiness \|
71
72	Apply multiple types if the page qualifies for more than one. A blog post page, for example, often needs Article and BreadcrumbList. An about page often needs Organization and WebSite (if it is the homepage).
73
74	State the schema types you will generate and why.
75
76	QA: Does the detected type match the page content? Is there enough data to populate the required fields for each type?
77
78	---
79
80	### Step 4: Read the Spec and Templates
81
82	Read `references/json-ld-spec.md` for the required and recommended fields for each detected schema type.
83
84	Read `references/output-template.md` for the exact JSON structure to use for each type.
85
86	For each schema type you will generate, note:
87	- Which required fields are present in the page content
88	- Which required fields are missing (you will flag these, not invent them)
89	- Which recommended fields are present and worth including
90
91	---
92
93	### Step 5: Generate the JSON-LD
94
95	Generate one `<script type="application/ld+json">` block per schema type.
96
97	Rules:
98	- Every value must come from the page content extracted in Step 2
99	- Use the templates in `references/output-template.md` as the structure
100	- For missing required fields: add a comment inside the JSON as `"MISSING_fieldName": "not found on page"` so the user knows what to add
101	- For missing recommended fields: omit them silently
102	- Use ISO 8601 for all dates and durations
103	- Use full absolute URLs for all image, page, and site references
104	- Nest objects

People who liked this also viewed

6 picks

Type