glossary-definition-hub
Skill0 starsChanged 2 months agoMITView on GitHub
Build a glossary, definition hub or "what is X" page set that owns the vocabulary of a topic and gets quoted by AI assistants. Use whenever the user mentions a glossary, definitions, "what is" pages, terminology pages, a knowledge base of terms, a wiki, or wants to rank for definitional queries. Also use when a product category has jargon customers don't understand, or when the site needs foundational pages for a topic cluster to link to.
In this repository29 other files it gives its agents.
- ai-bot-log-analysisSkill
- ai-crawler-policySkill
- ai-visibility-auditSkill
- best-of-listicle-pagesSkill
- canonical-duplicate-contentSkill
- comparison-alternatives-pagesSkill
- content-refreshSkill
- core-web-vitalsSkill
- ecommerce-seoSkill
- eeat-author-pagesSkill
- entity-brand-consistencySkill
- featured-snippet-passagesSkill
- hreflang-international-seoSkill
- image-seoSkill
- internal-linking-architectureSkill
- keyword-cannibalizationSkill
- keyword-research-briefsSkill
- link-building-outreachSkill
- local-seoSkill
- nextjs-seoSkill
- programmatic-seoSkill
- redirect-migration-planSkill
- schema-markupSkill
- search-console-analysisSkill
- shopify-seoSkill
- technical-seo-auditSkill
- topical-authority-mapSkill
- video-seoSkill
- wordpress-seoSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Don't build it when the terms are generic and already definitively covered elsewhere.
- Distinctive: line 34
All terms listed, grouped by theme rather than alphabetically.
- Distinctive: line 73
Definition first, immediately under the H1: No throat-clearing, no "in today's landscape".
- Distinctive: line 90
The code, config or record: if the term is technical
- Distinctive: line 98
If a term can only support 200 good words, give it 200 good words.
- Distinctive: line 134
Don't leave entries orphaned: Every entry needs inbound links from the hub, from siblings, and ideally from real content that uses the term.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Glossary and Definition Hubs
Definitional queries are the cheapest search traffic in most categories and the most reliably quoted by AI assistants, because a definition is exactly the shape of content an extraction system is looking for: short, self-contained, factual, unambiguous.
They're also strategically useful beyond their own traffic. A glossary gives every other page on the site something authoritative to link to with clean anchor text, which is how a topic cluster actually gets bound together.
The failure mode is obvious and common: 200 auto-generated definition pages of 80 words each, which is thin content at scale and gets treated as such.
When a glossary is worth building
Build it when at least two are true:
- The category has genuine jargon customers must understand to buy.
- The site already has a topical map these terms support. A glossary floating in isolation is decoration.
- You can write each entry with real authority, including the parts other definitions get wrong.
- There are 15 to 60 terms that matter. Fewer isn't a hub. More is usually padding.
Don't build it when the terms are generic and already definitively covered elsewhere. A SaaS company doesn't need a definition page for "API" and won't rank for it.
Structure
/glossary/ ← the hub, browsable and useful in itself
/glossary/term-name ← one page per termThe hub page is a real page, not a link dump:
- All terms listed, grouped by theme rather than alphabetically. Alphabetical is a fallback for when you have no idea how the concepts relate.
- A one-line definition next to each, so the hub answers questions on its own.
- A short intro explaining how the concepts fit together.
- Links from the hub down to every term, and from every term back up.
The entry template
H1 What is [Term]?
[Definition, 40-60 words. Complete, standalone, no
dependency on anything above it. Names the term itself
rather than starting with "It is".]
H2 How [Term] works
[Mechanism, concretely. Diagram if it helps.]
H2 Example
[A real one, with real values. This is the part most
glossaries skip and the part that makes it useful.]
H2 Why [Term] matters
[The practical consequence. What breaks without it.]
H2 [Term] vs [commonly confused term]
[Short table. This section brings in more traffic than
the definition itself, surprisingly often.]
H2 Common misconceptions
[What people get wrong. Where the expertise shows.]
H2 Related terms
[3-6 internal links to sibling entries]
[Link up to the pillar page for this topic]The rules that make entries rank and get quoted
- Definition first, immediately under the H1. No throat-clearing, no "in today's landscape".
- 40 to 60 words. Under 40 gets padded by extraction systems; over 60 gets truncated mid-sentence.
- Name the term in the first sentence. "SPF is a DNS record that..." not "It's a way of...". Extracted passages lose their heading.
- No context dependency. The paragraph must work pasted somewhere else with nothing around it.
- One term per page. Pages defining three related terms get extracted for none of them.
- Include the acronym expansion and both forms of the term where they exist.
- Add the comparison section. "X vs Y" for the term people confuse it with is often higher-volume than the definition itself.
- Server-render it. Content injected after hydration is invisible to most retrieval agents. See
featured-snippet-passages.
Making entries substantial without padding
The tension: definitional pages need to be genuinely useful, and padding a definition to 1,200 words makes it worse.
What adds real substance:
- A worked example with actual values, not a hypothetical
- A diagram of the mechanism
- The code, config or record if the term is technical
- The history, briefly, where it explains why something is the way it is
- What people get wrong, which is the clearest demonstration of expertise
- When it doesn't apply, or when the standard advice is wrong
- A short FAQ of the questions that genuinely follow
What doesn't: restating the definition three ways, listing synonyms, a paragraph on "why understanding [term] is important in today's fast-moving landscape", or an AI-generated expansion of the same 60 words.
If a term can only support 200 good words, give it 200 good words. Or fold it into a related entry as a section.
Why these get cited by AI assistants
Definitional content is disproportionately represented in AI answers because it's what the question shape asks for. What makes yours the one quoted rather than someone else's:
- Precision. Vague definitions get passed over for exact ones.
- The example. A definition with a concrete example is more useful and more quotable than one without.
- The disambiguation section. "X vs Y" content directly answers the follow-up a model anticipates.
- Consistency with other sources. A definition that agrees with the field's consensus and then adds something is stronger than one that contradicts it.
- Being correct about the edges. Where general sources are sloppy, being precise is what makes you the citation.
Structured data
DefinedTerm within a DefinedTermSet is the accurate markup for a glossary and it costs nothing to add. It doesn't produce a rich result, so don't oversell it — the value is unambiguous machine-readable structure.
{
"@context": "https://schema.org",
"@type": "DefinedTerm",
"@id": "https://example.com/glossary/spf#term",
"name": "SPF",
"description": "A DNS record listing which mail servers may send email for a domain.",
"inDefinedTermSet": {
"@type": "DefinedTermSet",
"@id": "https://example.com/glossary#set",
"name": "Email deliverability glossary"
}
}Don't do these
- Don't generate the glossary. A hundred LLM-written definitions is scaled content abuse with a nicer name, and it produces definitions that are subtly wrong in ways only an expert notices.
- Don't build 300 entries. Cover the terms that matter to your customers, thoroughly.
- Don't define terms you have no authority on. You won't rank and it dilutes what the site is about.
- Don't leave entries orphaned. Every entry needs inbound links from the hub, from siblings, and ideally from real content that uses the term.
- Don't publish and forget. Terminology shifts, standards get replaced, and a confidently wrong definition is a durable embarrassment.
- Don't make definition pages the whole strategy. They're low commercial intent. They support the cluster; they don't carry it. See
topical-authority-map.
Related skills
featured-snippet-passages, topical-authority-map, internal-linking-architecture, schema-markup, ai-visibility-audit
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
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.

