glossary
Skill1 starsChanged 6 months agoApache-2.0View on GitHub
Generate a glossary entry (single term) or glossary index (terms list) for a chosen managed site. Captures definition-stage search behavior ("what is [term]", "[term] meaning", "[term] definition") AND functions as an internal-link hub that distributes authority to commercial pages. Pulls definitions from site-specific authoritative sources, satisfies Tier 1 on-page SEO, validates DefinedTerm + DefinedTermSet schema, and ships per the site's publishing method. Use when the user types `/glossary` (one entry) or `/glossary --index` (full index) or asks for glossary content.
19 other projects use a version of this.
Adopted by
Most recently taken up by
- computerlovetech/skillstheir own version, first seen Nov 8, 2026
- harlan-zw/brundleflytheir own version, first seen Nov 8, 2026
- jeremy-farnault/claude-skillstheir own version, first seen Nov 3, 2026
- AcKeskin/contexturetheir own version, first seen Nov 1, 2026
- mrzli/skillstheir own version, first seen Nov 1, 2026
- TakaGoto/rag-learning-academytheir own version, first seen Oct 28, 2026
Used with
Projects with it also use readme, recap and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
kasperjungeSkillreadme
Generate beautiful, comprehensive README.md files for any codebase. Use when asked to create a README, improve documentation, or when the user says "readme", "/readme", or wants help documenting their project. Analyzes the codebase structure, dependencies, and code to produce professional documentation.
Also in 3 projects that use this
genomewalkerSkillrecap
Rebuild working context from transcripts and chitta memories in approximately 1500 tokens. Use when starting a new session to continue previous work.
Also in 3 projects that use this
OpenAISkilltest-driven-development
Use when implementing any feature or bugfix, before writing implementation code
Also in 3 projects that use this
SentrySkillreview
Fixture review skill.
Also in 4 projects that use this
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- chattocorp/chatto★ 3ksame name
- lightly-ai/lightly-studio★ 911same name
- genkovich/sdd★ 187same name
- intent-driven-dev/intent-driven-template★ 185same name
- aspi6246/Claude-Code-Skills-for-Academics★ 153same name
- tdimino/claude-code-minoan★ 41same name
- TakaGoto/rag-learning-academy★ 24same name
- Azure/azure-functions-agents-runtime★ 13same name
- intent-driven-dev/skills★ 9same name
- harlan-zw/brundlefly★ 7same name
9 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- alternativeSkill
- auditSkill
- blogSkill
- broken-backlinksSkill
- case-studySkill
- clusterSkill
- comparisonSkill
- competitor-backlinksSkill
- haroSkill
- integrationsSkill
- lovable-deploySkill
- pricingSkill
- programmatic-batchSkill
- refreshSkill
- semrush-baselineSkill
- serp-featuresSkill
- serviceSkill
- triageSkill
- wireframeSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
NO conversion CTA — glossary entries are pure informational, conversion happens via the "in context" links.
- Very specific: line 51
Term list: every entry with [Term] as a heading link to /glossary/{term-slug}, followed by the quick-definition sentence.
- Distinctive: line 70
Every definition that cites authority needs the citation (date accessed + URL or DOI for academic sources).
- Distinctive: line 71
No opinions in glossary entries — opinions go on blog posts, glossary is definitional.
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/glossary — Glossary entry / index generator
Glossaries do double duty: they capture definition-stage informational traffic AND function as the highest-density internal-linking hub on a site. A well-built glossary entry links to 5–10 commercial pages from a single page — distributing link equity downstream without any user-visible link spam. This skill builds both the individual entries and the index.
Inputs
Required (asked at start if not given):
- Site — must match a folder under
sites/[name]/. - Mode —
entry(single glossary term) |index(the full glossary index page). - Term (if mode=
entry) — the specific term being defined.
Optional (per-run overrides):
- Authoritative source — for terms that need definition citations, specify the source (default: skill picks from established industry sources via SERP analysis).
- Linked pages — if the term should link to specific internal pages, supply slugs; otherwise the skill picks based on topical relevance.
Workflow
This skill follows /blog's workflow (Steps 0–11) with the page-type-specific differences listed below. Read .claude/skills/blog/SKILL.md end-to-end before running.
What's unique to /glossary
Step 2 — Keyword selection:
- Mode=
entry: primary keyword forms —what is [term],[term] definition,[term] meaning,[term] explained. Pick fromkeywords.csvrows with intent=definitionorglossary. Volume is typically lower per term, but the cumulative compound (50+ entries × low-volume) drives 6-figure annual traffic for niche-authoritative glossaries. - Mode=
index: primary keyword is[topic] glossaryor[topic] terms— single keyword for the whole index.
Step 3 — Cluster (glossary-entry-specific):
- Cluster terms are: synonyms (
[term] vs synonym), related terms ([term] vs adjacent-term), and the broader category. Usually 3–5 cluster terms for a glossary entry — fewer than blog because the definition itself is the primary intent.
Step 4 — SERP analysis (glossary-specific):
- Top 3 glossary entries for this term — extract: word count (usually shorter than blogs, 300–800 words is typical), presence of "Related terms" section, presence of definition citations, presence of in-context examples.
- Wikipedia / academic sources often rank — those are difficult to outrank for general terms but easier for industry-specific terms.
Step 6 — Wireframe (glossary-entry-specific):
- Hero: "[Term]" as H1. No prefix, no marketing tagline — just the term.
- Quick definition (the first sentence after H1): "[Term] is [definition]." Direct. Self-contained (passes AI-search self-contained-facts test). One sentence, max 30 words. This is the snippet Google + LLMs cite.
- Extended definition (200–400 words): the longer explanation. Where the term came from, how it's used in this industry, what it's NOT (common misconceptions).
- Example section (80–200 words): one concrete in-context example. Stories.md material works well here if relevant.
- Related terms section (required, hub function): 5–10 internally-linked terms — to other glossary entries AND to commercial pages where the term appears. Format: bulleted list, each item is "[Linked term]" + 8–15 word descriptor.
- "In context" links (required): 3–5 anchor-text-rich links to commercial / service / blog pages on the site that USE this term. This is where the link-equity distribution happens.
- FAQ: 3–5 Qs — "Is [term] the same as [synonym]?", "When did [term] originate?", common misconceptions.
- NO conversion CTA — glossary entries are pure informational, conversion happens via the "in context" links.
Step 6b — Wireframe (glossary-index-specific):
- Hero: "[Topic] glossary" (H1). Subhead: 1–2 sentences explaining the glossary's scope and how it's maintained.
- A–Z filter / search (frontend component, called out in wireframe).
- Term list: every entry with
[Term]as a heading link to/glossary/{term-slug}, followed by the quick-definition sentence. Grouped alphabetically or by category — site-info determines. - Most-viewed terms section (5–10 entries, optional — populated from analytics).
- Schema: single
DefinedTermSetcontaining all entries.
Step 7 — Schema (glossary-entry-specific):
DefinedTermwithname,description(the quick definition),inDefinedTermSet(URL of the index)Article(the entry itself)BreadcrumbListFAQPageif FAQ section present- For multilingual sites, every entry has its own
DefinedTermper language, all part of the sameDefinedTermSet(withinLanguageper entry).
Step 7b — Schema (glossary-index-specific):
DefinedTermSetwithhasDefinedTerm: [ DefinedTerm × N ]— each pointing to aDefinedTermby URL.CollectionPagefor the index itself.BreadcrumbList.
Step 8 — Voice (glossary-specific extras):
- Definitions MUST be self-contained — each entry stands alone without requiring the reader to know the broader context. Critical for AI-search citation.
- Tone is encyclopedic, not promotional. The skill refuses if the draft slips into marketing voice.
- Every definition that cites authority needs the citation (date accessed + URL or DOI for academic sources).
- No opinions in glossary entries — opinions go on blog posts, glossary is definitional.
- AI-search rules: self-contained-facts rule applies aggressively. Q+A density via the FAQ; citation-friendly chunking via 1-sentence quick-definition + 3-sentence-max paragraphs in extended definition.
Refusal conditions
This skill refuses to ship if:
- Mode=
entryand the term is undefined in any authoritative source (skill refuses to invent definitions). - Term-slug collision with an existing glossary entry (suggest /refresh instead).
- Mode=
indexand fewer than 10 glossary entries exist (an index with <10 entries is thin content; build entries first).
Output
- Mode=
entry: standard_drafts/glossary/{term-slug}/layout (path-based to support the glossary directory pattern). - Mode=
index:_drafts/glossary/index/containing the index page draft + auto-generatedDefinedTermSetJSON-LD.
Length target: 300–800 words per entry; 600–1,200 words for the index.
Routine versioning + idempotency contract
Same as /blog. Idempotency key for entries: (site, term-slug, language). Index regeneration is idempotent per-day (re-running on the same day skips; running on a different day rebuilds with any new entries discovered).
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.

