glossary
Skill0 starsChanged 6 days agoMITView on GitHub
Create and maintain a project's glossary, the agreed names and short definitions of the concepts used to discuss the product. Use when a project concept is introduced, named, or renamed, when the user finds a project term unclear, or when terms in discussion conflict with the glossary or the code.
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
- TakaGoto/rag-learning-academytheir own version, first seen Oct 28, 2026
- genkovich/sddtheir own version, first seen Oct 25, 2026
Used with
Projects with it also use test-driven-development and review.
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.
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★ 2.9ksame name
- lightly-ai/lightly-studio★ 901same 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 repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- clarifySkill
- collectSkill
- handoffSkill
- interrogateSkill
- pendingSkill
- progressSkill
- recapSkill
- restateSkill
- spawnSkill
- warmupSkill
- yieldSkill
- tidy-docsSkill
- writing-agentsSkill
- writing-skillsSkill
- writing-textSkill
- teachSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
5
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 6
Keep the project's glossary accurate, so that the user and agents call each concept by one name and can look up what it means.
- Very specific: line 14
Follow the project's convention.
- Distinctive: line 35
Avoid the reuse where both meanings meet, such as a log entry about loading data that has both a field for the part of the app that wrote …
- Distinctive: line 43
Read the glossary before naming a concept, and check a new name against the built-in names of the frameworks and languages it is used with.
- Distinctive: line 45
Update an entry as soon as its term is settled, renamed, or found unclear.
- Distinctive: line 47
When a term in the discussion conflicts with the glossary, point out the conflict and settle which meaning is intended.
“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
Keep the project's glossary accurate, so that the user and agents call each concept by one name and can look up what it means. Finish when every term settled, renamed, or found unclear in the current work has an up-to-date entry.
What belongs
A term is a concept needed to talk about the product's behavior or structure, such as a processing stage, an element the user sees, or a kind of record. Leave out general programming concepts, such as timeouts or error types, and code identifiers that do not name a concept people discuss, such as a builder class.
Where it lives
Follow the project's convention. Otherwise use docs/glossary.md, created when the first term is settled. When creating it, add a pointer to it in the project's AGENTS.md.
Entry format
# Glossary
{One sentence on what the project is.}
## Terms
**Invoice** (`Invoice`):
A request for payment sent to a customer after delivery.
_Avoid_: bill, payment request- Choose one term per concept, preferring the name the user finds clearest. List rejected synonyms under
_Avoid_. - No two concepts share a name. A term differs from the project's other terms, unless it reuses a general word as the next item allows. It differs from the built-in names of the frameworks and languages it is used with, without exception. When a new or existing term clashes, rename whichever of the two fits its concept worse.
- A general word used as a term, such as "source" for a data source, always means the term's concept when it stands alone. Another concept may still use the word where its context always marks it:
- Such contexts include a field inside one file format and a qualified name like "log source". If that concept has its own entry, its term is the qualified name.
- Record the other use in a sentence after the term's definition, so readers are not misled.
- Avoid the reuse where both meanings meet, such as a log entry about loading data that has both a field for the part of the app that wrote it and a field for the data source. If they come to meet later, rename the reuse.
- Define what the concept is in one or two sentences, using other glossary terms where they apply.
- Give the code name when one exists, so readers can find it. Leave out other implementation details.
- Group terms under subheadings when clusters form. A flat list is fine otherwise.
- Describe the current state. Change an entry for a rename in the same change that renames the concept, and move the old name under
_Avoid_.
Keep it current
Read the glossary before naming a concept, and check a new name against the built-in names of the frameworks and languages it is used with. Use the glossary's terms in code, documentation, and conversation.
Update an entry as soon as its term is settled, renamed, or found unclear. Do not batch updates until the end of the work.
When a term in the discussion conflicts with the glossary, point out the conflict and settle which meaning is intended. When the user states how a concept works, check that the code agrees and raise any contradiction.
A name that is clear to the agent can still be opaque to the user. When the user asks what a term means or says they keep forgetting it, sharpen the definition or agree on a clearer name with the user.
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.

