domain-modeling
Skill13 starsChanged 4 months agoMITView on GitHub
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
195 other projects use a version of this, 152 of them edited.
Adopted by
Most recently taken up by
- anorth/agent-skillsedited, first seen Nov 8, 2026
- chrysogonus/power-agentsedited, first seen Nov 8, 2026
- The-Vibe-Company/quivredited, first seen Nov 8, 2026
- AJschoons/robowrightedited, first seen Nov 8, 2026
- tornikegomareli/Skillsedited, first seen Nov 8, 2026
- miklschmidt/archboardedited, first seen Nov 8, 2026
Used with
Projects with it also use setup-ts-deep-modules, decision-mapping and 10 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.
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 43 projects that use this
FabienDehopreSkilldecision-mapping
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Also in 8 projects that use this
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 62 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 56 projects that use this
AWSSkillwizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
Also in 134 projects that use this
LesaniSkillwriting-shape
Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.
Also in 60 projects that use this
- +1 more from Lesani
Other versions195 projects use a version of this.
Word for word · 0
None found.
Edited · 152
- mattpocock/skills★ 309k71% same
- QuivrHQ/quivr★ 40k72% same
- The-Vibe-Company/quivr★ 40k72% same
- windmill-labs/windmill★ 18k72% same
- GreyDGL/PentestGPT★ 16k76% same
- formbricks/formbricks★ 13k71% same
- ArcReel/ArcReel★ 6.3k71% same
- vinvcn/mattpocock-skills-zh-CN★ 5.5k21% same
- withcoral/coral★ 4.9k71% same
- bestofjs/bestofjs★ 3.1k76% same
142 more not listed
Wrote their own version · 43
- rohitg00/pro-workflow★ 2.9ksame name
- stevesolun/ctx★ 583same name
- devcxl/mattpocock-skills-zh★ 522same name
- Mathews-Tom/armory★ 340same name
- proflead/codex-skills-library★ 153same name
- etr/groundwork★ 45same name
- nimadorostkar/Claude-Skills-collection★ 33same name
- WenWuZhiDao/mattpocock-skills-zh★ 27same name
- oribarilan/97★ 25same name
- helderberto/agent-skills★ 19same name
33 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 repository21 other files it gives its agents.
- codebase-designSkill
- debugSkill
- grillingSkill
- grill-plainSkill
- grillSkill
- handoffSkill
- implementSkill
- improve-archSkill
- prototypeSkill
- reconcileSkill
- researchSkill
- setup-okf-matt-skillsSkill
- tddSkill
- teachSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- vetSkill
- wayfinderSkill
- which-skillSkill
- write-skillSkill
The file
We split this skill into the rules it gives an agent
11 rules. 6 are common, 3 are distinctive, and 2 are very specific to this project.
6
Common
Most of the 183 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 30
Create files lazily — only when you have something to write.
- Distinctive: line 36
Don't spin one up silently.
- Distinctive: line 39
Get the user's sanction: before creating the directory.
- Distinctive: line 42
Default to the existing three.
- Common: line 48
When the user uses a term that conflicts with the existing language in the glossary, call it out immediately.
- Common: line 52
When the user uses vague or overloaded terms, propose a precise canonical term.
- Common: line 56
When domain relationships are being discussed, stress-test them with specific scenarios.
- Common: line 60
When the user states how something works, check whether the code agrees.
- Very specific: line 64
When a term is resolved, write it to knowledge/glossary/ right there.
- Common: line 70
Only offer to create an ADR when all three are true:
- Common: line 76
If any of the three is missing, skip the ADR.
“Common” is measured: kept by at least 6 in 10 of the 183 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
Domain Modeling
Actively build and sharpen the project's domain model as you design. This is the active discipline — challenging terms, inventing edge-case scenarios, and writing the glossary and decisions down the moment they crystallise. (Merely reading the knowledge bundle's glossary for vocabulary is not this skill — that's a one-line habit any skill can do. This skill is for when you're changing the model, not just consuming it.)
File structure
The domain model lives in an Open Knowledge Format (OKF) knowledge bundle at knowledge/ in the repo root. Most repos have a single context:
knowledge/
├── index.md ← bundle map (reserved: no frontmatter)
├── log.md ← change history, newest first (reserved: no frontmatter)
├── glossary/ ← one file per term (the glossary)
│ ├── index.md
│ ├── order.md
│ └── customer.md
└── adr/ ← one file per decision
├── index.md
├── adr-0001-event-sourced-orders.md
└── adr-0002-postgres-for-write-model.mdFor multiple bounded contexts, each context is a subdirectory inside the one bundle (knowledge/ordering/glossary/, knowledge/billing/glossary/, …) and knowledge/index.md is the context map. See CONTEXT-FORMAT.md.
Create files lazily — only when you have something to write. If no knowledge/glossary/ exists, create it when the first term is resolved. If no knowledge/adr/ exists, create it when the first ADR is needed. Whenever knowledge changes, update the concept AND append to knowledge/log.md.
Extending the bundle (new concept categories)
glossary/ and adr/ are the two categories every bundle has; spec/ (written by /to-spec) is the third canonical one. But OKF is an open format — type is a free field and the bundle is not limited to a fixed set of folders. When you meet a durable domain entity that genuinely fits none of them — a recurring kind of thing the project needs recorded in its own right — a new concept category is legitimate.
Don't spin one up silently. When you judge a new category is warranted:
- Propose it — name the category, say what kind of entity it holds and why glossary/adr/prd don't fit.
- Get the user's sanction before creating the directory.
- Register it in
knowledge/index.md(and give it anindex.mdlike every other category) so the bundle map stays honest.
Default to the existing three. A new category is the exception, not the reflex.
During the session
Challenge against the glossary
When the user uses a term that conflicts with the existing language in the glossary, call it out immediately. "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?"
Sharpen fuzzy language
When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account' — do you mean the Customer or the User? Those are different things."
Discuss concrete scenarios
When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.
Cross-reference with code
When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?"
Update the glossary inline
When a term is resolved, write it to knowledge/glossary/ right there. Don't batch these up — capture them as they happen. Use the format in CONTEXT-FORMAT.md.
The glossary should be totally devoid of implementation details. Do not treat it as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else.
Offer ADRs sparingly
Only offer to create an ADR when all three are true:
- Hard to reverse — the cost of changing your mind later is meaningful
- Surprising without context — a future reader will wonder "why did they do it this way?"
- The result of a real trade-off — there were genuine alternatives and you picked one for specific reasons
If any of the three is missing, skip the ADR. Use the format in ADR-FORMAT.md.
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.

