domain-modeling
Skill2 starsChanged 2 months agoMITView on GitHub
Keeps a project's vocabulary and decision records honest by challenging overloaded terms against the code and recording canonical terms and hard-to-reverse decisions where the repo already keeps them. Use when a term, status, or field means two things, when naming a new concept or state, or when editing a glossary, GLOSSARY.md, or ADR. Do NOT use to interview the user about a plan (use grill-me) or to write a design doc.
195 other projects use a version of this.
Adopted by
Most recently taken up by
- bmcszk/agent-skillstheir own version, first seen Nov 16, 2026
- tunnckoCore/skillstheir own version, first seen Nov 16, 2026
- devdeepjs/kobayashi-marutheir own version, first seen Nov 16, 2026
- qelphybox/tg-mcptheir own version, first seen Nov 16, 2026
- lhotwll217/owner-operatortheir own version, first seen Nov 16, 2026
- bepaldes/heimdall-agenttheir own version, first seen Nov 16, 2026
Used with
Projects with it also use setup-ts-deep-modules, decision-mapping and 9 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 · 0
None found.
Wrote their own version · 195
- mattpocock/skills★ 325ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- windmill-labs/windmill★ 19ksame name
- GreyDGL/PentestGPT★ 16ksame name
- formbricks/formbricks★ 13ksame name
- ArcReel/ArcReel★ 6.6ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- withcoral/coral★ 4.9ksame name
- bestofjs/bestofjs★ 3.1ksame name
185 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 repository32 other files it gives its agents.
- agent-guardrailsSkill
- benchmark-checklistSkill
- blast-radiusSkill
- blog-reviewSkill
- code-reviewSkill
- create-formal-verification-skillSkill
- create-verification-skillSkill
- datavizSkill
- grill-meSkill
- grok-repoSkill
- hammerspoonSkill
- html-lessonSkill
- karpathy-planningSkill
- maintain-formal-verification-skillSkill
- mechanism-vizSkill
- obsidian-captureSkill
- obsidian-searchSkill
- paper-searchSkill
- readbackSkill
- repo-evalSkill
- route-skillSkill
- sherlockSkill
- show-meSkill
- sketch-conceptSkill
- skill-curatorSkill
- statechartSkill
- state-prototypeSkill
- test-writingSkill
- tla-modelSkill
- wait-whatSkill
- write-docsSkill
- write-skillSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 185 edited versions we read keep these.
6
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
- Distinctive: line 12
Read the repo's agent guide (AGENTS.md, CLAUDE.md) for where docs live.
- Distinctive: line 13
Search for an existing glossary and decision record:
- Very specific: line 19
Use the home you found, in its format.
- Distinctive: line 25
Probe each suspect term: ask what it means to each reader (the code that writes it, each code path that reads it, the user).
- Very specific: line 26
Check the code: when someone states how a term behaves, find the path:line that agrees or contradicts, and surface a contradiction at once.
- Distinctive: line 28
Ask naming choices as decisions: When the canonical name is the user's call, ask it in a grill-me round.
- Distinctive: line 29
Record each term when it resolves: Do not batch them.
- Distinctive: line 36
Decisions: only when hard to reverse, surprising without context, and a real tradeoff.
“Common” is measured: kept by at least 6 in 10 of the 185 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
Give each term one meaning, check that meaning against the code, and record it in the repo's existing home.
1. Find the home (REQUIRED)
- Read the repo's agent guide (
AGENTS.md,CLAUDE.md) for where docs live. - Search for an existing glossary and decision record:
Numbered decisions in design docs (rg -n -i '^#+ .*(glossary|vocabulary|terminology)' -g '*.md' fd -H 'GLOSSARY(-MAP)?\.md|^adr$'D1.,**D3.**) are a decision record too. - Use the home you found, in its format. Create
GLOSSARY.mdordocs/adr/only when none exists: lazily, in the docs location the guide names.
Done when you can name the one place each new term and decision goes.
2. Sharpen the language
- Probe each suspect term: ask what it means to each reader (the code that writes it, each code path that reads it, the user). Two answers mean two concepts: propose a name for each.
- Check the code: when someone states how a term behaves, find the
path:linethat agrees or contradicts, and surface a contradiction at once. - Test the boundary with one concrete scenario: "a
failedrow that later becomesdeleted: isfailedterminal?" - Ask naming choices as decisions. When the canonical name is the user's call, ask it in a grill-me round.
- Record each term when it resolves. Do not batch them.
Done when every term the current decision uses has one recorded meaning, with its aliases under _Avoid_.
3. Record
- Terms: GLOSSARY-FORMAT.md for a new glossary. An existing glossary keeps its format.
- Decisions: only when hard to reverse, surprising without context, and a real tradeoff. Use ADR-FORMAT.md, or the repo's own decision format.
- A status value is a term: define the one fact it records. If two writers set it for different reasons, it names two concepts.
Notes
- A glossary holds terms, not specs, status, or plans.
- Ported from mattpocock/skills (MIT), adapted to this repo's conventions and voice.
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.

