domain-modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
- License 许可
- MIT
- 最近更新
- 2026-10-14
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- domain-modeling
- description
- Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
02 资源文件 3
- 参考文档ADR-FORMAT.md2.7 KB
- 参考文档agents/openai.yaml101 B
- 参考文档CONTEXT-FORMAT.md2.3 KB
03 SKILL.md 正文
Domain Modeling
Converse sempre em português nesta sessão. Isso vale só para a interação com o usuário: não mexa no idioma de CONTEXT.md, ADRs ou qualquer arquivo já existente no repo, esses são compartilhados e ficam como estão, mesmo se já estiverem em inglês. Ao criar um arquivo novo, pode escrever em inglês, seguindo o padrão que já existe no projeto.
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 CONTEXT.md 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
Most repos have a single context:
/
├── CONTEXT.md
├── docs/
│ └── adr/
│ ├── 0001-event-sourced-orders.md
│ └── 0002-postgres-for-write-model.md
└── src/
If a CONTEXT-MAP.md exists at the root, the repo has multiple contexts. The map points to where each one lives:
/
├── CONTEXT-MAP.md
├── docs/
│ └── adr/ ← system-wide decisions
├── src/
│ ├── ordering/
│ │ ├── CONTEXT.md
│ │ └── docs/adr/ ← context-specific decisions
│ └── billing/
│ ├── CONTEXT.md
│ └── docs/adr/
Create files lazily: only when you have something to write. If no CONTEXT.md exists, create one when the first term is resolved. If no docs/adr/ exists, create it when the first ADR is needed.
During the session
Challenge against the glossary
When the user uses a term that conflicts with the existing language in CONTEXT.md, 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 CONTEXT.md inline
When a term is resolved, update CONTEXT.md right there. Don't batch these up: capture them as they happen. Use the format in CONTEXT-FORMAT.md.
CONTEXT.md should be totally devoid of implementation details. Do not treat CONTEXT.md 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.
How to ask
Every question this skill puts to the user (a term conflict, a fuzzy term, a scenario, a code contradiction, which context a topic belongs to, whether to write an ADR) goes through the structured question tool (AskUserQuestion in Claude Code), never as chat text. Follow the rules in the grilling skill's "How to ask" section: one question per call, 2-4 options with trade-offs in the descriptions, recommended option first with (Recomendado), multiSelect: true when choices are not exclusive.
Examples:
- Term conflict: options are the glossary meaning, the meaning the user seems to use, and "são dois termos diferentes".
- Fuzzy term: options are the candidate canonical terms.
- ADR offer: "Criar ADR" (with the proposed title in the description) and "Pular".
04 同仓库更多 Skills
revisar-branch
Revisão profunda da branch atual (ou do PR aberto dela) contra a branch-pai real — develop/main ou outra branch de issue da qual ela foi criada, revisando só os commits próprios —, usando a issue do Jira do nome da branch como contexto de escopo. Dispara múltiplos agentes em paralelo — bugs, exceções, edge-cases, duplicidade, segurança, performance, manutenibilidade —, verifica red/green de cada teste novo ou alterado, valida criticamente cada achado e propõe um fix por achado. Use quando pedirem "revise essa branch", "revise meu PR", "review antes de abrir PR", ou antes de /finish-issue.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
grill-with-docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
grill-me
A relentless interview to sharpen a plan or design.
atualizar-prs
Atualiza em cadeia uma pilha de PRs empilhados (develop -> PR1 -> PR2 -> PR3), de qualquer branch da pilha. Começa pela branch mais próxima da develop e desce uma por vez, sem paralelismo. Em cada branch remove a migration EF própria, mergeia a branch anterior, resolve conflitos, recria a migration preservando o custom code, compara antiga x nova, compila e testa. Só commita local, nunca dá push sem ordem explícita. Use quando pedirem "atualiza os PRs em cadeia", "atualiza a stack", "atualiza minhas branches com a develop" ou /atualizar-prs.