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 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.)
Mode detection
Before any file-structure guidance, check whether OpenSpec is present in the target repo:
openspec/config.yamlexists, oropenspec/specs/exists with at least one capability spec
If either is true, follow OpenSpec mode below. Otherwise follow Legacy mode.
When OpenSpec is absent and the user needs to initialize it, suggest the openspec-init skill.
OpenSpec mode
See OPENSPEC-MODE.md for detection, flat capability naming, ubiquitous language, spec/ADR routing, and cross-linking.
Do not use CONTEXT.md or CONTEXT-MAP.md in OpenSpec mode.
Specs and ADRs coexist: capability specs encode what; ADRs in docs/adr/ encode why. ferspec and similar schemas delegate ADR creation here.
File structure
/
├── docs/
│ └── adr/ ← rationale (why)
└── openspec/
├── config.yaml
├── specs/
│ ├── ubiquitous-language/spec.md ← replaces CONTEXT.md
│ ├── module-ordering/spec.md ← flat; category in slug
│ └── service-auth/spec.md
└── changes/<change-name>/specs/ ← pending spec deltas
Category is a kebab-case prefix on the capability slug (<category>-<name>). No nested folders like specs/modules/<name>/spec.md.
Create capability folders and docs/adr/ lazily — only when you have something to write.
During the session
Challenge against the glossary
When the user uses a term that conflicts with openspec/specs/ubiquitous-language/spec.md, call it out immediately. "Your ubiquitous-language spec 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 ubiquitous language inline
When a term is resolved and usage is consistent, update openspec/specs/ubiquitous-language/spec.md right there. Don't batch these up — capture them as they happen. Use the term entry format in OPENSPEC-MODE.md.
When usage is mixed or conflicting, surface the conflict and propose alignment — do not silently pick one meaning.
The ubiquitous-language spec is a glossary only. No implementation details, no scratch-pad content.
Offer specs and ADRs sparingly
Only offer to record an architectural decision 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 it.
- Behavioral contract → ADDED/MODIFIED requirements in the most relevant capability spec (canonical if already implemented; delta under
openspec/changes/<name>/specs/<capability>/spec.mdif change is required — suggest/opsx:propose) - Non-obvious rationale → ADR in
docs/adr/using ADR-FORMAT.md - Both apply → write both; cross-link per OPENSPEC-MODE.md
When working inside a ferspec change, discovery.md and design.md Decisions are working docs — distill durable decisions into ADRs as they crystallise or during apply Documentation tasks.
For complex ADRs (MADR, supersession chains), suggest the architecture-decision-records skill.
See OPENSPEC-MODE.md for what qualifies and how to name capability specs.
Legacy mode
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.
For complex ADRs (MADR, supersession chains), suggest the architecture-decision-records skill.