Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
.claude/skills/mkurman-ubiquitous-language/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -47% | 0% |
----- | ------------------------------------------------------- | --------------------- | | Order | A customer's request to purchase one or more items | Purchase, transaction | | Invoice | A request for payment sent to a customer after delivery | Bill, payment request |
| Term | Definition | Aliases to avoid | | ------------ | ------------------------------------------- | ---------------------- | | Customer | A person or organization that places orders | Client, buyer, account | | User | An authentication identity in the system | Login, account |
> Dev: "When a Customer places an Order, do we create the Invoice immediately?" > Domain expert: "No — an Invoice is only generated once a Fulfillment is confirmed. A single Order can produce multiple Invoices if items ship in separate Shipments." > Dev: "So if a Shipment is cancelled before dispatch, no Invoice exists for it?" > Domain expert: "Exactly. The Invoice lifecycle is tied to the Fulfillment, not the Order."
## Rules
- **Be opinionated.** When multiple words exist for the same concept, pick the best one and list the others as aliases to avoid.
- **Flag conflicts explicitly.** If a term is used ambiguously in the conversation, call it out in the "Flagged ambiguities" section with a clear recommendation.
- **Only include terms relevant for domain experts.** Skip the names of modules or classes unless they have meaning in the domain language.
- **Keep definitions tight.** One sentence max. Define what it IS, not what it does.
- **Show relationships.** Use bold term names and express cardinality where obvious.
- **Only include domain terms.** Skip generic programming concepts (array, function, endpoint) unless they have domain-specific meaning.
- **Group terms into multiple tables** when natural clusters emerge (e.g. by subdomain, lifecycle, or actor). Each group gets its own heading and table. If all terms belong to a single cohesive domain, one table is fine — don't force groupings.
- **Write an example dialogue.** A short conversation (3-5 exchanges) between a dev and a domain expert that demonstrates how the terms interact naturally. The dialogue should clarify boundaries between related concepts and show terms being used precisely.
<example>
## Example dialogue
> **Dev:** "How do I test the **sync service** without Docker?"
> **Domain expert:** "Provide the **filesystem layer** instead of the **Docker layer**. It implements the same **Sandbox service** interface but uses a local directory as the **sandbox**."
> **Dev:** "So **sync-in** still creates a **bundle** and unpacks it?"
> **Domain expert:** "Exactly. The **sync service** doesn't know which layer it's talking to. It calls `exec` and `copyIn` — the **filesystem layer** just runs those as local shell commands."
</example>
## Re-running
When invoked again in the same conversation:
1. Read the existing `UBIQUITOUS_LANGUAGE.md`
2. Incorporate any new terms from subsequent discussion
3. Update definitions if understanding has evolved
4. Re-flag any new ambiguities
5. Rewrite the example dialogue to incorporate new terms| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 21,677 | 11,737 | -46% | 1 | 1 | 0% | 3,652 | 3,131 | -14% | 0 | 0 | — |
case-02 | fail→pass | 22,495 | 13,357 | -41% | 1 | 1 | 0% | 3,604 | 3,186 | -12% | 0 | 0 | — |
case-03 | fail→fail | 19,167 | 12,624 | -34% | 1 | 1 | 0% | 3,480 | 3,198 | -8% | 0 | 0 | — |
case-04 | pass→pass | 10,621 | 12,356 | +16% | 1 | 1 | 0% | 2,205 | 3,244 | +47% | 0 | 0 | — |
case-05 | pass→pass | 12,587 | 47,834 | +280% | 1 | 1 | 0% | 2,689 | 5,760 | +114% | 0 | 0 | — |
case-06 | pass→pass | 15,373 | 20,144 | +31% | 1 | 1 | 0% | 3,599 | 4,601 | +28% | 0 | 0 | — |
case-07 | fail→pass | 20,469 | 12,461 | -39% | 1 | 1 | 0% | 3,538 | 3,241 | -8% | 0 | 0 | — |
case-08 | fail→pass | 17,416 | 12,694 | -27% | 1 | 1 | 0% | 2,967 | 3,170 | +7% | 0 | 0 | — |
case-09 | fail→pass | 23,639 | 12,067 | -49% | 1 | 1 | 0% | 4,091 | 2,972 | -27% | 0 | 0 | — |
case-10 | fail→pass | 30,667 | 10,887 | -64% | 1 | 1 | 0% | 5,112 | 2,722 | -47% | 0 | 0 | — |
case-11 | pass→pass | 22,725 | 13,398 | -41% | 1 | 1 | 0% | 4,023 | 3,271 | -19% | 0 | 0 | — |
case-12 | fail→pass | 24,194 | 11,072 | -54% | 1 | 1 | 0% | 3,991 | 2,902 | -27% | 0 | 0 | — |
case-13 | pass→pass | 12,753 | 13,182 | +3% | 1 | 1 | 0% | 2,472 | 3,302 | +34% | 0 | 0 | — |
case-14 | fail→pass | 21,613 | 18,360 | -15% | 1 | 1 | 0% | 3,650 | 4,028 | +10% | 0 | 0 | — |
case-15 | fail→pass | 27,134 | 14,982 | -45% | 1 | 1 | 0% | 4,307 | 3,612 | -16% | 0 | 0 | — |
case-16 | fail→pass | 23,448 | 12,512 | -47% | 1 | 1 | 0% | 4,123 | 3,244 | -21% | 0 | 0 | — |
case-17 | fail→pass | 26,929 | 11,209 | -58% | 1 | 1 | 0% | 4,559 | 2,951 | -35% | 0 | 0 | — |
case-18 | pass→pass | 16,838 | 12,316 | -27% | 1 | 1 | 0% | 3,197 | 3,204 | +0% | 0 | 0 | — |
case-19 | fail→pass | 30,469 | 15,144 | -50% | 1 | 1 | 0% | 5,012 | 3,591 | -28% | 0 | 0 | — |
case-20 | fail→pass | 25,358 | 15,377 | -39% | 1 | 1 | 0% | 4,264 | 3,539 | -17% | 0 | 0 | — |
case-21 | fail→pass | 22,081 | 13,893 | -37% | 1 | 1 | 0% | 3,696 | 3,428 | -7% | 0 | 0 | — |
case-22 | fail→pass | 27,893 | 13,773 | -51% | 1 | 1 | 0% | 4,640 | 3,157 | -32% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +64 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.