donald-ada/workinggenius / skills/domain-glossary
domain-glossary
VerifiedMaintain the project's shared vocabulary in CONTEXT.md — challenge conflicting terms, sharpen fuzzy language, record resolutions inline. Use when a term being settled with the user conflicts with the glossary or means two things, when a decision names a new project concept that later work will need a word for, or when another skill needs the glossary discipline. Reading CONTEXT.md to use its vocabulary is not this skill, and an ordinary request that uses a term is not an invitation to start a glossary.
Domain Glossary
One shared language between the user, the agent and the code — Domain-Driven Design's ubiquitous language — living in CONTEXT.md at the repo root: a glossary and nothing else. A term sharpened during one piece of work serves every later one: shorter conversations, consistent naming in code and tests. Left alone, each conversation coins its own word for the same thing, the code ends up naming one concept three ways, and a term settled once is fought over again by a session that never saw the fight.
The concept: one concept, one word — written into the glossary the moment it is settled.
Format
# {Project Name}
{One or two sentences on what this project is.}
## Language
**customer**:
{One or two sentences. What it IS, not what it does.}
Killed: *client*, *buyer* — one concept, one word.
**archive**:
Soft-hide; the user can restore it. Settled against permanent deletion in the
exports work — restorability is a support contract.
Killed: *trash*, *delete* — each carried both meanings at once.
- Be opinionated. When several words name one concept, pick the best and name the losers as killed — with what killed them where there was a real fight.
- A fought term keeps its fight. A term that collided carries the collision in one line: what collided, which won, why. A resolution recorded without its collision gets re-litigated.
- Published API names outrank opinion. A misleading name that's public API can't be renamed — define it against its general meaning instead ("not actually a cryptographic salt; the name is API, the definition rules").
- Tight definitions, one or two sentences, of what it is. Project concepts only — general programming concepts don't belong. No implementation details: not a spec, a scratchpad or a decision log — decisions live in their work file, indexed in
.genius/DECIDED.md. - Create lazily, at the first resolved term, because an empty skeleton is premature documentation. Don't hijack: an existing
CONTEXT.mdwith other content keeps it, because that content belongs to whoever wrote it and not to this discipline; append the## Languagesection and stay scoped to it.
The discipline
While any conversation is shaping work:
- Collide words with the glossary. The user's term conflicts with an entry → stop and hold the two meanings up side by side: "The glossary says an archived account is restorable, but you're describing permanent deletion — which do you mean?" No building on a word that means two things at once.
- Sharpen fuzzy terms. One word doing two jobs → propose a precise canonical term for each.
- Collide claims with the code. The user says how something works; the code disagrees → surface the contradiction.
- Update inline. The moment a term resolves, write it — not batched at the end. A resolution that isn't written down will be re-litigated.
- The flow's own names get one rendering in the project's language. Where records are written in a language other than English, slice, snapshot, contract, seam, kill-reason, assumed, backlog and the six stage names are terms like any other: rendered differently at each writing they become several words for one concept. Record each once under
## Language, the first time a record is written in that language (setup-working-geniusoffers it), and every record uses that rendering (record-proseskill).
Merely reading CONTEXT.md to use its vocabulary is not this skill. Invoke it only when the language itself is being built, challenged or changed.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |