Name It — turning a raw description into the precise term and a senior's question
The owner named a real fluency gap: he knows the concept but not the English term, so he asks questions clumsily. Built a reverse-glossary mode — dump a raw description and get the precise term(s), a one-line definition, the polished way a senior would ask the question, and related terms.
The owner surfaced the gap under the gap: it's not that he can't speak, it's that when he has a concept in his head and doesn't know its English term, he asks for it raw — a clumsy paraphrase instead of the word. A glossary doesn't help, because a glossary goes term → meaning, and his problem is the reverse: meaning → term.
So /askright ("Name It") is a reverse lookup. You dump the clumsy description — Korean, broken English, or spoken — and it returns the precise term or two you were reaching for with a one-line definition, the polished way a senior engineer would actually ask that question out loud using the right term, and a few adjacent terms worth knowing. It's text-first so it works anywhere (⌘/Ctrl+Enter to submit, example chips to seed it), with the mic as an option that reuses the existing transcribe loop. Backed by gpt-4o since it's a fast lookup, not deep reasoning.
Verified live: "데이터가 두 군데 따로 저장돼서 안 맞는 거" came back as Data Inconsistency / Data Synchronization, a clean question to ask, and related terms (Replication, Consistency Model, Conflict Resolution). So instead of fumbling, he gets the word plus the sentence to say.
The reusable idea: the hard half of vocabulary fluency is meaning → term, not term → meaning — and pairing the term with the question-asking pattern trains both recognition and the reflex to ask it like a senior.