Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Prompt file imported from grandeclip/grandeclip-workspace (.claude/commands/create-command.md). Copyright stays with the author.
Create Command
커스텀 명령어를 만듭니다.
실행
/create-command
대화형 생성
Claude Code가 질문하며 명령어를 만들어줍니다:
"명령어 이름은?" → 예: meeting-prep
"설명은?" → 예: "미팅 준비 자료 생성"
"어떤 작업을 수행하나요?" → 단계별 설명
활용 아이디어
/weekly-plan - 주간 계획 생성
/expense - 경비 정리
/client-brief - 클라이언트 브리핑
/lecture-outline - 강의 개요 작성
출력
.claude/commands/명령어이름.md 파일 생성
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# Create Command
커스텀 명령어를 만듭니다.
## 실행```bash
/create-command
```
## 대화형 생성
Claude Code가 질문하며 명령어를 만들어줍니다:
1. "명령어 이름은?" → 예: `meeting-prep`2. "설명은?" → 예: "미팅 준비 자료 생성"3. "어떤 작업을 수행하나요?" → 단계별 설명
## 활용 아이디어
- `/weekly-plan` - 주간 계획 생성
- `/expense` - 경비 정리
- `/client-brief` - 클라이언트 브리핑
- `/lecture-outline` - 강의 개요 작성
## 출력`.claude/commands/명령어이름.md` 파일 생성
Installed into a catalogue, chosen by a router
Install create-command and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.