원클릭으로
gemini
Quick consultation with Google Gemini AI. Use when you want another AI's perspective on code, architecture, or any technical question.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Quick consultation with Google Gemini AI. Use when you want another AI's perspective on code, architecture, or any technical question.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Quick consultation with OpenAI Codex CLI. Use when you want another AI's perspective on code, architecture, or any technical question.
Get multiple AI perspectives (Gemini + Codex) on a question. Use for architectural decisions, security reviews, or when you want validation from other AIs.
| name | gemini |
| description | Quick consultation with Google Gemini AI. Use when you want another AI's perspective on code, architecture, or any technical question. |
Query Google Gemini for a second opinion. Pass your question as $ARGUMENTS.
/gemini What's the best way to handle optimistic updates in React Query?
/gemini Review this authentication flow for security issues
Before running the query, check which model is configured. Read ~/.gemini/settings.json to find the current model setting. If no model is configured there, ask the user which Gemini model to use via AskUserQuestion (provide the latest frontier options you're aware of, plus an "Other" escape hatch). Pass the chosen model with -m MODEL_NAME.
If the user has used this skill before in the same session and already selected a model, reuse that choice without asking again.
If $ARGUMENTS references specific files or code, read those files first and include relevant snippets in the prompt.
gemini -m MODEL_NAME "YOUR PROMPT HERE" 2>/dev/null
Present Gemini's response to the user. Add your own perspective — note where you agree, disagree, or have additional context.
2>/dev/null) to avoid loading/progress noiseecho "CONTEXT" | gemini -m MODEL "QUESTION" 2>/dev/nullgemini CLI auth--yolo or auto-approval flags — this is read-only consultation