model-switcher
por puaservice
Coding Agents & IDEsResumo
Automatically switch between fast (haiku) and powerful (sonnet) models based on task complexity.
Descrição
O que esta skill faz
Detects task complexity from message content and switches between a fast model (haiku) and a powerful model (sonnet) automatically. Keyword detection covers Chinese-language terms for analysis, refactoring, architecture, optimization, and debugging. The switch is communicated to the user only when it actually occurs.
Avoids manual model selection by inferring complexity from message content, keeping fast responses for simple tasks and stronger reasoning for complex ones.
Quando usá-la
- Switching to sonnet when asking for a system architecture review
- Staying on haiku for quick single-line code questions
- Batching complex refactoring work on sonnet before switching back
- Auto-detecting Chinese-language analysis requests
- Resetting to the default model after completing a complex session
Exemplo de fluxo de trabalho
User asks: "帮我分析一下这个系统的架构"
- 1
Check current model using session_status
- 2
Detect keywords in the message: 分析, 架构
- 3
Determine that a complex task is detected and current model is haiku
- 4
Switch to sonnet using session_status({ model: "kiro-cli" })
- 5
Inform user: "切换到 sonnet 模型来处理这个复杂任务..."
Model switched to sonnet; response generated using the more powerful model
Instalação
clawhub install puaservice/model-switcherExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.