Vai al contenuto
TakoAPI
Torna alle skill

model-switcher

di puaservice

Coding Agents & IDEs
516Download riportati da clawskills.sh
1Visualizzazioni
0 likeAccedi per mettere like a questa skill
—Non ancora valutato
La tua valutazione

Sintesi

Automatically switch between fast (haiku) and powerful (sonnet) models based on task complexity.

Descrizione

Cosa fa questa skill

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 usarla

  • 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

Esempio di workflow

INPUT

User asks: "帮我分析一下这个系统的架构"

AGENT
  1. 1

    Check current model using session_status

  2. 2

    Detect keywords in the message: 分析, 架构

  3. 3

    Determine that a complex task is detected and current model is haiku

  4. 4

    Switch to sonnet using session_status({ model: "kiro-cli" })

  5. 5

    Inform user: "切换到 sonnet 模型来处理这个复杂任务..."

OUTPUT

Model switched to sonnet; response generated using the more powerful model

Installazione

clawhub install puaservice/model-switcher

Esegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.

Link