glm-autoroute
por raufimusaddiq
Productivity & TasksResumo
Binary model routing for ZAI GLM models - lightweight vs heavyweight tasks.
Descrição
O que esta skill faz
Routes tasks between two ZAI GLM models based on complexity. GLM-4.7 handles simple lookups, status checks, and formatting by default. GLM-5 is spawned via sessions_spawn for coding, analysis, research, and multi-step reasoning.
Prevents unnecessary use of the heavier model for simple queries, keeping response times low and resource usage proportional to task complexity.
Quando usá-la
- Running routine heartbeat checks without escalating to the heavier model
- Automatically escalating code generation tasks to GLM-5
- Keeping cron job responses lightweight when no reasoning is needed
- Spawning GLM-5 for debugging or multi-step analysis
- Routing research and architecture planning to the more capable model
Exemplo de fluxo de trabalho
User asks: 'Write a Python script to parse CSV files'
- 1
Identifies the task as coding, which always routes to GLM-5
- 2
Spawns a GLM-5 session via sessions_spawn with the full task description and a short label
- 3
GLM-5 writes the script, saves it to file, and announces a summary of what was created
- 4
Main session returns to GLM-4.7 as default
Python script saved to file; summary of file path, status, and dependencies announced to user (GLM-5)
Instalação
clawhub install raufimusaddiq/glm-autorouteExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.