dynamic-model-selector
par mpelissari
Coding Agents & IDEsRésumé
Dynamically select the best AI model for a task based on complexity, cost, and availability in GitHub Copilot.
Description
Ce que fait ce skill
Analyzes user queries to recommend the optimal AI model from GitHub Copilot's available options. Routes tasks based on complexity, cost sensitivity, and task type such as code generation or multi-step reasoning.
Instead of manually picking a model each time, the classification script matches task complexity to the right model, avoiding overpaying for simple queries or underserving complex ones.
Quand l'utiliser
- Routing simple chat queries to free models to avoid unnecessary cost
- Selecting gpt-4o for complex analysis tasks automatically
- Picking code-optimized models for code generation requests
- Comparing model options before starting a long reasoning task
- Keeping costs low on high-volume automated workflows
Exemple de workflow
User asks: 'Explain the difference between TCP and UDP'
- 1
Pass the query to classify_task.py
- 2
Script evaluates complexity, task type, and cost constraints
- 3
Classification returns medium complexity, general explanation
- 4
Selector recommends gpt-4o based on models.md criteria
- 5
User proceeds with the recommended model in GitHub Copilot
Model recommendation: gpt-4o for a medium-complexity explanation task
Prérequis
- GitHub Copilot subscription or access
Installation
clawhub install mpelissari/dynamic-model-selectorExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.