model-routing

Route tasks to Opus, Sonnet, or Haiku tiers based on complexity and bug scoring.

5|Updated Feb 6, 2026
One-click install
npx skills add https://github.com/FaisalAlqarni/sp-ecc --skill model-routing-faisalalqarni
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-routing
Source: https://github.com/FaisalAlqarni/sp-ecc/tree/main/skills/model-routing
Command: npx skills add https://github.com/FaisalAlqarni/sp-ecc --skill model-routing-faisalalqarni

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of efficiently allocating tasks to different Large Language Models (LLMs) based on their complexity and cost, ensuring optimal resource utilization without compromising output quality.

Core Features & Use Cases

  • Task Classification: Automatically categorizes incoming tasks to determine the most suitable LLM tier (Opus, Sonnet, Haiku).
  • Bug Complexity Scoring: Provides a framework to score bug complexity, guiding escalation to more powerful (and expensive) models like Opus only when necessary.
  • Cost Optimization: Implements patterns to route tasks, leading to significant cost savings by avoiding the overuse of high-tier models for simpler tasks.
  • Use Case: When a bug is reported, the skill analyzes its complexity. If it's a simple bug, it's routed to Sonnet. If it's a complex, multi-file issue with no clear stack trace, it's escalated to Opus for deeper analysis.

Quick Start

Use the model-routing skill to classify the complexity of the current bug report and suggest the appropriate LLM tier.

Frequently Asked Questions about model-routing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I optimize LLM costs by routing tasks to different models?

LLM cost optimization through model routing assigns tasks to Opus, Sonnet, or Haiku tiers based on complexity scoring. This framework analyzes bug severity and task classification to escalate only multi-file issues to expensive models, maintaining output quality while reducing overall AI workflow expenditures.

What is the best way to classify bug complexity for AI model escalation?

Bug complexity classification for AI model escalation uses a scoring framework to evaluate issue severity, stack trace clarity, and multi-file scope. Simple bugs route to Sonnet, while complex issues lacking clear traces escalate to Opus for deeper analysis and reasoning.

When should I escalate a bug report to a higher-tier LLM like Opus?

Escalate a bug report to a higher-tier LLM like Opus when the issue involves complex, multi-file problems with no clear stack trace. The model routing framework uses bug complexity scoring to trigger this escalation only for deep analysis requirements.

How does task classification improve AI efficiency in software engineering?

Task classification improves AI efficiency by categorizing incoming software engineering tasks to determine the most suitable LLM tier. This intelligent resource allocation prevents overuse of high-tier models for simple applications, optimizing cost-effectiveness and maintaining quality.

Can I use this model routing framework for simple application tasks?

You can use this model routing framework for simple application tasks by classifying them to route directly to lower-tier, cost-effective models like Haiku or Sonnet. This ensures intelligent resource allocation without wasting high-tier model capacity on basic implementations.