Intelligent Routing

This handles automatic agent selection so you don't have to keep typing @mentions. It analyzes incoming requests, detects domains like auth, frontend, or database work, then routes to the right specialist agent or combination of agents. Simple tasks get sent directly to a single agent, moderate complexity might invoke two or three, and anything hairy goes to the orchestrator. The selection matrix is comprehensive, covering everything from UI components to security reviews. The main win is speed: instead of thinking about which agent to invoke, you just describe what you need and it figures out whether to apply security-auditor plus backend-specialist for login features or frontend-specialist for button work. You can still override with explicit mentions if the auto-routing misses.

skills.sh installs: 157
GitHub stars: 7.6K
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add vudovn/antigravity-kit --skill intelligent-routing --agent claude-code

Installs into .claude/skills of the current project.

Files

Intelligent Agent Routing

Purpose: Automatically analyze user requests and route them to the most appropriate specialist agent(s) without requiring explicit user mentions.

Core Principle

The AI should act as an intelligent Project Manager, analyzing each request and automatically selecting the best specialist(s) for the job.

How It Works

1. Request Analysis

Before responding to ANY user request, perform automatic analysis:

graph TD
    A[User Request: Add login] --> B[ANALYZE]
    B --> C[Keywords]
    B --> D[Domains]
    B --> E[Complexity]
    C --> F[SELECT AGENT]
    D --> F
    E --> F
    F --> G[security-auditor + backend-specialist]
    G --> H[AUTO-INVOKE with context]