skill-router

Route agent actions through the correct Topia skill before technical responses.

1|Updated May 18, 2026
One-click install
npx skills add https://github.com/linenoize/topia --skill skill-router-linenoize
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-router
Source: https://github.com/linenoize/topia/tree/main/skills/skill-router
Command: npx skills add https://github.com/linenoize/topia --skill skill-router-linenoize

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Skill-router prevents agents from acting on impulse by forcing every technical request through the correct Topia skill before any code is written, file is read, or decision is made. It reduces skipped steps, wrong-skill execution, and workflow drift by enforcing disciplined routing.

Core Features & Use Cases

  • Universal request routing: Classifies user intent and sends build, debug, review, plan, or domain work to the appropriate skill.
  • Adaptive overrides: Checks routing overrides and model hints so previously learned corrections can change the path when needed.
  • Workflow enforcement: Applies hard gates for code changes, compound intent resolution, and quality constraints across the skill stack.
  • Use case: A user asks to fix a bug and add tests, and the router chains the request through the correct skills in the right order instead of letting the agent improvise.

Quick Start

Use the skill-router logic to classify the request and route it through the correct Topia skill before answering.

Frequently Asked Questions about skill-router

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

FAQPage Schema
How do I enforce agent workflow routing before code changes are made?

Agent workflow routing is enforced by classifying user intent and sending every request through the correct skill before any technical response is produced, preventing skipped steps and wrong-skill execution.

What is intent classification for agent orchestration and when is it needed?

Intent classification for agent orchestration is the pre-response process of categorizing user requests to apply adaptive overrides, layer discipline, and skill-specific constraints before any technical decision is made.

Can I chain multiple skills together for compound requests like fixing bugs and adding tests?

Yes, compound intent resolution allows you to chain requests like fixing bugs and adding tests through the correct skills in the right order, applying hard gates for code changes across the skill stack.

Why does my agent skip workflow steps and improvise during debugging?

Agents skip workflow steps and improvise during debugging because they act on impulse without routing guardrails; forcing requests through intent classification and quality constraints prevents this workflow drift.

What's the best way to apply adaptive overrides during skill selection?

The best way to apply adaptive overrides during skill selection is to check routing overrides and model hints, allowing previously learned corrections to change the routing path when needed.