skills.rest
nopkhun
nopkhunCOMMUNITY
Explore all skills by this author →
GitHub

smart-routing

Route /toh commands to agents using intent classification and confidence scoring.

Updated Mar 3, 2026
Search Tags:#routing#agent selection#intent classification#context awareness#ide detection#request processing
One-click install
npx skills add https://github.com/nopkhun/KO-STOCK-SYSTEM --skill smart-routing-nopkhun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: smart-routing
Source: https://github.com/nopkhun/KO-STOCK-SYSTEM/tree/main/.gemini/skills/smart-routing
Command: npx skills add https://github.com/nopkhun/KO-STOCK-SYSTEM --skill smart-routing-nopkhun

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill intelligently routes user requests to the appropriate agent, ensuring efficient and accurate task execution by analyzing intent, context, and environment.

Core Features & Use Cases

  • Intent Classification: Maps natural language requests to specific agent functions using keywords and context.
  • Confidence Scoring: Assesses the clarity and certainty of a request to determine the best routing strategy.
  • IDE Detection: Adapts execution strategy (parallel/sequential) based on the detected development environment.
  • Memory Integration: Leverages past interactions and project context for more informed routing decisions.
  • Use Case: When a user types "/toh create a login page", this skill identifies the intent as "Create UI" and routes it directly to the UI Agent. For a more ambiguous request like "/toh improve it", it might route to the Plan Agent for clarification.

Quick Start

Use the smart-routing skill to process the request "create a user profile page".

Frequently Asked Questions about smart-routing

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

FAQPage Schema
How does intent classification work for routing natural language requests to agents?▼

Intent classification maps natural language requests to specific agent functions by analyzing keywords and context. It identifies the user's goal, such as UI creation, and routes the request directly to the appropriate agent for execution.

How do you route ambiguous user requests when the target agent is unclear?▼

For ambiguous requests, confidence scoring assesses request clarity to determine the routing strategy. Low confidence inputs are routed to a Plan Agent for clarification, ensuring accurate task execution before proceeding.

Can I use context awareness to improve request processing based on past interactions?▼

Yes, request processing uses a memory-first approach that leverages past interactions and project context. This memory integration enables more informed routing decisions by maintaining context awareness across requests.

Does IDE detection adapt request processing for different development environments?▼

IDE detection identifies the current development environment and adapts the execution strategy accordingly. It determines whether to process tasks in parallel or sequentially based on the detected IDE context.

What is the best way to handle request routing for multiple agent tasks?▼

The best way to handle multi-agent request routing is using intelligent request analysis that evaluates intent and confidence. It routes tasks to appropriate agents sequentially or in parallel based on IDE detection and context.

Related Skills

Explore More Software Engineering Skills→
wasintohwasintoh
90

smart-routing

Route user requests to appropriate agents based on intent and context.

Community
Basic
beshkenadzebeshkenadze
3

verify-known-issues

Verifies suspected bugs or limitations in external software via web search and citation-first reporting.

Community
Intermediate
oaustegardoaustegard
137

asking-questions

Identify ambiguous user requests and ask targeted clarifying questions.

Community
Basic
majiayu000majiayu000
12

skill

Route user requests to registered skill modules and execute them in context.

Community
Basic