service-gateway

Route LLM generation, embedding, reranking, and token counting through a unified gateway.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/quarkloop/agent --skill service-gateway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: service-gateway
Source: https://github.com/quarkloop/agent/tree/main/plugins/services/gateway
Command: npx skills add https://github.com/quarkloop/agent --skill service-gateway

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bifrost, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of manually handling various LLM tasks like generation, embedding, reranking, and token counting, by providing a unified gateway to streamline these processes.

Core Features & Use Cases

  • Unified Gateway: Simplifies access to LLM services for generation, embeddings, reranking, token counting, and more.
  • Provider Integration: Seamlessly integrates with multiple LLM providers for flexible use.
  • Usage Accounting: Provides detailed usage information for tracking and monitoring.
  • Use Case: Automate the generation of content, embedding of text, reranking of search results, and token counting within your applications.

Quick Start

Use the gateway skill to generate text based on the input prompt 'How AI is transforming industries'.

Frequently Asked Questions about service-gateway

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

FAQPage Schema
How do I streamline LLM generation, embeddings, and reranking through a unified gateway?

A unified gateway centralizes access to LLM generation, embeddings, and reranking by routing requests through a single endpoint. This simplifies provider integration and automates content generation workflows without manual endpoint management.

Can I track token counting and usage details across multiple LLM providers?

Yes, you can track token counting and usage details across multiple LLM providers. The gateway provides detailed usage accounting metrics to monitor consumption and track service integration within your application workflows.

Does the service gateway require bifrost to integrate LLM providers?

Yes, the service gateway requires the bifrost dependency to function properly. You must install bifrost to enable the gateway to integrate LLM providers and route generation, embedding, and reranking requests.

What is the best way to automate content generation and token counting in application workflows?

The best way to automate content generation and token counting is by implementing a unified gateway. It routes LLM generation requests and calculates token metrics automatically while providing detailed usage accounting for your application workflows.

How do I integrate multiple LLM providers for embeddings and reranking services?

You integrate multiple LLM providers for embeddings and reranking by connecting them to the unified gateway. This approach seamlessly manages provider integration to simplify access and automate text processing tasks.