llm-client

Community

Unify all LLM calls through a single client.

AuthorVikaskanturi
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill unifies all LLM calls across the migration pipeline by routing them through a single client, ensuring consistent prompts, error handling, and provider-agnostic behavior.

Core Features & Use Cases

  • Centralized LLM interface for all agents, guaranteeing a single import path (core.llm_client.LLMClient) and uniform interaction patterns.
  • Support for multiple providers (Groq, HuggingFace, Ollama, OpenAI) with configurable models, retry logic, and JSON parsing utilities.
  • Safe, testable integration with rotation of providers and robust error handling to recover from transient failures in production environments.

Quick Start

Configure the LLM provider and credentials, then instantiate LLMClient and inject it into all agents.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: llm-client
Download link: https://github.com/Vikaskanturi/java_to_python_migration_agent/archive/main.zip#llm-client

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.