K-LEAN

🥈Silver

K-LEAN is a cross-platform toolkit that enhances Claude Code with multi-LLM consensus, specialist agents, semantic knowledge search, and one-command install. It benefits developers and operations teams by automating code reviews, integrating with CLI, and providing persistent memory for AI agents. K-LEAN connects to Claude Code, Litellm, Nano-GPT, and OpenRouter.

2570Updated 1mo ago

Intermediate30min to implementautomation

Saves ~75 min per use

Quick InstallView Source

git clone https://github.com/calinfaja/K-LEAN.git

Works with:

Claude

Overview

About This Skill

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/calinfaja/K-LEAN

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Using K-LEAN, perform a multi-LLM consensus code review for the following Python script: [SCRIPT]. Compare the feedback from Claude Code, Nano-GPT, and OpenRouter. Identify any discrepancies in their recommendations and suggest a final version that incorporates the best elements from each. Also, provide a one-line command to install any missing dependencies required by this script.

Example Output

After analyzing the provided Python script, here's the multi-LLM consensus review:

1. Claude Code identified a potential memory leak in the data processing loop and suggested adding a context manager for the file operations.
2. Nano-GPT agreed with the memory leak concern but also pointed out that the error handling could be more robust, suggesting specific try-except blocks.
3. OpenRouter concurred with both points and additionally recommended using a more efficient data structure for the cache.

The final recommended version incorporates all suggestions: it adds the context manager, implements robust error handling, and uses a more efficient data structure. The one-line command to install missing dependencies is: `pip install pandas numpy efficient-cache`.