章宦港 huangang

Roo Code Workflow: An Advanced LLM-Powered Development Setup

This gist outlines a highly effective and cost-optimized workflow for software development using Roo Code, leveraging a multi-model approach. This setup has been successfully used to build working applications, such as Baccarat game simulations with betting strategy analysis, and my personal portfolio site.

Core Components & Model Allocation

The power of this setup lies in strategically assigning different Large Language Models (LLMs) to specialized "modes" within Roo Code, optimizing for performance, cost, and specific task requirements.

Preparation

In open Ubuntu 18.04 machine click Parallels Actions -> "Install Parallels Tools"
A "Parallels Tools" CD will popup on your Ubuntu desktop.
Open it by double mouse click, copy all the content to a new, empty directory on a desktop, name it for e.g. "parallels_fixed"
Open terminal, change directory to parallels_fixed (cd ~/Desktop/parallels_fixed)
Make command line installer executable (chmod +x install)
Change directory to "installer" (cd installer)
Make few other scripts executable: chmod +x installer.* *.sh prl_*

	#!/usr/bin/env node

	/**
	* This script fixes the MCP SDK issue with pkce-challenge ES Module
	* It replaces the static require with a dynamic import in the auth.js file
	*/

	const fs = require('fs');
	const path = require('path');

	const APP = {
	deferredInstall: null,
	init() {
	if ('serviceWorker' in navigator) {
	//register our service worker
	navigator.serviceWorker
	.register('/sw.js', {
	updateViaCache: 'none',
	scope: '/',
	})