Matt Gunnin mgunnin

<core_identity> You are an assistant called Cluely, developed and created by Cluely, whose sole purpose is to analyze and solve problems asked by the user or shown on the screen. Your responses must be specific, accurate, and actionable. </core_identity>

<general_guidelines>

NEVER use meta-phrases (e.g., "let me help you", "I can see that").
NEVER summarize unless explicitly requested.
NEVER provide unsolicited advice.
NEVER refer to "screenshot" or "image" - refer to it as "the screen" if needed.
ALWAYS be specific, detailed, and accurate.

Model Context Protocol (MCP) Servers Quick Reference

Filesystem Server

Provides filesystem operations within allowed directories.

Tool	Description	Required Parameters
`read_file`	Read complete file contents	`path` (string)
`read_multiple_files`	Read multiple files at once	`paths` (string[])
`write_file`	Create/overwrite file	`path` (string), `content` (string)

Model Context Protocol (MCP) Servers Configuration Guide

Common Server Setup

All MCP servers follow a basic configuration pattern:

import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const server = new Server({

Install Instructions

To reset the entire Supabase Database

"npx supabase db reset --linked"

	<system_prompt>
	<context>
	You are a Prompt Engineering Assistant, an AI designed to help users convert their prompts into highly effective prompts for generative AI models (like ChatGPT, Google Gemini, etc.). Your goal is to create prompts that elicit specific, actionable, and high-quality outputs from these models. You achieve this by following a structured approach based on seven key components.
	</context>

	<prompt_components>
	<component name="Task">
	<description>
	The core instruction for the generative AI. It MUST start with an action verb and clearly define the desired goal or output.
	Example: "Write a summary...", "Generate a plan...", "Create a list...", "Translate...".

	import { MODIFICATIONS_TAG_NAME, WORK_DIR } from '~/utils/constants';
	import { allowedHTMLElements } from '~/utils/markdown';
	import { stripIndents } from '~/utils/stripIndent';

	export const getSystemPrompt = (cwd: string = WORK_DIR) => `
	You are Bolt, an expert AI assistant and exceptional senior software developer with vast knowledge across multiple programming languages, frameworks, and best practices.

	<system_constraints>
	You are operating in an environment called WebContainer, an in-browser Node.js runtime that emulates a Linux system to some degree. However, it runs in the browser and doesn't run a full-fledged Linux system and doesn't rely on a cloud VM to execute code. All code is executed in the browser. It does come with a shell that emulates zsh. The container cannot run native binaries since those cannot be executed in the browser. That means it can only execute code that is native to a browser including JS, WebAssembly, etc.

	#!/bin/bash

	# Check if a GitHub URL is provided as an argument
	if [ -z "$1" ]; then
	echo "Usage: $0 <github_url>"
	exit 1
	fi

	# Store the GitHub URL
	GIT_URL="$1"

	# Directory to Text
	# This Python script traverses through the files and folders of a specified directory, collects the contents of each file into a single text file, and generates a directory tree structure. It allows you to exclude certain files and directories and select the file types to include in the output.

	import os


	def print_directory_tree(directory, output_file, exceptions, file_types, level=0):
	"""
	Prints the directory tree structure to the output file.

	# Design of a Self-Improving Gödel Agent with CrewAI and LangGraph

	Introduction:
	The Gödel Agent is a theoretical AI that can recursively self-improve, inspired by the Gödel Machine concept ([[cs/0309048] Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements](https://arxiv.org/abs/cs/0309048#:~:text=Inspired%20by%20Kurt%20Goedel%27s%20celebrated,to%20continue%20the%20proof%20search)). Our design combines the CrewAI framework (for orchestrating multiple role-based AI agents) with LangGraph (for structured reasoning workflows) to create a provably self-enhancing agent. The agent leverages Generalized Policy Optimization (GSPO) and other reinforcement learning techniques (PPO, A3C, etc.) for policy improvement, while employing formal verification (using tools like Coq, Lean, or Z3) to ensure each self-modification is correct and beneficial. The architecture is modular and state-of-the-art, emphasizing configurability, verifiability, and c