cablej

<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.

martinbowling

You are the user's live-meeting co-pilot. The **ONLY** relevant moment is the end of the audio transcript (CURRENT MOMENT). 
Respond **only** to the LAST QUESTION asked by the interviewer. 
If no question exists, provide a *brief* definition of the last technical term / company / place that appears and has not yet been defined.

Transcript annotation rules
• If lines are tagged with ("me") and ("them"), ("them") = interviewer.  
• If only ("me") tags exist, infer who is asking.

================  OUTPUT FORMAT  ================
1. Start with **one SHORT headline (≤ 6 words)** answering/deciding. No greetings.

Maharshi-Pandya

You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

## Core Principles

1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference

disler

Four Level framework for prompt engineering

Watch the breakdown here in a Q4 2024 prompt engineering update video

LLM library

Ollama

Level 1: Ad hoc prompt

• Quick, natural language prompts for rapid prototyping
• Perfect for exploring model capabilities and behaviors

artsparkAI

You are a world-class Staff Engineer in React, Typescript, Next.js and Tailwind CSS. Your role is to generate complete,
functional front-end code based on the user's specifications. Adhere to these guidelines:


<CleanCode>
Don't Repeat Yourself (DRY)
Duplication of code can make code very difficult to maintain. Any change in logic can make the code prone to bugs or can
make the code change difficult. This can be fixed by doing code reuse (DRY Principle).

The DRY principle is stated as "Every piece of knowledge must have a single, unambiguous, authoritative representation

soulbliss

// Nuke 'em all
// Marc's tweet https://twitter.com/marc_louvion/status/1776629697046339969

import { useEffect } from 'react';

useEffect(() => {
  let referral_url = new URL(window?.location?.href);

  if (
    referral_url?.searchParams?.has('gclid') &&

lithdew

# syntax = docker/dockerfile:1

# Adjust BUN_VERSION as desired
ARG BUN_VERSION=1.1.1
FROM oven/bun:${BUN_VERSION}-slim as base

LABEL fly_launch_runtime="Next.js"

# Next.js app lives here
WORKDIR /app

marcpinet

Activate Sublime Text (for ever)

1. Go to https://hexed.it/
2. Click Open File in the top left corner and select sublime_text.exe
3. Press CTRL + F or on the Search for bar in the left panel and look for: 80 78 05 00 0f 94 C1
4. Now in the editor, click on the first byte (80) and start replacing each byte by: C6 40 05 01 48 85 C9
5. Finally, in the top left corner again, click on Save as and replace the old executable file with the newly created one.

Enjoy an Unlimited User License!

merlinmann

Merlin's Wisdom Project

Or: “Everybody likes being given a glass of water.”

By Merlin Mann.

It's only advice for you because it had to be advice for me.

whitep4nth3r

#!/bin/bash

# Input flags

LANG=""
APP_NAME=""

# The directory path must be relative to where the script lives
DIR=""