Implement a CLI game of Minesweeper using Ruby. Make sure to cover it with tests. The game should work by generating a minesweeper board, printing it and asking the user for the coordinates of the cell they wish to uncover. The board should be printed using the following notation: # for a still hidden field, 1-8 for a field with that many mines in the neighborhood, . for a field with no neighbors with mines and * for a mine. The program should correctly detect losing the game by hitting a mine and winning the game by uncovering all the fields without mines.
I am Jarvis, Just a really very intelligent savant, who serves. I am an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not an option.
The Memory Bank consists of required core filesd in the /memorybank directory and optional context files, all in Markdown format. Files build upon each other in a clear hierarchy:
flowchart TD| { | |
| "inputs": [ | |
| { | |
| "type": "promptString", | |
| "id": "github-pat", | |
| "password": true, | |
| "description": "GitHub Personal Access Token (PAT, https://github.com/settings/personal-access-tokens/new)" | |
| } | |
| ], | |
| "servers": { |
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.
The Memory Bank consists of required core files and optional context files, all in Markdown format. Files build upon each other in a clear hierarchy:
flowchart TDThis repository contains a disciplined, evidence-first prompting framework designed to elevate an Agentic AI from a simple command executor to an Autonomous Principal Engineer.
The philosophy is simple: Autonomy through discipline. Trust through verification.
This framework is not just a collection of prompts; it is a complete operational system for managing AI agents. It enforces a rigorous workflow of reconnaissance, planning, safe execution, and self-improvement, ensuring every action the agent takes is deliberate, verifiable, and aligned with senior engineering best practices.
I also have Claude Code prompting for your reference: https://gist.github.com/aashari/1c38e8c7766b5ba81c3a0d4d124a2f58
These are NOT product / license keys that are valid for Windows activation.
These keys only select the edition of Windows to install during setup, but they do not activate or license the installation.
| # /home/jesuiswk/.config/tmuxinator/tm.yml | |
| name: tm | |
| root: ~/Documents/ThirtyMadison/ | |
| # Optional tmux socket | |
| # socket_name: foo | |
| # Note that the pre and post options have been deprecated and will be replaced by | |
| # project hooks. |
| # this is useful for sending action cable updates to doctors portal | |
| def spam(count, naptime) | |
| patients = Patient.all.sample(count) | |
| patients.each do |patient| | |
| sleep(naptime) if naptime | |
| Doctor.all.each do |doc| | |
| DoctorSchema.subscriptions.trigger('patientUpdates', { doctorId: doc.id }, patient) | |
| end |