Maxiviper117

Just had a thought, LLMs work best by following a sequence of actions and steps… yet we usually guide them with plain English prompts, which are unstructured and vary wildly depending on who writes them.

Some people in other AI use cases have used JSON prompts for example, but that is still rigid and not expressive enough.

What if we gave AI system instructions as sequence diagrams instead?

What is a sequence diagram:

A sequence diagram is a type of UML (Unified Modeling Language) diagram that illustrates the sequence of messages between objects in a system over a specific period, showing the order in which interactions occur to complete a specific task or use case.

Maxiviper117

const TreeifyErrorNode: z.ZodType<any> = z.lazy(() =>
    z.object({
        errors: z.array(z.string()),
        properties: z.record(z.string(), TreeifyErrorNode).optional(),
        items: z.array(TreeifyErrorNode.or(z.undefined())).optional(),
    })
);

Maxiviper117

mode	model
agent	GPT-4.1

You are a Laravel development setup assistant. Your task is to setup a Laravel development environment with the necessary tools and configurations. You MUST follow the steps below exactly and in order. Do NOT skip, reorder, or modify any step. Use only the necessary tools to create and edit files, as well as terminal command executions. If any step fails, halt and report the error immediately.

Tasks

Setup Larastan

Maxiviper117

import { Effect, Layer, Console } from "effect"

// ─────────────────────────────────────────────────────────────────────────────
// 1) CONFIG AS A SERVICE
// ─────────────────────────────────────────────────────────────────────────────
export class Config extends Effect.Service<Config>()("Config", {
    accessors: true,
    effect: Effect.succeed({
        getConfig: Effect.succeed({
            logLevel: "DEBUG",

Maxiviper117

mode	model
agent	GPT-4.1

You are a Laravel development setup assistant. Your task is to setup a Laravel development environment with the necessary tools and configurations. You MUST follow the steps below exactly and in order. Do NOT skip, reorder, or modify any step. Use only the necessary tools to create and edit files, as well as terminal command executions. If any step fails, halt and report the error immediately.

Tasks

Setup Larastan

Maxiviper117

FrankenPHP + Docker + Custom HTTPS (laravel.test) Setup Guide

A step‑by‑step guide to run your Laravel app with FrankenPHP in “classic mode” inside Docker, using your own locally‑trusted HTTPS certificates.

---

📋 Prerequisites

• Docker Desktop installed and running
• PowerShell on Windows

Maxiviper117

Prerequisites

• Windows 10/11 with WSL 2 and your Laravel project working under WSL.
• Chocolatey installed on Windows (for easy Caddy install).
• A .test (or similar) hostname mapped to 127.0.0.1 (we’ll set that up below).

---

1. Install Caddy on Windows

Maxiviper117

1. Installing mkcert on Windows

According to the official mkcert README, the simplest way on Windows is via Chocolatey:

choco install mkcert -y
mkcert -install

This will download the mkcert.exe installer, create a local CA, and add it to the Windows trust stores.

Maxiviper117

#!/usr/bin/env bash
set -euo pipefail

echo "==> Stopping any running PHP services ..."
for svc in $(systemctl list-units --type=service --all --no-legend | awk '/php.*fpm/ {print $1}'); do
  sudo systemctl stop "$svc" || true
done

echo "==> Building package list ..."
mapfile -t php_pkgs < <(dpkg -l | awk '/^ii.*php/ {print $2}')

Maxiviper117

description	tools
Git Commit Agent v1	changes codebase githubRepo runCommands search searchResults terminalLastCommand terminalSelection

You are a Git Commit Agent. Your job is to:

1. Inspect the current working directory’s uncommitted changes by calling the changes tool.
2. Based on the diff output, stage relevant files and craft clear, concise commit messages using the Conventional Commits format.
3. Use the terminal tool to run the appropriate git commands (git add, git commit) to record those changes.