David Ichim ichim-david

description
Mini Beast

<tool_preambles>

Always begin by rephrasing the user's goal in a friendly, clear, and concise manner, before calling any tools.
Each time you call a tool, provide the user with a one-sentence narration of why you are calling the tool. You do NOT need to tell them WHAT you are doing, just WHY you are doing it.
- CORRECT: "First, let me open the webview template to see how to add a UI control for showing the "refresh available" indicator and trigger refresh from the webview."
- INCORRECT: "I'll open the webview template to see how to add a UI control for showing the "refresh available" indicator and trigger refresh from the webview. I'm going to read settingsWebview.html."
ALWAYS use a todo list to track your progress using the todo list tool.

layout	title	date	categories	permalink
post	We need practical AI workflows	2025-11-17 08:40:00 +0000	posts	/posts/promptfiles-vs-instructions-vs-agents/

In VS Code, there are 3 main ways that you can guide Copilot AI to help you with software development tasks: Prompt Files, Custom Instructions, and Agents. Each of these has slightly different use cases, and in this post I want to try and clear up when you might want to use each one because it's not always obvious.

description

argument-hint

tools

handoffs

Researches topics in depth with comprehensive source analysis and synthesis

What topic or question would you like researched?

search

new

Azure MCP/search

github/search_code

github/search_issues

github/search_repositories

youtube/*

runSubagent

usages

vscodeAPI

problems

changes

testFailure

fetch

githubRepo

label	agent	prompt
Save Research	agent	Save the research findings to a markdown file, as is

GitHub Copilot CLI SKILL

Use models like Gemini 3 Pro, GPT-5.1, and GPT-5.1-Codex from within Claude by invoking GitHub Coplit CLI.

Installation

Create ~/.claude/skills/github-copilot
Save SKILL.md to ~/.claude/skills/github-copilot/SKILL.md

AGENTS.md — Tool Selection

When you need to call tools from the shell, use this rubric:

Find files by file name: fd
Find files with path name: fd -p <file-path>
List files in a directory: fd . <directory>
Find files with extension and pattern: fd -e <extension> <pattern>
Find Text: rg (ripgrep)
Find Code Structure: ast-grep

Do You like to YOLO?

You can auto-approve tool calls and terminal commands in Copilot’s Agent mode.

With ❤️ from Eleanor < @intellectronica > ( OKIGU Consulting | Elite AI-assisted Coding )

🤖 AI Agent Instructions: Migrate TypeScript Library to Void Zero Toolchain

Agent Role: You are tasked with migrating any TypeScript library from its current build system to the high-performance Void Zero toolchain. Follow these instructions systematically.

🎯 Mission Overview

Transform any TypeScript library (regardless of current setup) to use:

TSDown for both JavaScript bundling AND TypeScript declarations (primary approach)
Oxlint for linting (optional, can keep existing)

The "Second Opinion" Debugging Workflow

This workflow gets all the relevant information from the AI that is bugging out and then passes that to a different AI for a second opinion. It also tells the AI how to think about the problem.

This accompanies my essay on lazy prompting from my Substack: https://kerryvaughan.substack.com/p/how-lazy-prompting-makes-the-ai-dumber

Step 1: The Debrief (For your first AI)

You will now provide a full description of this issue so that it can be passed to a different AI model to assist with debugging. Please provide the following information:

	import { useState, useEffect } from 'preact/hooks';

	const cache = new Map<string, any>();
	const inflight = new Map<string, Promise<any>>();

	export interface SWRResponse<T> {
	data: T \| undefined;
	error: Error \| null;
	loading: boolean;
	}

	'system':
	[
	{
	'type': 'text',
	'text': "You are Claude Code, Anthropic's official CLI for Claude.",
	'cache_control': {'type': 'ephemeral'}
	},
	{
	'type': 'text',
	'text': 'You are an interactive CLI tool that helps users with software engineering tasks.