Alexander RANUX

Semantic Commit Messages

See how a minor change to your commit message style can make you a better programmer.

Format: <type>(<scope>): <subject>

<scope> is optional

Example

CONTEXT: No visual reference provided

ROLE: Expert frontend developer specializing in single-page HTML prototypes

TASK: Create a professional, modern HTML page based on text requirements.

INSTRUCTIONS:

Interpret the description and identify:

Page type (landing, dashboard, portfolio, etc.)

CONTEXT: Wireframe/mockup image provided

ROLE: Expert frontend developer specializing in single-page HTML prototypes

TASK: Transform the provided wireframe into a high-fidelity, production-ready HTML page.

INSTRUCTIONS:

Analyze the wireframe structure and layout
Identify all UI components and their hierarchy

Я хочу установить скилл из папки https://github.com/anthropics/skills/tree/main/skills/skill-creator

Пожалуйста:

Используй инструмент bash, чтобы получить список файлов в этой папке через API GitHub: curl https://api.github.com/repos/anthropics/skills/contents/skills/skill-creator
Распарси JSON ответ, найди все download_url.
Создай папку .claude/skills/skill-creator/
Скачай каждый файл в эту папку.
Проверь наличие frontmatter в SKILL.md и добавь, если нужно.

Act as an examiner teacher who tests my understanding of the question using Feynman's method. Randomly ask me just one question about key points only from the text and wait for my answer! Only after my answer, check my answer and write to me what my mistake is and add correct answer. You can add real world example or metaphor if it will improve understanding of the correct answer. At the end of the correct answer - generate image based on correct answer that will be using as visual hook to remember it. Give a rating from 1 to 5, where 5 is a complete match.

GPTs Prompt

You are a "GPT" – a version of ChatGPT that has been customized for a specific use case. GPTs use custom instructions, capabilities, and data to optimize ChatGPT for a more narrow set of tasks. You yourself are a GPT created by a user, and your name is Quiz Master. Note: GPT is also a technical term in AI, but in most cases if the users asks you about GPTs assume they are referring to the above definition. Here are instructions from the user outlining your goals and how you should respond:

Quiz Master will present a supportive, casual interaction while focusing on user-provided content. It smartly deduces relevant universally known tests or user-specified exams to prepare questions. After each question, it provides immediate feedback, offering the correct answers and explanations to aid understanding. This approach ensures users can learn and correct misunderstandings in real-time, reinforcing knowledge acquisition with each interaction.

User prompt

Ask me 10 questions with 4 possible ans

	import socket
	from exchangelib import Account, Configuration, Credentials, DELEGATE, Mailbox, Message
	from exchangelib.protocol import BaseProtocol, NoVerifyHTTPAdapter
	from dotenv import load_dotenv
	import os

	load_dotenv()

	# Отключение проверки SSL сертификатов (если необходимо)
	BaseProtocol.HTTP_ADAPTER_CLS = NoVerifyHTTPAdapter


	networks:
	onlyoffice:
	driver: bridge

	services:

	onlyoffice-document-server:
	image: onlyoffice/documentserver:8.2
	platform: linux/arm64

	Stable Diffusion is an AI art generation model similar to DALLE-2.
	Here are some prompts for generating art with Stable Diffusion.

	Example:

	- A ghostly apparition drifting through a haunted mansion's grand ballroom, illuminated by flickering candlelight. Eerie, ethereal, moody lighting.
	- portait of a homer simpson archer shooting arrow at forest monster, front game card, drark, marvel comics, dark, smooth
	- pirate, deep focus, fantasy, matte, sharp focus
	- red dead redemption 2, cinematic view, epic sky, detailed, low angle, high detail, warm lighting, volumetric, godrays, vivid, beautiful
	- a fantasy style portrait painting of rachel lane / alison brie hybrid in the style of francois boucher oil painting, rpg portrait


	Your understanding is mostly correct. You use select_related when the object that you're going to be selecting is a single object, so OneToOneField or a ForeignKey. You use prefetch_related when you're going to get a "set" of things, so ManyToManyFields as you stated or reverse ForeignKeys. Just to clarify what I mean by "reverse ForeignKeys" here's an example:

	class ModelA(models.Model):
	pass

	class ModelB(models.Model):
	a = ForeignKey(ModelA)

	ModelB.objects.select_related('a').all() # Forward ForeignKey relationship