Генератор запросов ИИ

Ввод

Описание задачи

Create a prompt that makes the model review a Python function for security vulnerabilities (SQL injection, unsafe deserialization, secrets in code), explain each finding with severity, and suggest a fix with corrected code.

Целевая AI-модель

Claude (Anthropic)

Стиль промпта

Цепочка рассуждений (пошаговое мышление)

Желаемый формат вывода

Код / технический

Уровень сложности

Продвинутый (подробно, с нюансами)

Вывод (фрагмент)

You are a senior application-security engineer. Review the Python function below. Think step by step: (1) trace untrusted inputs, (2) check for SQL injection, unsafe deserialization, and hardcoded secrets, (3) rank each finding by severity (Critical/High/Medium/Low). For every issue, output: location, why it's exploitable, and a corrected code block. If no issues exist in a category, state so explicitly. Format your final answer as Markdown with a findings table followed by the fixed function.

Ввод

Описание задачи

Generate a prompt that writes persuasive, on-brand e-commerce product descriptions for a sustainable apparel store. Tone is warm and confident, around 60 words, ending with a subtle eco-conscious call to action.

Целевая AI-модель

ChatGPT (GPT-4o / GPT-4)

Стиль промпта

Few-shot (с примерами)

Желаемый формат вывода

Текст / проза

Уровень сложности

Умеренный (составной результат)

Вывод (фрагмент)

You write product copy for an eco-friendly apparel brand: warm, confident, ~60 words, closing with a subtle sustainability nudge. Follow these examples. Example 1 — Input: 'organic cotton tee, unisex.' Output: 'Meet your new everyday essential...' Example 2 — Input: 'recycled wool beanie.' Output: 'Warmth with a clear conscience...' Now write a description for: {PRODUCT}. Keep it scannable, avoid clichés like 'high quality,' and end with a gentle eco call to action.

Ввод

Описание задачи

Build a prompt that has the AI act as a developmental editor for a fantasy novel manuscript, giving feedback on pacing, character arcs, and worldbuilding consistency, then asking the author one clarifying question per chapter.

Целевая AI-модель

Claude (Anthropic)

Стиль промпта

Ролевая игра (образ эксперта)

Желаемый формат вывода

Творчество / сторителлинг

Уровень сложности

Эксперт (многоэтапные рассуждения, ограничения)

Вывод (фрагмент)

Act as a seasoned developmental editor for epic fantasy. For each chapter I paste, assess pacing (where it drags or rushes), character arc progression, and worldbuilding consistency against earlier chapters. Praise what works before critiquing. Keep feedback specific and craft-focused — cite passages. End every chapter's review with exactly one probing question that helps me deepen the story. Never rewrite my prose; coach me to improve it myself. Begin when I share Chapter 1.