GitHub Copilot Prompt for Correcting a Text

GitHub Copilot, GitHub's AI assistant integrated directly into your code editor, is not limited to code generation. It also excels at correcting and improving texts, whether for technical documentation, README files, code comments, or editorial content. By leveraging its language understanding capabilities, you can entrust it with proofreading your texts to identify and correct spelling, grammar, syntax, and style errors. This approach is particularly valuable for developers writing multilingual documentation or clear commit messages. Instead of switching to an external tool, you stay in your usual working environment, streamlining your workflow. The prompt we offer here is structured to guide Copilot precisely: it defines the expected role, the type of corrections desired, and the output format, ensuring consistent and actionable results every time.

The prompt

GitHub Copilot

Act as a professional francophone proofreader. Analyze the following text and correct all spelling, grammar, conjugation, punctuation, and syntax errors. Preserve the original meaning, tone, and style of the author. For each correction made, add a brief comment in brackets explaining the nature of the error. First return the corrected text in its entirety, then a summary list of the modifications made. Text to correct:

[PASTE_YOUR_TEXT_HERE]

Personalize this prompt with Léa

Answer 3 questions and Léa tailors the prompt to your situation.

Why it works

This prompt works because of the explicit assignment of an expert role (professional proofreader), which guides the model towards a rigorous linguistic register. The exhaustive list of error types to target avoids omissions, while the request for comments in brackets forces a reflective analysis that improves correction accuracy. The dual output format (corrected text + summary) allows for quick verification without rereading the entire document.

Expected result

You will get a clean, corrected version of your text, faithful to the original style and tone, accompanied by inline annotations indicating each change. A summary at the end of the response will list all corrections with their justification, allowing you to learn from your recurring mistakes and validate each change at a glance.

Variants by level

FAQ

Can GitHub Copilot correct texts in languages other than French?

Yes, GitHub Copilot effectively handles correction in most European languages as well as Chinese, Japanese, and Korean. Simply adapt the prompt by specifying the target language. However, its performance is optimal in English and French, the languages on which its model has been most trained. For less represented languages, it is recommended to check the corrections with a native speaker.

Does Copilot respect the style and tone of my original text when correcting?

When the prompt explicitly specifies it — as in our main version with the instruction "preserve the author's tone and style" — Copilot strives to maintain the original voice of the text. Without this instruction, it may tend to rephrase certain passages in a more neutral style. For texts with a very marked tone (humorous, literary, technical), specify the expected register in your prompt for better results.

What is the maximum text length I can have corrected at once?

The limit depends on the context window of the model used by Copilot. In practice, you can handle texts of 2,000 to 4,000 words in a single pass via Copilot Chat. For longer documents, it is better to split the text into logical sections (chapters, thematic paragraphs) and submit them separately. This ensures better correction quality as the model can fully focus on each segment.

How to use this prompt

Copy the prompt with the button above.
Paste it into ChatGPT, Claude or your favorite AI assistant.
Replace the bracketed variables with your details, then refine the result.

About Prompt Guide

Prompt Guide is a free library of 2500+ ready-to-use prompts for ChatGPT, Claude and other AIs, with guides to learn prompting and tools to build and optimize your own prompts.

Prompt library Learn prompting Prompt builder Prompt optimizer

Already have a prompt?

Paste it into the Optimizer, AI improves it in 5 seconds: role, context, format. Free, no signup.

Open the Optimizer

More prompts to explore

GitHub Copilot Prompt for Creating a Content Strategy

GitHub Copilot, initially designed as a development assistant, proves to be a formidable ally for creating content strategies. Thanks to its ability to understand complex instructions and generate structured text directly in your code editor, it allows marketers and content creators to design comprehensive editorial plans without leaving their work environment.

GitHub Copilot Prompt for Creating a Sales Funnel

GitHub Copilot, the AI-powered coding assistant, is not limited to writing functions or unit tests. Used with the right prompts, it becomes a formidable ally to build a complete sales funnel directly in your code editor. Whether you are developing a landing page, an email capture form, a payment page sequence, or an automated follow-up system, Copilot can generate the HTML, CSS, JavaScript, and backend code needed for each stage of the funnel. The major advantage lies in execution speed: where a developer would spend hours wiring funnel components, Copilot produces functional structures in minutes. By combining precise instructions on the funnel architecture with details about your offer and target audience, you get clean, responsive, and conversion-optimized code. This guide offers you a main prompt as well as variants tailored to your technical level to create a high-performance sales funnel with GitHub Copilot, from the opt-in form to the order confirmation page.

GitHub Copilot Prompt for Creating an Ad Script

GitHub Copilot, GitHub's AI-powered coding assistant, is not limited to code generation. Thanks to its natural language understanding capabilities, it can be creatively repurposed to produce structured and impactful ad scripts.

GitHub Copilot Prompt for Creating an Email Campaign

GitHub Copilot, GitHub's AI-powered coding assistant, is not limited to writing code. Used intelligently, it becomes a formidable ally

GitHub Copilot Prompt for Creating E2E Tests

End-to-end (E2E) tests are essential for validating the overall functionality of an application, but writing them is often time-consuming and repetitive.

GitHub Copilot Prompt for Creating Illustrations

GitHub Copilot, initially designed as a programming assistant, proves to be a remarkable tool for generating code to create illustrations