GitHub Copilot Prompt: Generate a Review Plan
GitHub Copilot goes beyond code completion: it's an assistant capable of structuring comprehensive review plans for your software projects. Whether you are preparing a code review before deployment, a major refactoring, or a security audit, a well-crafted prompt enables Copilot to produce a methodical plan covering every critical aspect. The challenge is to provide enough context about your codebase, goals, and constraints so that the generated plan is actionable, not generic. A good review plan identifies risk areas, prioritizes checks, and proposes clear acceptance criteria. By using Copilot Chat in your IDE, you can quickly iterate on this plan by confronting it directly with the source code open in your editor. This approach transforms a often overlooked task—structured review planning—into a fast and reproducible process that improves overall code quality and reduces regressions in production.
Paste in your AI
Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.
Act as a senior lead developer specialized in code review. Generate a structured and exhaustive review plan for the following project:
Project Context: [describe the project, its tech stack and architecture]
Review Scope: [specify the files, modules or features concerned]
Main Objective: [e.g., pre-deployment, refactoring, security audit, onboarding]
Constraints: [deadline, reviewer experience level, internal standards]
The plan must include:
- A checklist prioritized by criticality (blocking / important / minor)
- Identified risk zones with justification
- Specific checks per layer (business logic, API, database, UI)
- Measurable acceptance criteria for each point
- A time estimate per section
- Recommended tools or commands to automate certain checks
Format the plan in Markdown with tables for the checklist and clearly separated sections.
Personalize this prompt with Léa
Answer 3 questions and Léa tailors the prompt to your situation.
Why this prompt works
This prompt works thanks to the attribution of an expert role that frames the response register, combined with contextual variables in brackets that force the user to provide discriminating information. The six-point numbered structure acts as a format constraint that prevents Copilot from producing a vague response, while the request for prioritization by criticality exploits the model's ability to classify and hierarchize information.
Use Cases
Variants
Expected Output
You will obtain a structured Markdown document containing a review checklist classified by criticality level, with for each point a precise acceptance criterion and a time estimate. The plan will also include an analysis of risk zones specific to your architecture, as well as concrete commands (linters, tests, verification SQL queries) to automate repetitive checks.
Frequently Asked Questions
How do I adapt this prompt for a project with a very large codebase?
For large codebases, break the review down by modules or business domains instead of including everything at once. In your prompt, specify the specific files or directories involved, and ask Copilot to generate a batch plan. You can also open the target files in your IDE before using Copilot Chat: it will factor in the context of open files to produce a more relevant plan. Remember to mention dependencies between modules so the plan reflects the optimal review order.
Can Copilot automatically detect risk areas in my code?
Copilot Chat can analyze the code open in your editor and identify problematic patterns (unparameterized SQL queries, missing error handling, outdated dependencies). However, it doesn't replace a dedicated static analysis tool like SonarQube or Semgrep. The recommended approach is to use the plan generated by Copilot as a structure, then supplement it with results from SAST tools for checks that can be automated. The advanced prompt actually includes recommendations for complementary tooling.
What is the difference between using this prompt in Copilot Chat versus a regular editor?
In Copilot Chat integrated into the IDE (VS Code, JetBrains), the model has access to the context of your open files and workspace, which makes the review plan much more specific. In an external chat without code context, the plan will remain more generic. For optimal results, open the key files within the review scope before launching the prompt, and use the @workspace command so that Copilot considers the whole project.
Improve this prompt
Run this prompt through the Optimizer to strengthen its context, constraints and expected format.
Improve this prompt with the OptimizerComments
- LéaAI
Pour un audit sécurité, ajoutez une section « vulnérabilités connues » basée sur l’OWASP Top 10, et demandez à Copilot de lier chaque point à un identifiant CWE. Cela renforce la traçabilité et facilite la relecture par l’équipe SecOps.
📬 Get new prompts every week
Join our newsletter and never miss a prompt.
Go further
Similar Prompts
Concept Explainer (Feynman Technique)
Understanding difficult concepts by simplifying them first
Peer Review Response Letter
Responding to peer review feedback
Sora Prompt for Creating a Training Program
Sora, the video generation model developed by OpenAI, opens up new possibilities for creating training programs. By combining precise textual instructions with Sora's visual capabilities, trainers and instructional designers can produce immersive content that captures learners' attention. Whether you are designing corporate training, an online course, or an onboarding program, Sora enables the generation of realistic educational videos illustrating scenarios, process demonstrations, or practical situations. The main challenge lies in the quality of the prompt: a well-structured prompt ensures videos that are coherent, professional, and perfectly aligned with your learning objectives. In this guide, you will discover a main prompt optimized for creating a complete training program with Sora, as well as variants adapted to different expertise levels. Each prompt is designed to maximize the relevance of the generated videos while respecting the fundamental principles of instructional design: logical progression, visual engagement, and clarity of message.
Level 3 Behavior Change Survey
Tracking on-the-job application of learning