AI USE CASES YOU CAN REUSE.English edition · Individuals, independents, small businesses
Spotted on the web

Unlock tedious code migrations with an agent instructions file

Use described publicly by Blog de BlaBlaCar (26 December 2025), summarised by the desk. Not tested by iadujour.

The result to aim for

The BlaBlaCar front-end team entrusted the GitHub agent Copilot with repetitive code migrations that remained in plan, describing the task in a reusable prompt file.

What was done

According to an article published on 26 December 2025 on BlaBlaCar's blog, several necessary but boring migrations stagnated for lack of volunteers. The team tested the GitHub agent Copilot on two projects: replacing an old simulation solution from the API (low risk) and rewriting Selenium tests in Playwright (more delicate). After a successful manual trial on an example in VS Code, the task was described in a Copilot prompt file: role, context, precise steps (create branch, migrate file, delete old, declare new routes), search for examples in already labelled pull requests, instructions for shell commands, then create the pull request with a dedicated label. The article insists that the quality of the instructions and the examples condition the quality of the result, and describes a gradual increase in the responsibility entrusted to the agent. He announced that the first assisted migration had been completed.

Before you start

Tool cited by the source: GitHub Copilot. Gather the information the prompt asks for. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.

The method, in three steps.

  1. Gather the context

    Gather the information described in the prompt.

  2. Adapt the prompt

    Copy the prompt below, replace the bracketed items, then paste it into GitHub Copilot.

  3. Reread before using

    Reread the result, correct it if needed and keep the final decision. Caveats are detailed below.

Your starting point.

Replace the bracketed items, then adapt the proposal to your situation. This prompt is written by the iadujour desk It is not a quotation from the source.

The prompt to customise
Role: experienced engineer on
Context: we migrate
Task, for the file I'm telling you:
1. Creates a gird called
2. Migrate the file by inspired sweaters requests labeled
3. Remove the old file and update the references.
4. Opens a pull request with a short title and description.
Ask me for a check instead of running an order you're not sure about.

What deserves your attention

An automated migration remains a series of requests to read: ask the agent to request checks rather than execute any order, and keep the tests as judge.
Origin of the case. Use described publicly by Blog de BlaBlaCar (26 December 2025).
Proof level: Testimony published by an identified source. Source checked on 10 November 2026. Use described by the source, not tested by the desk. Original summary written by iadujour.fr: figures and claims are the source’s; the prompt is a desk proposal, not a quotation.

Useful skills

Official skills on the same task, paired by the desk: they are not part of the described case.

  • Build an application with SDK GitHub CopilotMicrosoft · Guides the creation of applications that rely on GitHub Copilot via the Copilot SDK, for programmatic integrations in Node.js/TypeScript, Python, Go or .NET: sessions, custom tools, streaming, hooks, MCP servers, BYOK providers, persistence, agents and skills, and deployment schemes.
TO GO FURTHER

Other ideas to put to work.

The whole Dev theme
Dev

Make a pull request by an agent before the human review

A first automated passage to identify probable bugs, missing tests and safety risks, so that the human review focuses on the essentials.

Tool: Claude CodeType: Practical case
DISCUSSION

Comments.

A field note, a question, a precision on this use case? Comments are reviewed before publication.

Published comments

Loading comments…

    Leave a comment

    Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.