News

Microsoft Shares Copilot Prompts in New GitHub Repo (Contributions Welcomed)

Remember when "prompt engineer" job posts were listing salaries north of $300,000? Much has changed since then, and the "engineer" aspect has dimmed, with prompting advice, tools and resources freely available and abundant.

Microsoft has taken a step further in democratizing the prompt engineering field by sharing a collection of prompts for its various Copilots in a new GitHub repository. It's community-led and contributions are welcome, though you should be comfortable with your forking, branching, cloning and such.

Here's one example:

Find Meeting Time with Another User
[Click on image for larger view.] Find Meeting Time with Another User (source: Microsoft).

The Copilot prompts repo was announced today (May 14), starting with 11 samples, in which meetings is a dominant theme (Microsoft Teams, anyone?). The other 10 samples (conveniently in the samples folder) are as follows at the time of this writing:

  • Generate adaptive card using GitHub Copilot
    Generate Adaptive Card Using GitHub Copilot in Animated Action
    [Click on image for larger, animated GIF view.] Generate Adaptive Card Using GitHub Copilot in Animated Action (source: Microsoft).
  • Locate unresponded meeting invitations
  • Create meeting action items
  • List meeting invitees for a meeting distinguishing internal and external invitees
  • Locate my name mentioned in meetings
  • Post meeting summary
  • Summarize chat group discussions
  • Create a Timeline of My Upcoming Meetings
  • Create Annual Sales Report template
  • Create an welcome slide to existing PowerPoint presentation

"This repo is a collection of prompts that will help you use the power of Microsoft Copilot across various application from Word to PowerPoint to Microsoft Teams, and more!" said Microsoft's Rabia Williams in the announcement. "This new GitHub repository is more than just a collection of prompts, it is there to get you ahead in the AI revolution. By contributing and utilizing these prompts, we can all push the boundaries of what's possible with Copilot. "

The repo invites contributions for great sample prompts for Microsoft Copilot, GitHub Copilot or Microsoft Copilot for Microsoft 365.

As noted, being familiar with GitHub repos helps enormously here, as Williams detailed this process for contributing your own prompts:

  • Fork the repository: Go to the repository and select the Fork button to create your own copy.
  • Create a new branch: Clone your forked repository and create a new branch with a unique name that reflects your prompt's purpose.
  • Add a new folder: Inside the samples folder, create a new folder following the naming convention: <apphost-functionality-prompt>. For example, if you're creating a prompt for a PowerPoint sales report, name it ppt-sales-report-prompt.
  • Prepare the readme file: Find an existing readme.md file in any sample folder. Copy it into the new folder you created in the step above and update the contents in the file to describe your prompt.
  • Create an assets folder: Within your new folder, add a subfolder named assets. This is where you'll store any images or GIF files that your readme file refers to.
  • Copy the sample JSON file: Locate the sample.json file in any existing sample's assets folder. Copy this file into your own assets folder.
  • Update the JSON file: Modify the sample.json file in your assets folder to match the details of your prompt.

Williams further advised community contributors to create a pull request from their forked repos' new branch to the upstream repository's main branch so their prompts can be reviewed and approved by the community.

Would-be prompt contributors daunted by all of the above can also just open an issue and post an image and prompt, after which someone from the community can take care of putting it in the repo, providing full credit to the author.

About the Author

David Ramel is an editor and writer at Converge 360.

comments powered by Disqus

Featured

  • Compare New GitHub Copilot Free Plan for Visual Studio/VS Code to Paid Plans

    The free plan restricts the number of completions, chat requests and access to AI models, being suitable for occasional users and small projects.

  • Diving Deep into .NET MAUI

    Ever since someone figured out that fiddling bits results in source code, developers have sought one codebase for all types of apps on all platforms, with Microsoft's latest attempt to further that effort being .NET MAUI.

  • Copilot AI Boosts Abound in New VS Code v1.96

    Microsoft improved on its new "Copilot Edit" functionality in the latest release of Visual Studio Code, v1.96, its open-source based code editor that has become the most popular in the world according to many surveys.

  • AdaBoost Regression Using C#

    Dr. James McCaffrey from Microsoft Research presents a complete end-to-end demonstration of the AdaBoost.R2 algorithm for regression problems (where the goal is to predict a single numeric value). The implementation follows the original source research paper closely, so you can use it as a guide for customization for specific scenarios.

  • Versioning and Documenting ASP.NET Core Services

    Building an API with ASP.NET Core is only half the job. If your API is going to live more than one release cycle, you're going to need to version it. If you have other people building clients for it, you're going to need to document it.

Subscribe on YouTube