new instruction use-cliche-data-in-docs.instructions

[jhauga]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services.
• My contribution adds a new instruction, prompt, agent, skill, or workflow file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, or workflow with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the staged branch for this pull request.

---

Description

Tested an initial version of the instructions on a repo I pretty much vibe-coded using real data in order to live test and make sure features worked correctly. The repo is extractEmail. I made the instructions because Copilot kept putting examples from the prompt into the documentation. Some of which were not good for documentation. Others examples had sensitive information. Even after ending with something like "And DO NOT put this example data in the documentation".

So, I made an initial draft. It worked good. Polished everything, and now I'm here.

The test for the updated instruction was to create a tool using real example data, and make sure the documentation did not include it. In short - it worked. For the full test results ctrl + click support-repo.

• Agent: Local
• Model: GPT-5.4
• Number of Prompts: 1
• Post Edits: none

Prompt

Make a command-line tool that will stylistically output the content of a data
file. Call it `versal.py`. Use python. The main goal is for every new
paragraph, or section of data following a blank line, then the first character
should be Versal or a sytled raised capital. For example, using the file
"NewYork-NewYork.txt" and looking at the first two paragraphs of the story; the
Versal output would be like:

     ```bash
     |\=======/|
     ||  ---  ||  
     || || |\ ||
     || || || || 
     || || || ||
     ||  ---  ||
     |/=======\|pening Scene: "New York, New York"
     As the young man prepares ...

     ||\======/|
     ||  ==== ||  
     || ||    ||
     ||   ==  || 
     ||     | ||
     || ===== ||
     |/=======\|cene 1: "Luck Be a Lady"
     The young man arrives in ...

     ```

Create the command-line patterns for the Versal characters, and provide several
options for customizing the character. For example

     ```bash
     versal --no-border file.ext
     ```

Create documentation file called `versal.md` with:

- Install instructions
- List of options
- Use examples
- License MIT

Results

Good. A fun little command-line tool that does versal lettering, and used cliche data for documentation, and not data from prompt.

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• Update to existing instruction, prompt, agent, plugin, skill, or workflow.
• Other (please specify):

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

[Copilot]

Pull request overview

Adds a new Copilot instruction aimed at preventing documentation from leaking real/sensitive data by requiring generic placeholder (“cliche”) example values.

Changes:

• Introduces use-cliche-data-in-docs.instructions.md with rules and examples for substituting real data with safe placeholders in docs.
• Registers the new instruction in docs/README.instructions.md for discovery and installation.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
instructions/use-cliche-data-in-docs.instructions.md	New instruction defining a strict boundary between implementation data and documentation examples, with approved placeholder patterns.
docs/README.instructions.md	Adds the instruction to the documented catalog with install links and a short description.