MicrosoftKnown publishermicrosoft/frontier-ghcp-ttt-rvas/sessions/session-m3-02-cloud-agent/lab/starter/copilot-instructions.mdfrontier-ghcp-ttt-rvas / starter
Copilot instructions3 starsChanged 54 days agoMITView on GitHub
This synthetic Node.js 20 project exposes an in-memory task API with Express. Tests use Jest and Supertest. Report the command result accurately. Stop and ask for clarification if the issue requires work outside this scope.
We split this copilot-instructions.md into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 12
Keep the existing priority behavior.
- Very specific: line 18
Use the existing error response shape: { "error": "<message>" }.
- Distinctive: line 19
Use synthetic data only.
- Distinctive: line 20
Never add credentials or external service calls.
≈ “Common” is an estimate: at least 1 in 5 of the 3,669 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Repository Instructions
Project
This synthetic Node.js 20 project exposes an in-memory task API with Express. Tests use Jest and Supertest.
Scope for the training issue
- Change only
src/app.jsandtests/app.test.js. - Reject missing, empty, or whitespace-only task titles.
- Preserve the existing response shape for valid task creation.
- Keep the existing priority behavior.
Constraints
- Add no dependency.
- Change no other endpoint.
- Use the existing error response shape:
{ "error": "<message>" }. - Use synthetic data only.
- Never add credentials or external service calls.
Validation
Run:
npm testReport the command result accurately. Stop and ask for clarification if the issue requires work outside this scope.
Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.
Of the Copilot instructions files we read, the 2,297 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- sessions/session-m2-03-spaces-and-context/lab/solution/ecommerce-project/.github/copilot-instructions.mdCopilot instructions
- sessions/session-m2-03-spaces-and-context/lab/solution/instructions-lab/.github/copilot-instructions.mdCopilot instructions
- sessions/session-m5-03-hve-core-challenge/lab/solution/decision-api/.github/copilot-instructions.mdCopilot instructions
- baoyu-infographicSkill
- diagram-creatorSkill
- docxSkill
- excalidraw-diagramSkill
- humanize-contentSkill
- impeccableSkill
- pdfSkill
- pptxSkill
- rvap-brandSkill
- skill-creatorSkill
- xlsxSkill
- impeccableSkill
- session-format-validatorSkill
- deploymentSkill
- api-designSkill
- grillingSkill
- grill-meSkill
- deploymentSkill
- replace-with-directory-nameSkill
- decision-interviewSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.