awesome-copilot-adventures
Copilot instructions1 starsChanged 2 months agoMITView on GitHub
This repository is an educational curriculum for agentic development with GitHub Copilot. Each adventure must include metadata, official references, story, objectives, prerequisites, concepts, Ask → Plan → Agent workflow, guided mission, intentional failure, independent challenge, evidence checklist, reset instructions, and a rubric. - Use “Model Context Protocol,” never “Model Control Protocol.” - Use .agent.md for custom agents; do not teach deprecated custom chat modes. - Mark hooks, memory, or experimental features with their documented status. - Do not state that…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- workshop-gbb/awesome-copilot-adventuresword for word, first seen Sep 5, 2026
Other versions1 project uses a version of this.
Word for word · 1
- workshop-gbb/awesome-copilot-adventures★ 1100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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 2,336 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- canvas-designSkill
- evidence-firstSkill
- frontend-dashboard-visualizationSkill
- frontend-experience-coreSkill
- frontend-form-interactionsSkill
- frontend-mobile-desktop-testingSkill
- frontend-requirements-and-storiesSkill
- frontend-visual-e2e-testingSkill
- frontend-visual-systemSkill
- ms-presentation-deckSkill
- official-docsSkill
- web-design-reviewerSkill
The file
Show its rules and text
We split this copilot-instructions.md into the rules it gives an agent
13 rules. About 0 are common, 5 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
8
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
- Very specific: line 14
Write current adventures in adventures/<level>/<slug>/.
- Very specific: line 15
Put executable starters in labs/<slug>/.
- Very specific: line 16
Put current site pages in docs/.
- Very specific: line 17
Keep numbered hands-on exercises and their fixtures in mslearn-github-copilot/.
- Very specific: line 18
Put generated media in assets/.
- Very specific: line 19
Treat legacy/ as read-only historical material unless the task explicitly targets it.
- Distinctive: line 27
Use “Model Context Protocol,” never “Model Control Protocol.”
- Very specific: line 28
Use .agent.md for custom agents.
- Distinctive: line 30
Do not state that a tool, model, or target is universally available.
- Distinctive: line 31
Do not claim performance or productivity improvements without executed evidence.
- Distinctive: line 32
Never commit secrets or real API keys.
- Distinctive: line 33
Use the canonical monochrome palette, accessible title/description, legend and explanation for every Mermaid diagram.
- Very specific: line 38
Run npm test after documentation or JavaScript changes.
≈ “Common” is an estimate: at least 1 in 5 of the 3,779 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
This repository is an educational curriculum for agentic development with GitHub Copilot.
Priorities
- Technical accuracy against current official GitHub and Microsoft documentation.
- Reproducible learning with observable evidence.
- Clear separation of role, harness, execution environment, and customization primitive.
- Accessible fantasy storytelling that supports rather than obscures the lesson.
Structure
- Write current adventures in
adventures/<level>/<slug>/. - Put executable starters in
labs/<slug>/. - Put current site pages in
docs/. - Keep numbered hands-on exercises and their fixtures in
mslearn-github-copilot/. - Put generated media in
assets/. - Treat
legacy/as read-only historical material unless the task explicitly targets it.
Adventure format
Each adventure must include metadata, official references, story, objectives, prerequisites, concepts, Ask → Plan → Agent workflow, guided mission, intentional failure, independent challenge, evidence checklist, reset instructions, and a rubric.
Guardrails
- Use “Model Context Protocol,” never “Model Control Protocol.”
- Use
.agent.mdfor custom agents; do not teach deprecated custom chat modes. - Mark hooks, memory, or experimental features with their documented status.
- Do not state that a tool, model, or target is universally available.
- Do not claim performance or productivity improvements without executed evidence.
- Never commit secrets or real API keys.
- Use the canonical monochrome palette, accessible title/description, legend and explanation for every Mermaid diagram. Do not add fantasy stories to the hands-on track.
Validation
Run npm test after documentation or JavaScript changes. Run the targeted language build/test when changing a solution.
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.