copilot-kit: Instructions file for GitHub Copilot

XML-like Tags for AI-Consumed Content

Markdown files in .github/agents/, .github/skills/, .github/prompts/, and .github/instructions/ are consumed primarily by AI agents, not humans. Standard Markdown conveys structure (headers, lists, tables) but not content type — the agent can't reliably distinguish "follow this instruction" from "output this template" from "learn from this example."

XML-like tags solve this by wrapping content blocks with explicit semantic boundaries. They tell the agent what kind of content a block is and how to process it.

When to Use Tags

Use XML-like tags when Markdown alone creates ambiguity about content type. Specifically:

• Templates vs instructions — Is a code block something to fill in and output, or an example to learn from? Wrap it in <template> or <example>.
• Hard rules vs advisory guidance — Are these bullet points non-negotiable constraints or suggestions? Wrap them in <rules> or <best-practices>.
• Agent content vs user content — Should the agent process this internally or display it verbatim? Wrap user-facing output in <user-message>.
• Action items vs reference material — Should the agent iterate through a checklist or read it for context? Wrap checklists in <validation> or <questions>.

Do not use tags when Markdown is unambiguous on its own — explanatory prose, section introductions, and standard tables don't need wrapping.

Tag Vocabulary

Every tag below is part of the standard vocabulary. Use these exact tag names — do not invent one-off tags.

Action Tags (agent should DO something with this content)

Tag	Purpose	Agent action
<questions>	Interview questions to ask the user before proceeding	Iterate through and ask each question
<validation>	Checklist to verify before reporting completion	Iterate through every item and confirm
<context-gathering>	Steps for scanning workspace/environment before acting	Execute each scan step in order