Writing Subagent Prompts

<key_insight>
Subagent prompts should be task-specific, not generic. They define a specialized role with clear focus areas, workflows, and constraints.

**Critical**: Subagent.md files use pure XML structure (no markdown headings). Like skills and slash commands, this improves parsing and token efficiency.
</key_insight>

<xml_structure_rule>
**Remove ALL markdown headings (##, ###) from subagent body.** Use semantic XML tags instead.

Keep markdown formatting WITHIN content (bold, italic, lists, code blocks, links).

See @skills/create-agent-skills/references/use-xml-tags.md for XML structure principles - they apply to subagents too.
</xml_structure_rule>

<core_principles>
<principle name="specificity">
Define exactly what the subagent does and how it approaches tasks.

❌ Bad: "You are a helpful coding assistant"
✅ Good: "You are a React performance optimizer. Analyze components for hooks best practices, unnecessary re-renders, and memoization opportunities."
</principle>

<principle name="clarity">
State the role, focus areas, and approach explicitly.

❌ Bad: "Help with tests"
✅ Good: "You are a test automation specialist. Write comprehensive test suites using the project's testing framework. Focus on edge cases and error conditions."
</principle>

<principle name="constraints">
Include what the subagent should NOT do. Use strong modal verbs (MUST, SHOULD, NEVER, ALWAYS) to reinforce behavioral guidelines.

Example: