Make AskUserQuestion instruction more imperative for Claude Code

Changed from passive "use the AskUserQuestion tool" to imperative
"STOP and call the AskUserQuestion tool" to ensure Claude actually
asks clarifying questions when context is missing.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.claude/commands/teach-impeccable.md

@@ -20,7 +20,7 @@ Note what you've learned and what remains unclear.
 
 ## Step 2: Ask UX-Focused Questions
 
-use the AskUserQuestion tool to clarify what you cannot infer. Focus only on what you couldn't infer from the codebase:
+STOP and call the AskUserQuestion tool to clarify. Focus only on what you couldn't infer from the codebase:
 
 ### Users & Purpose
 - Who uses this? What's their context when using it?

.claude/skills/frontend-design/SKILL.md

@@ -8,7 +8,7 @@ This skill guides creation of distinctive, production-grade frontend interfaces
 
 ## Design Thinking
 
-Great design requires understanding. First, scan available context—README, existing components, brand guidelines, design tokens—to infer purpose, audience, and constraints. If critical context is missing, use the AskUserQuestion tool to clarify what you cannot infer. Don't guess on fundamentals.
+Great design requires understanding. First, scan available context—README, existing components, brand guidelines, design tokens—to infer purpose, audience, and constraints. If critical context is missing, STOP and call the AskUserQuestion tool to clarify. Don't guess on fundamentals.
 
 Then commit to a BOLD aesthetic direction:
 - **Purpose**: What problem does this interface solve? Who uses it?

dist/claude-code-prefixed/.claude/commands/i-teach-impeccable.md

@@ -20,7 +20,7 @@ Note what you've learned and what remains unclear.
 
 ## Step 2: Ask UX-Focused Questions
 
-use the AskUserQuestion tool to clarify what you cannot infer. Focus only on what you couldn't infer from the codebase:
+STOP and call the AskUserQuestion tool to clarify. Focus only on what you couldn't infer from the codebase:
 
 ### Users & Purpose
 - Who uses this? What's their context when using it?

dist/claude-code-prefixed/.claude/skills/frontend-design/SKILL.md

@@ -8,7 +8,7 @@ This skill guides creation of distinctive, production-grade frontend interfaces
 
 ## Design Thinking
 
-Great design requires understanding. First, scan available context—README, existing components, brand guidelines, design tokens—to infer purpose, audience, and constraints. If critical context is missing, use the AskUserQuestion tool to clarify what you cannot infer. Don't guess on fundamentals.
+Great design requires understanding. First, scan available context—README, existing components, brand guidelines, design tokens—to infer purpose, audience, and constraints. If critical context is missing, STOP and call the AskUserQuestion tool to clarify. Don't guess on fundamentals.
 
 Then commit to a BOLD aesthetic direction:
 - **Purpose**: What problem does this interface solve? Who uses it?

dist/claude-code/.claude/commands/teach-impeccable.md

@@ -20,7 +20,7 @@ Note what you've learned and what remains unclear.
 
 ## Step 2: Ask UX-Focused Questions
 
-use the AskUserQuestion tool to clarify what you cannot infer. Focus only on what you couldn't infer from the codebase:
+STOP and call the AskUserQuestion tool to clarify. Focus only on what you couldn't infer from the codebase:
 
 ### Users & Purpose
 - Who uses this? What's their context when using it?

dist/claude-code/.claude/skills/frontend-design/SKILL.md

@@ -8,7 +8,7 @@ This skill guides creation of distinctive, production-grade frontend interfaces
 
 ## Design Thinking
 
-Great design requires understanding. First, scan available context—README, existing components, brand guidelines, design tokens—to infer purpose, audience, and constraints. If critical context is missing, use the AskUserQuestion tool to clarify what you cannot infer. Don't guess on fundamentals.
+Great design requires understanding. First, scan available context—README, existing components, brand guidelines, design tokens—to infer purpose, audience, and constraints. If critical context is missing, STOP and call the AskUserQuestion tool to clarify. Don't guess on fundamentals.
 
 Then commit to a BOLD aesthetic direction:
 - **Purpose**: What problem does this interface solve? Who uses it?

scripts/lib/utils.js

@@ -301,7 +301,7 @@ export const PROVIDER_PLACEHOLDERS = {
   'claude-code': {
     model: 'Claude',
     config_file: 'CLAUDE.md',
-    ask_instruction: 'use the AskUserQuestion tool to clarify what you cannot infer.'
+    ask_instruction: 'STOP and call the AskUserQuestion tool to clarify.'
   },
   'cursor': {
     model: 'the model',