docs: Update examples to show Claude as primary driver with Gemini validation

- Replaced generic examples with Claude-driven workflows
- Added examples showing Claude's extended thinking validated by Gemini
- Emphasized the feedback loop: Claude designs → Gemini validates → Claude refines
- Added real-world example flow for microservices architecture
- Updated best practices to position Claude as the primary thinker
- Made it clear that Gemini is for validation, edge cases, and extended context

This better reflects the intended usage pattern where Claude Code does the
heavy lifting and Gemini provides additional validation and context.

README.md

@@ -180,14 +180,14 @@ Be specific about what you want from Gemini:
 
 ### Common Workflows
 
-#### 1. **Extended Code Review**
+#### 1. **Claude's Extended Thinking + Gemini Validation**
 ```
-You: "Implement feature X"
+You: "Design a distributed task queue system"
-Claude: [implements]
+Claude: [provides detailed architecture and implementation plan]
-You: "Use Gemini to review this implementation for scalability issues"
+You: "Share your complete design with Gemini and ask it to identify potential race conditions or failure modes"
-Gemini: [provides detailed feedback]
+Gemini: [analyzes and finds edge cases]
-You: "Based on Gemini's feedback, improve the implementation"
+You: "Address the issues Gemini found"
-Claude: [refines based on feedback]
+Claude: [updates design with safeguards]
 ```
 
 #### 2. **Large File Analysis**
@@ -204,11 +204,16 @@ Claude: [refines based on feedback]
 "Ask Gemini to find all circular dependencies in /src"
 ```
 
-#### 4. **Second Opinion & Validation**
+#### 4. **Claude-Driven Design with Gemini Validation**
 ```
-"I'm planning to refactor using pattern X. Ask Gemini for potential issues"
+Claude: "I've designed a caching strategy using Redis with TTL-based expiration..."
-"Use Gemini to validate my database schema design"
+You: "Share my caching design with Gemini and ask for edge cases I might have missed"
-"Have Gemini suggest alternative approaches to this algorithm"
+
+Claude: "Here's my implementation plan for the authentication system: [detailed plan]"
+You: "Use Gemini to analyze this plan and identify security vulnerabilities or scalability issues"
+
+Claude: "I'm thinking of using this approach for the data pipeline: [approach details]"
+You: "Have Gemini review my approach and check these 10 files for compatibility issues"
 ```
 
 #### 5. **Security & Performance Audits**
@@ -219,10 +224,25 @@ Claude: [refines based on feedback]
 ```
 
 ### Best Practices
-- Use Gemini when you need analysis beyond Claude's context window
+- Let Claude do the primary thinking and design work
-- Leverage Gemini's 1M token limit for whole-codebase analysis
+- Use Gemini as a validation layer for edge cases and extended context
-- Combine both assistants: Claude for implementation, Gemini for review
+- Share Claude's complete thoughts with Gemini for comprehensive review
-- Be specific in your requests for more accurate responses
+- Have Gemini analyze files that are too large for Claude
+- Use the feedback loop: Claude designs → Gemini validates → Claude refines
+
+### Real-World Example Flow
+```
+1. You: "Create a microservices architecture for our e-commerce platform"
+2. Claude: [Designs comprehensive architecture with service boundaries, APIs, data flow]
+3. You: "Take my complete architecture design and have Gemini analyze it for:
+   - Potential bottlenecks
+   - Missing error handling
+   - Security vulnerabilities
+   - Scalability concerns"
+4. Gemini: [Provides detailed analysis with specific concerns]
+5. You: "Based on Gemini's analysis, update the architecture"
+6. Claude: [Refines design addressing all concerns]
+```
 
 ## 📝 Notes