boundary-bbcr-fallback
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Optimize build processes and speed
$ npx -y skills add qdhenry/Claude-Command-Suite --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/optimize-buildContext preview
What this command does when you run it.
Optimize build processes and speed
Optimize build processes and speed
Follow this systematic approach to optimize build performance: **$ARGUMENTS**
1. **Build System Analysis**
2. **Performance Baseline**
3. **Dependency Optimization**
4. **Caching Strategy**
5. **Bundle Analysis**
6. **Code Splitting and Lazy Loading**
7. **Asset Optimization**
8. **Development Build Optimization**
9. **Production Build Optimization**
10. **Parallel Processing**
11. **File System Optimization**
12. **CI/CD Build Optimization**
13. **Memory Usage Optimization**
14. **Output Optimization**
15. **Monitoring and Profiling**
16. **Tool-Specific Optimizations**
**For Webpack:**
**For Vite:**
**For TypeScript:**
17. **Environment-Specific Configuration**
18. **Testing Build Optimizations**
19. **Documentation and Maintenance**
Focus on the optimizations that provide the biggest impact for your specific project and team workflow. Always measure before and after to quantify improvements.
A comprehensive development toolkit designed following Anthropic's Claude Code Best Practices for AI-assisted software development.
Repo: qdhenry/Claude-Command-Suite
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Analyze semantic position relative to knowledge boundaries to prevent hallucination and identify uncertainty zones.
Generate a visual heatmap of knowledge boundaries showing safe zones, risk areas, and semantic coverage.
Evaluate the current risk level and provide detailed analysis of potential hallucination or reasoning failure.
Find and construct semantic bridges to safely navigate from current position to target concept without crossing dangerous boundaries.
Takes an input prompt and returns ONLY a token-optimized version that preserves meaning while minimizing token count. Based on LLM tokenization principles:…