What problem does it solve?
Ensuring high code quality and reliability in AI-generated outputs can be challenging, leading to errors and regressions. This Skill provides a comprehensive system for real-time truth scoring, automated verification, and instant rollback, guaranteeing that only high-quality, reliable code persists.
Core Features & Use Cases
- Truth Scoring: Get real-time reliability metrics (0.0-1.0) for code, agents, and tasks, with trends and confidence intervals.
- Verification Checks: Automated validation of code correctness, security, best practices, performance, and documentation.
- Automatic Rollback: Instantly revert changes that fail verification (default threshold: 0.95), preventing bad code from entering the codebase.
- Use Case: Integrate this Skill into your CI/CD pipeline. Any pull request that introduces code with a truth score below 0.95 is automatically flagged, and if merged, the changes are instantly rolled back, ensuring your main branch remains pristine.
Quick Start
View current truth scores
npx claude-flow@alpha truth
Run verification check on current directory
npx claude-flow@alpha verify check
Rollback last failed verification
npx claude-flow@alpha verify rollback --last-good