What problem does it solve?
Ensuring high code quality and reliability in AI-generated or human-written code is critical but often manual and subjective. This Skill provides an objective, automated system for truth scoring, comprehensive verification, and automatic rollback, preventing low-quality code from persisting.
Core Features & Use Cases
- Truth Scoring System: Real-time reliability metrics (0.0-1.0) for code, agents, and tasks, with trends and confidence intervals.
- Comprehensive Verification Checks: Automated validation of code correctness, best practices, security, performance, and documentation.
- Automatic Rollback: Instantly reverts changes that fail verification (default threshold: 0.95), ensuring only high-quality code is integrated.
- Use Case: Integrate into your CI/CD pipeline to automatically verify every pull request. If the overall truth score falls below 0.95 due to security vulnerabilities or performance regressions, the changes are automatically rolled back, preventing deployment of faulty code.
Quick Start
View current truth scores for your codebase, then run a comprehensive verification check on your src/app.js file with a strict threshold.
npx claude-flow@alpha truth
npx claude-flow@alpha verify check --file src/app.js --threshold 0.98