What problem does it solves?
This Skill ensures the highest quality and reliability of AI-generated code and agent outputs by providing real-time truth scoring, comprehensive verification checks, and an automatic rollback system, preventing low-quality changes from persisting.
Core Features & Use Cases
- Truth Scoring: Get real-time reliability metrics (0.0-1.0) for code, agents, and tasks, with a default 0.95 accuracy threshold for production-ready quality.
- Verification Checks: Automate comprehensive checks for code correctness, security vulnerabilities, performance issues, and adherence to best practices.
- Automatic Rollback: Instantly revert changes that fail verification, maintaining codebase integrity and preventing regressions.
- Use Case: Integrate into your CI/CD pipeline to automatically verify every pull request. If the truth score falls below 0.95, the changes are automatically rolled back, and a detailed report is generated, ensuring only high-quality code is merged.
Quick Start
View current truth scores for your codebase and agent tasks
npx claude-flow@alpha truth
Run a comprehensive verification check on your current working directory
npx claude-flow@alpha verify check
Rollback the last failed verification to the last known good state
npx claude-flow@alpha verify rollback --last-good