What problem does it solve? Agent-generated code and task outputs often ship without objective quality gates, letting low-quality or insecure changes persist in the codebase. This skill enforces measurable quality standards through truth scoring, automated verification checks, and instant rollback of changes that fall below a configurable threshold. ## Core Features & Use Cases - Truth Scoring: Computes 0.0-1.0 reliability metrics for code, agents, and tasks with trends, statistics, and exportable reports in JSON, CSV, HTML, or Markdown. - Verification Checks: Validates code correctness, security, performance, documentation, and best practices on files, directories, or task outputs, with optional auto-fix. - Automatic Rollback: Reverts failed changes via git in under a second, with selective, interactive, and dry-run modes. - Use Case: A team wiring quality gates into CI/CD runs verification in GitHub Actions, fails the build when the truth score drops below 0.95, and monitors agent performance trends on a live dashboard. ## Quick Start Run a verification check on my src directory with a 0.95 threshold and show me the truth scores for the last 7 days.