What problem does it solve? Agent-generated code and task outputs can silently introduce defects, security issues, or regressions. This Skill enforces measurable quality gates by scoring outputs on a 0.0-1.0 truth scale, running verification checks, and automatically rolling back changes that fall below a configurable threshold (default 0.95). ## Core Features & Use Cases - Truth Scoring & Metrics: View per-agent and per-task reliability scores with trends, statistics, and exportable reports in table, JSON, CSV, or HTML formats. - Verification Checks: Validate files, directories, or task outputs against correctness, security, performance, documentation, and best-practices criteria, with optional auto-fix. - Automatic Rollback: Revert failed changes via git-based, selective, or dry-run rollback modes, with automatic backups. - CI/CD & Monitoring Integration: Emit JSON output for GitHub Actions or GitLab CI pipelines, run a real-time web dashboard, and push metrics to Prometheus or DataDog. - Use Case: A team running multi-agent code generation adds a pre-commit hook that runs a verification check; any commit scoring below 0.95 is blocked and rolled back to the last known good state. ## Quick Start Run a verification check on my current project and show me the truth scores for the last 24 hours.
