What problem does it solve? Code changes and agent outputs can silently introduce regressions or low-quality work that slips into production. This Skill provides a verification layer that scores output reliability, runs regression-guard checks in CI, and rolls back changes that fall below a configurable quality threshold. ## Core Features & Use Cases - Truth Scoring: Computes 0.0-1.0 reliability metrics for code, agents, and tasks with trends, confidence intervals, and exportable reports (JSON, CSV, HTML). - CI Regression Guards: Ships behavioral smoke tests, a tool-description discoverability audit with monotone-decreasing baselines, and Ed25519-signed witness manifests that verify documented fixes remain present in builds. - Automatic Rollback: Reverts changes that fail verification against a configurable threshold (default 0.95), with selective, dry-run, and backup-first modes. - Use Case: A team adds a new MCP tool and pushes to CI; the tool-description audit fails because the description lacks usage guidance, blocking publish until the baseline violation is fixed. ## Quick Start Run a verification check on my current project and show me the truth scores for the last 7 days.