Verification & Quality Assurance

Run verification checks and produce CI-friendly JSON reports with exit codes.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/softmg/product-tracker --skill verification-quality-assurance-softmg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Verification & Quality Assurance
Source: https://github.com/softmg/product-tracker/tree/main/.claude/skills/verification-quality
Command: npx skills add https://github.com/softmg/product-tracker --skill verification-quality-assurance-softmg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates uncertainty about code and agent outputs by providing automated truth scoring, verification checks, and instant rollback to prevent low-quality or unsafe changes from reaching production.

Core Features & Use Cases

  • Truth Scoring & Metrics: Real-time reliability scores (0.0–1.0) with trends, confidence intervals, and per-agent/file breakdowns.
  • Automated Verification: Syntax, type, security, performance, and documentation checks with CI-friendly JSON output and standard exit codes.
  • Automatic Rollback & Recovery: Git-integrated selective rollback, backups, dry-run previews and pre-commit hooks to stop regressions.
  • Use Case: Integrate into CI pipelines to fail pull requests below a threshold, continuously monitor agent outputs, or run watch-mode verification during local development and pair programming.

Quick Start

Run a verification check on the current repository and produce a JSON report for CI integration.

Frequently Asked Questions about Verification & Quality Assurance

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate code verification and block CI pipelines from merging unsafe changes?

Automated code verification runs syntax, type, security, and performance checks to produce CI-friendly JSON reports and standard exit codes, failing pipelines before unsafe changes merge.

What is truth scoring for agent outputs and how does it evaluate code correctness?

Truth scoring evaluates code correctness by generating real-time reliability scores from 0.0 to 1.0, providing confidence intervals and per-agent or per-file breakdowns for development tasks.

Do I need a Git repository and Node.js to run automated rollback and recovery?

Yes, automated rollback and recovery require a Git repository for selective backups and pre-commit hooks, alongside Node.js for dashboard components and claude-flow tooling for execution.

Can I use this verification tool to monitor multi-agent coordination in local development?

Yes, you can monitor multi-agent coordination and local development by running watch-mode verification, continuously validating agent outputs, syntax, and performance during pair programming.

What's the best way to preview a Git rollback before applying it to my repository?

The best way to preview a Git rollback is using dry-run previews, which evaluate selective rollback strategies and backups against your repository state before executing actual recovery actions.