Verification & Quality Assurance

Produces numeric truth scores and JSON reports for code and agent outputs.

1|Updated Jun 9, 2020
One-click install
npx skills add https://github.com/dalager/jernkorsetbreve --skill verification-quality-assurance-dalager
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Verification & Quality Assurance
Source: https://github.com/dalager/jernkorsetbreve/tree/main/.claude/skills/verification-quality
Command: npx skills add https://github.com/dalager/jernkorsetbreve --skill verification-quality-assurance-dalager

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill reduces uncertainty and manual effort by scoring the reliability of code, agent outputs, and development tasks, surfacing correctness, security, and quality regressions so teams can act quickly.

Core Features & Use Cases

  • Truth Scoring: Continuous numeric reliability metrics for files, tasks, and agents (0.0-1.0) to drive gating decisions.
  • Verification Checks & Metrics: Automated correctness, security, style, performance, and documentation checks with JSON/HTML report outputs for CI/CD ingestion.
  • Automatic Rollback & Integration: Git-aware rollback of failing changes, pre-commit and pipeline hooks, dashboards for trend analysis, and configurable thresholds for production, staging, and development.
  • Use Case: Block a pull request in GitHub Actions when the verification overallScore falls below 0.95, generate a JSON report for triage, and optionally rollback selective files to last-known-good state.

Quick Start

Run a verification scan on the current repository, export a JSON verification report, and flag or rollback changes that fall below a 0.95 threshold.

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 quality verification and block pull requests with failing checks?

Automate code quality verification by applying truth scoring to your code and configuring thresholds to block pull requests in CI/CD pipelines when the overall score falls below a set limit like 0.95.

What is truth scoring for code and how does it measure reliability?

Truth scoring is a continuous numeric reliability metric ranging from 0.0 to 1.0 applied to files, tasks, and agent outputs to evaluate correctness, security, and quality regressions for automated gating decisions.

Can I use automated Git rollback for failing changes in a CI/CD pipeline?

Yes, you can use Git-aware rollback in your CI/CD pipeline to automatically revert failing changes, selectively rolling back specific files to a last-known-good state when verification checks detect regressions.

How do I generate structured verification reports for CI/CD pipelines?

Generate structured JSON and HTML verification reports by running automated correctness, security, style, performance, and documentation checks, outputting the results for pipeline ingestion and triage.

Does truth scoring work for verifying multi-agent workflow outputs?

Yes, truth scoring applies to multi-agent workflows by evaluating agent outputs and task results, surfacing correctness and security regressions across local development and CI/CD environments.

What's the best way to configure verification thresholds across different deployment environments?

Configure separate verification thresholds for production, staging, and development environments to enforce varying levels of code quality, using pre-commit and pipeline hooks to gate deployments based on numeric truth scores.