Can I integrate this with GitHub Actions?

Yes, the skill provides structured JSON and HTML output formats, specifically designed to function as quality gates within CI/CD pipelines like GitHub Actions or GitLab CI.

Does it support real-time monitoring?

Yes, it includes a watch mode for CLI updates and an interactive web-based dashboard that uses WebSockets for real-time quality and performance visualization.

Can I customize the verification thresholds?

Absolutely. You can set global thresholds in the configuration or pass specific flags during command execution to adjust strictness for different environments like production or staging.

What is a Truth Score in this skill?

A Truth Score is a reliability metric from 0.0 to 1.0 that evaluates the correctness, security, and quality of code or agent-generated tasks based on predefined validation rules.

How does the automatic rollback work?

If a verification check falls below the default 0.95 accuracy threshold, the skill uses Git integration to instantly revert the codebase to its last known stable state.

Verification & Quality Assurance

Name: Verification & Quality Assurance
Author: Microck

byMicrock

•

セキュリティとテスト

Ensures high-quality agent outputs through truth scoring, automated code verification, and an intelligent rollback system.

This skill provides a comprehensive quality assurance framework for Claude Code, focusing on reliability and code correctness. By implementing a sophisticated truth scoring system (0.0-1.0) and automated verification checks across security, performance, and best practices, it prevents regressions and ensures production-grade output. Its standout feature is the automatic rollback system, which instantly reverts changes that fall below defined confidence thresholds, making it an essential tool for developers building autonomous agent workflows or maintaining complex codebases.

主な機能

01Instant Git-based rollback system for changes failing accuracy thresholds

02Automated verification of security, performance, and best practices

0381 GitHub stars

04Real-time Truth Scoring (0.0-1.0 scale) for code and agent tasks

05Interactive web-based dashboards for quality metrics and trend analysis

06Seamless CI/CD integration with structured JSON/HTML reporting

ユースケース

01Enforcing security and coding standards across collaborative development teams

02Monitoring autonomous agent reliability during large-scale refactoring tasks

03Automating quality gates in CI/CD pipelines to prevent poor code from merging

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microck/ordinary-claude-skills verification-quality-assurance

For use in Claude.ai and ChatGPT

Download Skill