How does the parallel verification work?

It launches five specialized sub-agents—Security Auditor, Code Quality Reviewer, Backend Architect, Frontend Developer, and Test Generator—concurrently to analyze your code from different domain perspectives in a single message.

Does it require manual skill loading?

No, if you are using Claude Code 2.1.6 or later, relevant skills like security-scanning and code-review-playbook are automatically discovered and activated when the verify skill is invoked.

What is included in the verification report?

The report compiles unit/integration test results, coverage percentages, quality gate statuses (type safety, linting), and specific security scan findings into a standardized Markdown format.

Which testing frameworks are supported?

It includes pre-configured patterns for Pytest, Poetry, NPM, Vitest, and Playwright, but it is flexible enough to be used with any CLI-based test runner.

Can it verify UI changes visually?

Yes, it utilizes agent-browser capabilities to open your local development server, take screenshots, and verify UI elements against your requirements.

Comprehensive Feature Verification

Name: Comprehensive Feature Verification
Author: yonatangross

byyonatangross

•

보안 및 테스팅

Verifies software implementations through parallelized agent analysis, automated testing, and detailed evidence compilation.

소개

The Verify skill provides a robust framework for validating software changes using a multi-agent approach within Claude Code. It automatically triggers specialized sub-agents for code quality, security, backend architecture, frontend UI, and test generation to ensure comprehensive coverage across the entire stack. Designed for production-grade development, it streamlines the verification lifecycle—from gathering git context and running cross-platform test suites to generating detailed quality gate reports and performing E2E browser-based validation with agent-browser integration.

주요 기능

Smart Context Discovery: Automatically identifies affected code areas and loads relevant skill playbooks for deep analysis.
E2E Browser Validation: Integrates with agent-browser for real-world UI interaction snapshots and visual verification.
29 GitHub stars
Cross-Stack Test Execution: Orchestrates backend (Pytest), frontend (NPM/Vitest), and E2E (Playwright) testing workflows.
Parallel Multi-Agent Analysis: Deploys five specialized agents simultaneously for security, quality, and architecture reviews.
Automated Evidence Compilation: Generates detailed verification reports including coverage metrics and quality gate status.

사용 사례

Validating a new feature implementation before merging to ensure it meets quality and security standards.
Automating the generation of verification reports and test evidence for PR reviews or compliance.
Performing a comprehensive security and quality audit on existing codebases or legacy refactors.

소개

주요 기능

Smart Context Discovery: Automatically identifies affected code areas and loads relevant skill playbooks for deep analysis.
E2E Browser Validation: Integrates with agent-browser for real-world UI interaction snapshots and visual verification.
29 GitHub stars
Cross-Stack Test Execution: Orchestrates backend (Pytest), frontend (NPM/Vitest), and E2E (Playwright) testing workflows.
Parallel Multi-Agent Analysis: Deploys five specialized agents simultaneously for security, quality, and architecture reviews.
Automated Evidence Compilation: Generates detailed verification reports including coverage metrics and quality gate status.

사용 사례

Validating a new feature implementation before merging to ensure it meets quality and security standards.
Automating the generation of verification reports and test evidence for PR reviews or compliance.
Performing a comprehensive security and quality audit on existing codebases or legacy refactors.