verification-loop

Automate end-to-end quality verification for Claude Code sessions across build, type, lint, tests, security, and diffs.

1|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/hbvg234/jnmt.vn --skill verification-loop-hbvg234
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-loop
Source: https://github.com/hbvg234/jnmt.vn/tree/main/.claude/skills/verification-loop
Command: npx skills add https://github.com/hbvg234/jnmt.vn --skill verification-loop-hbvg234

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured, multi-phase verification workflow to ensure Claude Code sessions meet build, type safety, lint, tests, security, and change-diff quality before PRs and releases.

Core Features & Use Cases

  • Build Verification: Detects and reports build failures early, enabling immediate fixes.
  • Type Check: Validates TypeScript and Python types across the project.
  • Lint Check: Enforces coding standards and style.
  • Test Suite: Runs tests with coverage reporting and enforces a minimum threshold.
  • Security Scan: Searches for secrets and insecure patterns to prevent data leakage.
  • Diff Review: Reviews file changes to catch regressions and edge cases.

Quick Start

Run the verification loop to execute all phases and generate a verification report for your project.

Frequently Asked Questions about verification-loop

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

FAQPage Schema
How do I run end-to-end build, type, and lint verification before opening a pull request?

End-to-end verification is automated by running build checks, type validation, linting, tests, security scans, and diff reviews, outputting a standardized report with pass/fail status, metrics, and suggested fixes for your PR prechecks.

What is the best way to validate TypeScript and Python types after a major code refactor?

Post-refactor type validation is handled by running TypeScript and Python type checks using standard tooling like tsc and pyright, catching type regressions and outputting failures within a comprehensive verification report.

Can I enforce a minimum test coverage threshold and scan for security leaks in a CI-CD workflow?

Yes, test suite execution includes coverage reporting with minimum threshold enforcement, and the security scan phase detects secrets and insecure patterns, preventing data leakage before releases.

Does end-to-end verification work with both JavaScript and Python projects?

Yes, verification supports both JavaScript/TypeScript and Python projects, requiring standard package managers like npm, pnpm, or yarn, and tools like eslint and ruff to execute the quality checks.

How do I review file diffs to catch regressions and edge cases during feature development?

The diff review phase automatically analyzes file changes to catch regressions and edge cases, incorporating the results into the final verification report alongside build, type, lint, test, and security metrics.

Why does my verification loop fail even when the build passes successfully?

A successful build does not guarantee overall verification; failures can occur in type checks, linting standards, minimum test coverage thresholds, or security scans for insecure patterns, all detailed in the verification report.