How does the security scan work?

The skill performs automated scans of your codebase to identify exposed secrets like API keys and ensure that debug statements like console.log are removed before production.

Does it support both TypeScript and Python?

Yes, the skill includes pre-configured commands for both TypeScript (using tsc and npm) and Python (using pyright and ruff) environments.

When should I use this skill?

You should call this skill after finishing a feature, performing a major refactor, or right before creating a pull request to ensure all quality gates are passed.

What is the Verification Loop skill?

It is a specialized capability for Claude Code that runs a systematic quality check across build, type, lint, test, and security phases to ensure code reliability.

What is the target test coverage for this skill?

The Verification Loop skill targets a minimum of 80% test coverage and provides a standardized report on passed, failed, and total test counts.

Verification Loop

Name: Verification Loop
Author: unju-ai

byunju-ai

0•

Security & Testing

Automates a multi-stage quality assurance process to ensure codebases meet build, type-safety, and security standards before deployment.

The Verification Loop skill provides a structured framework for validating code changes within Claude Code sessions. It guides the AI through a six-stage pipeline—including build checks, TypeScript or Python type validation, linting, test suite execution with coverage targets, security scanning for secrets, and a comprehensive diff review. This systematic approach ensures that AI-generated code is production-ready, minimizes regressions, and maintains high quality thresholds, making it an essential tool for refactoring and preparing pull requests.

Key Features

01Standardized verification reports to simplify PR sign-off and code review

02Automated test coverage monitoring with a standardized 80% threshold target

030 GitHub stars

04Six-stage validation pipeline covering builds, types, linting, tests, security, and diffs

05Security scanning to detect exposed API keys and accidental debug logs

06Pre-configured support for both TypeScript (tsc) and Python (pyright/ruff) environments

Use Cases

01Finalizing complex refactors to ensure no functional regressions or type errors were introduced

02Implementing continuous quality checkpoints during long-running AI coding sessions

03Preparing a comprehensive quality report before submitting a Pull Request

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add unju-ai/ecc verification-loop

For use in Claude.ai and ChatGPT