verification-loop

Runs build, type, lint, test, security, and diff checks to produce a verification report.

1|Updated Oct 11, 2025
One-click install
npx skills add https://github.com/ibytechaos/claude --skill verification-loop-ibytechaos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-loop
Source: https://github.com/ibytechaos/claude/tree/main/plugins/everything-claude-code/skills/verification-loop
Command: npx skills add https://github.com/ibytechaos/claude --skill verification-loop-ibytechaos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After finishing a feature or refactor, it is easy to miss a failing build, type error, or leaked secret before opening a PR. This Skill runs a structured multi-phase verification pass so quality gates are checked consistently before code is submitted. ## Core Features & Use Cases - Six-Phase Verification: Sequentially checks build, TypeScript/Python type errors, lint results, test coverage, secret and console.log scans, and git diff review. - Standardized Report: Produces a PASS/FAIL summary with test counts, coverage percentage, and a READY/NOT READY verdict for PRs. - Continuous Mode: Supports periodic re-verification during long sessions after each function, component, or task. - Use Case: After refactoring a TypeScript module, invoke the skill to confirm the build passes, tests meet the 80% coverage target, and no API keys were accidentally committed before creating the pull request. ## Quick Start Run the verification loop on my current changes and tell me whether the code is ready for a PR.

Frequently Asked Questions about verification-loop

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

FAQPage Schema
How do I verify code quality before creating a pull request?

Run a verification loop that checks the build, type errors, lint results, test coverage, and security scans, then reviews the git diff. The skill outputs a report with a READY or NOT READY verdict listing issues to fix first.

How to run type checking and linting for TypeScript and Python projects?

For TypeScript use npx tsc --noEmit and npm run lint; for Python use pyright and ruff check. The verification loop runs the appropriate commands per language and reports all errors before continuing.

Does the verification loop work with both npm and pnpm projects?

Yes, the build phase supports both npm run build and pnpm build commands. Test execution uses npm run test with coverage flags, targeting an 80% minimum coverage threshold.

What security issues does the verification loop detect?

It scans source files for leaked secrets such as sk- prefixed keys and api_key strings, plus leftover console.log statements in TypeScript files. Findings are reported as part of the security phase in the final report.

When should I run verification during a long coding session?

Run it after completing each function, finishing a component, or before moving to the next task, roughly every 15 minutes in continuous mode. It complements PostToolUse hooks by providing deeper comprehensive review.