verification-loop

Runs build, type check, lint, tests, security scan, and diff review before pull requests.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/Clay-HHK/claude-skills --skill verification-loop-clay-hhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-loop
Source: https://github.com/Clay-HHK/claude-skills/tree/main/verification-loop
Command: npx skills add https://github.com/Clay-HHK/claude-skills --skill verification-loop-clay-hhk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code changes often ship with undetected build failures, type errors, lint violations, failing tests, or leaked secrets. This Skill provides a structured six-phase verification workflow that catches these issues before a pull request is created. ## Core Features & Use Cases - Six-Phase Verification: Sequentially runs build verification, type checking (tsc/pyright), linting (npm lint/ruff), test suites with coverage (pytest/npm test), security scanning for hardcoded secrets and debug statements, and git diff review. - Standardized Report: Produces a pass/fail verification report summarizing each phase with an overall READY/NOT READY verdict for PR submission. - Use Case: After finishing a feature branch in a Python project, invoke the skill to run uv build, pyright, ruff, pytest with coverage, and a secret scan, then receive a consolidated report listing issues to fix before opening the PR. ## Quick Start Ask the assistant to run the verification loop on the current project and report whether the changes are ready for a pull request.

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 changes before creating a pull request?▼

Run a verification loop covering build, type check, lint, tests, security scan, and diff review in sequence. Each phase reports pass or fail, and the final summary states whether the changes are ready for a PR.

What checks should a code quality verification workflow include?▼

A thorough workflow includes build verification, static type checking with tsc or pyright, linting with ruff or npm lint, test execution with coverage reporting, secret and debug-statement scanning, and a git diff review of changed files.

Does this verification workflow support both Python and Node.js projects?▼

Yes, each phase provides commands for both ecosystems. Python projects use uv build, pyright, ruff, and pytest, while Node.js projects use npm or pnpm build, tsc, npm lint, and npm test.

How do I scan code for leaked API keys and secrets?▼

Use grep to search source files for patterns like sk- and api_key, and run pip-audit for Python dependency vulnerabilities. The workflow also flags leftover print and console.log debug statements.

When should I run verification during a long coding session?▼

Run verification after completing each function or component, after major changes, and always before creating a PR. For long sessions, a checkpoint roughly every 15 minutes keeps issues from accumulating.