verify

Run build, type, lint, test, security, and diff checks across a project.

1|1|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/zb-ss/claude-plugin-workflow --skill verify-zb-ss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verify
Source: https://github.com/zb-ss/claude-plugin-workflow/tree/main/skills/verify
Command: npx skills add https://github.com/zb-ss/claude-plugin-workflow --skill verify-zb-ss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you quickly validate that your current code changes are correct, consistent, and low-risk by running a structured verification loop across the most common quality gates.

Core Features & Use Cases

  • Tiered verification phases: runs build, type checking, linting, tests, security scanning, and diff review in a single workflow.
  • Project-aware command adaptation: detects project type (Node, PHP, Python, Rust, etc.) and selects appropriate tools/commands per phase.
  • Actionable reporting: outputs a clear PASS/FAIL/WARN matrix with timing and a next-steps section so you can fix issues immediately.
  • Phase targeting: re-runs only a specific phase (e.g., lint or security) when you want faster feedback.

Quick Start

Invoke /workflow:verify to run the full verification loop on your current changes and get a summarized report of build, types, lint, tests, security, and diff results.

Frequently Asked Questions about verify

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

FAQPage Schema
How do I run pre-merge build, test, and security checks on my code changes?

Pre-merge build, test, and security checks are executed by running a structured verification loop across your active project. It detects the project type from configuration files and runs the corresponding toolchain to produce a consolidated PASS/FAIL/WARN report with timings.

What is the best way to validate code changes across multiple languages like Node and Python?

To validate code changes across multiple languages, project-aware command adaptation detects the project type from configuration files and selects appropriate tools per phase. This automatically adapts the verification workflow for Node, PHP, Python, or Rust environments.

Can I run only a specific lint or security scanning phase instead of the full verification loop?

Yes, you can target a specific phase such as lint or security scanning to get faster feedback. Phase targeting allows you to re-run only the selected check rather than executing the entire build, type, test, and diff verification workflow.

How does the verification report show which CI quality gate failed?

The CI quality gate results are displayed in an actionable reporting matrix showing PASS, FAIL, or WARN status with timings. It includes error details and a next-steps section so you can immediately identify and fix the failed verification phase.

Does the verification workflow require any specific CI pipeline dependencies to operate?

No CI pipeline dependencies are required. The verification workflow operates standalone by detecting your project type from local configuration files and executing the corresponding build, type, lint, test, security, and diff toolchain directly.

Why should I use a tiered verification loop instead of running tests manually?

A tiered verification loop provides structured confidence signals by running build, type checking, linting, tests, security scanning, and diff review in a single workflow. This catches consistency and security risks that manual test execution might miss during continuous development.