verify

Executes real-world verification of web apps and APIs with status reporting.

Updated Mar 29, 2026
One-click install
npx skills add https://github.com/rolopez23/agent-harness --skill verify-rolopez23
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verify
Source: https://github.com/rolopez23/agent-harness/tree/main/skills/verify
Command: npx skills add https://github.com/rolopez23/agent-harness --skill verify-rolopez23

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ensures end-to-end verification of implemented code against a live system, going beyond unit tests to confirm real-world behavior and to report whether verification passed, failed, or is incomplete when the system cannot be reached.

Core Features & Use Cases

  • End-to-end checks for APIs via real HTTP requests and for web UIs via browser automation.
  • Detailed verification reporting that distinguishes success, failure, and incomplete outcomes.
  • Triggers from user intents such as "verify this" or when a plan dashboard requires an update to the verification status.

Quick Start

Run a live end-to-end verification against the deployed environment and report the results.

Frequently Asked Questions about verify

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

FAQPage Schema
How do I run end-to-end verification against a live API environment?

End-to-end verification sends real HTTP requests to your live API endpoints to confirm actual system behavior. It executes real requests against the deployed environment and generates a structured report indicating whether checks passed, failed, or are incomplete.

What is the difference between unit testing and end-to-end system verification?

End-to-end system verification goes beyond unit tests by checking real-world behavior against a live environment. It validates actual web UIs via browser automation and APIs via real HTTP requests, ensuring your deployed system responds correctly rather than just testing isolated code components.

Can I verify web UIs using browser automation and get a structured report?

Yes, end-to-end verification supports web UIs through browser automation and generates detailed reporting. It distinguishes between success, failure, and incomplete outcomes, providing clear statuses that confirm whether your live web interface behaves as expected.

How do I handle unreachable systems during end-to-end quality assurance checks?

End-to-end verification gracefully handles unreachable systems by returning a clear incomplete status. When a live environment is partially reachable or completely down, it reports the outcome as incomplete rather than failing, ensuring you know the system state accurately.

What's the best way to report end-to-end testing results for a deployed system?

The best way to report end-to-end testing results is through structured outcome reports that distinguish success, failure, and incomplete statuses. This approach clarifies whether the live system passed verification, failed checks, or could not be fully reached.