One-click install
npx skills add https://github.com/btseytlin/ultrapack --skill uverify
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: uverify
Source: https://github.com/btseytlin/ultrapack/tree/main/plugins/up/skills/uverify
Command: npx skills add https://github.com/btseytlin/ultrapack --skill uverify

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

uverify helps you validate that a previously executed change is truly correct by attacking it with adversarial checks, so you can demonstrate breakage or confidently advance to review.

Core Features & Use Cases

  • Attack-checklist verification: Builds a hypothesis-driven set of checks covering happy-path, negative, invariants/assumptions, and interface mismatches.
  • Evidence-first verification loop: Re-runs each attack in the current message to prevent “it should work” assumptions, capturing real outputs as evidence.
  • Task-file audit trail: Writes a concise Verify summary into the task file’s ## Verify section, and routes to up:ureview or up:uexecute based on outcomes.

Quick Start

Ask the agent to run uverify against the current task’s Execute output and update docs/tasks/<slug>.md under the Verify section with the attack results and next action.

Frequently Asked Questions about uverify

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

FAQPage Schema
What is adversarial code verification after making a change?

Adversarial code verification generates fresh attacks against executed changes to prove they break or hold, capturing real outputs as evidence instead of relying on assumptions that the code should work.

How do I verify a code change using attack checklists?

To verify a code change, build an attack checklist covering happy-path, negative, invariants, and interface mismatches, then re-run each attack to record held, broke, or deferred verdicts in your task documentation.

How do I document verification results in a git-centered task workflow?

Document verification results by writing a concise summary of attack outcomes into the task file's Verify section under docs/tasks/<slug>.md, creating an audit trail that routes passing changes to review or failures back for execution.

Does code verification work with end-to-end smoke testing?

Yes, code verification optionally applies smoke testing to the end-to-end path alongside adversarial checks, ensuring the full workflow remains intact before routing the task to the next workflow phase.

What happens when an adversarial verification check breaks?

When an adversarial verification check breaks, the workflow routes back to the execution phase with remediation guidance, requiring the agent to loop back on failures and re-verify until the change holds.