ultraqa

Automates QA cycling with verification, diagnosis, and fix loops up to five iterations.

1|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/Leap0920/Clean-Portfolio --skill ultraqa-leap0920
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ultraqa
Source: https://github.com/Leap0920/Clean-Portfolio/tree/main/%25USERPROFILE%25/.openclaude/plugins/cache/omc/oh-my-claudecode/4.14.0/skills/ultraqa
Command: npx skills add https://github.com/Leap0920/Clean-Portfolio --skill ultraqa-leap0920

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates a repeated QA loop by running the right verification step, diagnosing failures when they occur, applying targeted fixes, and continuing until the specified quality goal is achieved or stopping conditions are met.

Core Features & Use Cases

  • Goal-driven QA cycling: Choose a goal type such as tests, build, lint, typecheck, custom output pattern, or interactive QA and keep iterating until it passes.
  • Failure diagnosis and fix loop: When the goal fails, it triggers an architect diagnosis step and then an executor fix step to implement recommended changes.
  • Safety stops and state tracking: Caps cycles at 5, detects repeated failures to exit early, and tracks session state in a JSON file that is cleaned up on completion or cancellation.

Quick Start

Run ultraqa in tests mode and let it keep cycling until the test suite passes or the maximum cycles are reached.

Frequently Asked Questions about ultraqa

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

FAQPage Schema
How can I automate my build verification and test fixing loop?

You can automate iterative QA cycling by running a workflow that executes your verification command, diagnoses failures via an architect step, and applies executor fixes until the test suite passes or it hits five cycle iterations.

What is autonomous QA cycling and how does it handle lint or typecheck failures?

Autonomous QA cycling is an iterative workflow that runs verification steps for tests, build, lint, or typecheck, diagnosing failures and applying targeted fixes until the specified goal passes or stopping conditions are met.

How do I set up an iterative quality gate workflow for custom output patterns?

You set up iterative quality gates by defining a custom output pattern goal, which the workflow then checks by running the appropriate verification command, diagnosing mismatches, and applying fixes up to five times.

Does autonomous QA cycling stop automatically if the same test keeps failing?

Yes, autonomous QA cycling includes safety stops that cap iterations at five cycles and detect repeated failures to exit early, ensuring the loop terminates if fixes are not resolving the issue.

Can I use autonomous QA cycling for interactive CLI or service testing?

Yes, autonomous QA cycling supports interactive CLI and service testing by running the appropriate verification commands, diagnosing failures, and applying fixes until the interactive QA goal is met or cycles are exhausted.

What happens to the state tracking file when the QA cycling workflow is cancelled?

When the QA cycling workflow is cancelled or completed, the process cleans up by deleting the persistent JSON state artifact used for tracking session state, ensuring no residual files remain.