ultraqa

Automate iterative QA verification by running checks and repairing failures until goals pass.

Updated Feb 20, 2026
One-click install
npx skills add https://github.com/ssccio/cc-on-web-base --skill ultraqa-ssccio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ultraqa
Source: https://github.com/ssccio/cc-on-web-base/tree/main/skills/ultraqa
Command: npx skills add https://github.com/ssccio/cc-on-web-base --skill ultraqa-ssccio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the repetitive effort of running QA checks, diagnosing failures, applying fixes, and rerunning until a defined quality goal is met.

Core Features & Use Cases

  • Goal-driven QA cycling: Runs the appropriate verification loop for tests, builds, lint, type checks, custom success patterns, or interactive QA tasks.
  • Failure diagnosis with specialization: Uses an architect pass to determine root cause and targeted remediation steps when the goal is not met.
  • Iterative execution and repeat: Applies recommended fixes via an executor agent and repeats until the goal passes or stop conditions trigger.

Use case: When a project’s test suite fails after a change, run UltraQA with a goal like tests, let it diagnose which failures matter most, apply precise fixes, and repeat until all tests pass or the maximum cycle limit is reached.

Quick Start

Ask for UltraQA by running: /oh-my-claudecode:ultraqa --tests

Frequently Asked Questions about ultraqa

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

FAQPage Schema
How do I automate fixing failing tests and build validation errors?

To automate fixing failing tests and build validation errors, this Skill runs iterative QA verification cycles that diagnose root causes via an architect pass and applies targeted fixes until all checks pass or retry limits trigger.

What is autonomous QA cycling for CI verification workflows?

Autonomous QA cycling for CI verification workflows is a process that repeatedly runs goal-specific checks like tests, linting, and TypeScript type checking, then repairs failures automatically until the defined quality goal is satisfied.

How do I run iterative debugging cycles with capped retries for TypeScript type checking?

To run iterative debugging cycles with capped retries for TypeScript type checking, initiate the agent workflow with a type check goal to trigger deterministic cycle control, state tracking, and clean state deletion upon completion.

Does this autonomous failure diagnosis approach work with interactive service verification?

Yes, this autonomous failure diagnosis approach works with interactive service verification, applying its iterative execution loop to diagnose failures, apply executor fixes, and repeat until the service quality goal is met.

What are the limitations of automated agent workflows for QA verification?

The primary limitation of automated agent workflows for QA verification is the maximum cycle limit; if the stop conditions trigger before the quality goal passes, the process halts and manual intervention is required to resolve remaining failures.