enclawed-qa-testing

Run and debug Enclawed QA workflows with artifact inspection and deterministic reruns.

2|Updated May 23, 2026
One-click install
npx skills add https://github.com/enclawed/enclawed-oss --skill enclawed-qa-testing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: enclawed-qa-testing
Source: https://github.com/enclawed/enclawed-oss/tree/main/.agents/skills/enclawed-qa-testing
Command: npx skills add https://github.com/enclawed/enclawed-oss --skill enclawed-qa-testing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of running, watching, and debugging the Enclawed QA workflow so you can validate scenarios, inspect artifacts, and fix failures quickly.

Core Features & Use Cases

  • Repo-backed QA execution: Run the qa-lab suite and related qa-channel flows directly against the repository.
  • Live artifact inspection: Review summaries, reports, logs, and other generated outputs to understand what passed or failed.
  • Failure debugging and extension: Investigate broken scenarios, correct harness or product issues, and add new QA coverage when needed.
  • Model and lane guidance: Follow the prescribed live OpenAI policy and choose between mock/dev and real validation lanes appropriately.

Quick Start

Use the enclawed-qa-testing skill to run the repo-backed QA suite for the scenario or lane you want to validate, then inspect the generated artifacts and fix any failing cases.

Frequently Asked Questions about enclawed-qa-testing

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

FAQPage Schema
How do I run and debug QA workflows against my repository?

To run and debug QA workflows, execute the repo-backed qa-lab suite and qa-channel flows to validate scenarios, inspect generated artifacts, and identify failures. You can review summaries, reports, and logs to understand test outcomes and correct harness issues quickly.

What is the best way to inspect live QA artifacts after a test run?

The best way to inspect live QA artifacts is to review the generated summaries, reports, and logs produced during the suite execution. This allows you to examine the outputs directly to understand which scenarios passed or failed and diagnose issues.

Do I need an OpenAI model policy to execute QA testing lanes?

Yes, you need a live OpenAI model policy to execute QA testing. The workflow requires you to follow the prescribed policy and choose appropriately between mock or dev lanes and real validation lanes when running the character-eval harness.

How do I add new coverage for broken QA scenarios?

To add new coverage for broken QA scenarios, investigate the failures, correct harness or product issues, and extend the suite with new tests. You can then perform deterministic reruns through the suite and character-eval harness to verify fixes.

Why are my deterministic QA reruns failing across different lanes?

Deterministic QA reruns fail when scenario markdown files are missing or when the incorrect lane is selected. Ensure you are following the live OpenAI model policy and verifying that the character-eval harness is configured correctly for mock versus live validation.