openclaw-qa-testing

Coordinate repository-backed QA tests for OpenClaw using qa-lab and qa-channel.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/191854169/openclawFork --skill openclaw-qa-testing-191854169
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openclaw-qa-testing
Source: https://github.com/191854169/openclawFork/tree/main/.agents/skills/openclaw-qa-testing
Command: npx skills add https://github.com/191854169/openclawFork --skill openclaw-qa-testing-191854169

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps teams run, monitor, debug, and extend the OpenClaw QA suite using qa-lab and qa-channel across local and CI workflows.

Core Features & Use Cases

  • Seed scenarios live in qa/ and are executed by the central runner.
  • The main workflow is implemented in extensions/qa-lab/src/suite.ts with a QA-lab server that coordinates tests, artifacts, and reporting.
  • It supports live OpenAI runs with a configured provider-mode and model, along with artifact collection for analysis.

Quick Start

Run the QA suite with the live OpenAI provider using model openai/gpt-5.4 and collect artifacts in the designated outputs.

Frequently Asked Questions about openclaw-qa-testing

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

FAQPage Schema
How do I run repository-backed QA tests for seed scenarios in a CI workflow?

Repository-backed QA tests execute seed scenarios defined in qa/seed-scenarios.json through a central runner in extensions/qa-lab/src/suite.ts, coordinating artifact collection and reporting across local and CI workflows.

Can I configure live OpenAI runs with a specific provider-mode and model?

Live OpenAI runs support configuring provider-mode and model settings, allowing you to execute the QA suite with specific models like openai/gpt-5.4 while collecting artifacts in designated output paths.

What files do I need to set up before executing the QA suite?

Executing the QA suite requires the qa suite files, specifically qa/seed-scenarios.json for seed-scenario validation and extensions/qa-lab/src/suite.ts for the central runner and QA-lab server coordination.

How does the QA-lab server coordinate test execution and artifact collection?

The QA-lab server coordinates tests, artifacts, and reporting by running the main workflow implemented in extensions/qa-lab/src/suite.ts, managing seed-scenario validation and live OpenAI runs across development and CI environments.

What is the best way to validate seed scenarios locally before CI integration?

Seed-scenario validation runs locally through the central runner that processes qa/seed-scenarios.json, using the QA-lab server to coordinate artifact collection and reporting before promoting tests to CI workflows.

Does the QA testing workflow support artifact collection for post-run analysis?

Artifact collection is supported during live OpenAI runs and seed-scenario validation, storing outputs in designated paths for analysis across both local development and CI workflow environments.