kova-qa-testing

Execute and monitor Kova qa-lab and qa-channel scenarios across mock, live OpenAI, OTEL smoke, and matrix lanes.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/chiragborse1/KovaLab --skill kova-qa-testing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kova-qa-testing
Source: https://github.com/chiragborse1/KovaLab/tree/main/.agents/skills/kova-qa-testing
Command: npx skills add https://github.com/chiragborse1/KovaLab --skill kova-qa-testing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Kova developers need a repeatable way to run, watch, and debug QA-lab and qa-channel end-to-end scenarios, including live OpenAI lanes and matrix coverage, without losing time to setup, failures, or missing artifacts.

Core Features & Use Cases

  • QA Suite Execution for qa-lab/qa-channel: Guides selecting the correct lane (mock/dev vs live-frontier) and produces deterministic artifact outputs for review.
  • Live Run Monitoring & Failure Recovery: Specifies where to find the suite summary/report, how to locate the QA listen port for watching live UI, and what to do when a scenario fails.
  • Specialized Validation Flows: Covers OTEL smoke validation, Matrix lane sharding for transport/media/e2ee coverage, and character evaluation to judge persona/style consistency across models.
  • Credential & Environment Handling: Documents how to source QA secrets from 1Password and how to map provider modes and Telegram/Docker/Convex requirements correctly.

Quick Start

Ask the AI agent to run the live OpenAI QA suite using gpt-5.4 fast mode and output artifacts to .artifacts/qa-e2e for your chosen tag.

Frequently Asked Questions about kova-qa-testing

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

FAQPage Schema
How do I run end-to-end QA testing across mock and live OpenAI lanes?

End-to-end QA testing across mock and live OpenAI lanes is executed by selecting the correct provider mode and model, running the suite, and outputting deterministic artifacts to a specified path for review and debugging.

What is the best way to debug failing QA scenarios and locate live run reports?

Debugging failing QA scenarios involves locating the suite summary report, checking the QA listen port to watch the live UI, and diagnosing failures using the generated artifact outputs and summaries.

Can I use gpt-5.4 fast mode for live OpenAI QA suite execution?

Yes, gpt-5.4 fast mode is the specified model constraint for live OpenAI QA suite execution, satisfying lane selection constraints while running and monitoring your end-to-end scenarios.

Do I need 1Password credentials to source QA secrets for local environment setup?

Yes, 1Password is required to source QA secrets, mapping provider modes and configuring Telegram, Docker, and Convex environment requirements correctly for local scenario execution.

How does OTEL smoke validation and matrix lane sharding work for e2ee coverage?

OTEL smoke validation works by performing local trace validation, while matrix lane sharding partitions transport, media, and e2ee coverage across multiple lanes for comprehensive scenario testing.

Why does my matrix testing fail to verify artifact paths after sharded coverage runs?

Matrix testing fails artifact path verification when output directories are misconfigured, requiring you to explicitly output artifacts to a verified local path like .artifacts/qa-e2e after running sharded lanes.