brikko-studio-qa-testing

Execute and debug Brikko Studio qa-lab and qa-channel QA test suites.

1|Updated May 3, 2026
One-click install
npx skills add https://github.com/brikkoAI/brikko-studio --skill brikko-studio-qa-testing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: brikko-studio-qa-testing
Source: https://github.com/brikkoAI/brikko-studio/tree/main/packages/core/.agents/skills/openclaw-qa-testing
Command: npx skills add https://github.com/brikkoAI/brikko-studio --skill brikko-studio-qa-testing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually running, monitoring, and debugging QA test suites for Brikko Studio's qa-lab and qa-channel is time-consuming and prone to human error, especially when working across multiple test lanes, LLM models, and live test environments.

Core Features & Use Cases

  • End-to-end test execution: Run full qa-lab test suites across mock and live OpenAI lanes, with support for OpenTelemetry smoke tests and configurable matrix profiles for different testing scopes.
  • Scenario debugging and extension: Debug failing test scenarios, extend the QA suite with new end-to-end test cases, and run character/persona evaluations across multiple LLM backends to validate response consistency and style.
  • Secure credential management: Handle QA secrets for Telegram and Convex live test environments via integrated 1Password workflows, eliminating the need to manually manage sensitive test credentials. Use case: A QA engineer working on Brikko Studio can use this skill to run a full live QA suite, debug a failing E2E messaging scenario, and validate character consistency across 8 different LLM providers without manually constructing test commands or handling sensitive credentials.

Quick Start

Use the brikko-studio-qa-testing skill to run the full live QA suite for the current branch and share the pass/fail counts and test artifact paths with me.

Frequently Asked Questions about brikko-studio-qa-testing

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

FAQPage Schema
How do I run end-to-end QA test suites across multiple LLM providers?

End-to-end QA test suites execute across mock and live OpenAI lanes to validate LLM response consistency. You can run full qa-lab suites using configurable matrix profiles to cover different testing scopes without manual command construction.

What is OpenTelemetry smoke validation in QA testing?

OpenTelemetry smoke validation is a testing mechanism that verifies system observability and tracing during end-to-end test runs. It ensures your test environment correctly captures telemetry data for product validation workflows.

How do I manage live test environment credentials for Telegram and Convex?

Live test environment credentials for Telegram and Convex are managed securely via integrated 1Password workflows. This eliminates the need to manually handle sensitive test credentials during QA suite execution.

Can I debug failing test scenarios and extend the QA suite with new end-to-end test cases?

Yes, you can debug failing test scenarios and extend the QA suite with new end-to-end test cases. This includes running character and persona evaluations across multiple LLM backends to validate response consistency and style.

Does this QA testing approach support privacy contract verification for LLM responses?

Yes, the QA testing approach supports LLM response consistency and privacy contract verification. It validates that LLM backends adhere to expected privacy contracts during end-to-end test execution.

What are the limitations of manual QA test suite execution for multi-model evaluation?

Manual QA test suite execution for multi-model evaluation is time-consuming and prone to human error, especially across multiple test lanes and live test environments. Automated execution with secure credential handling eliminates these bottlenecks.