qa-tester

Execute repository QA plans serially and record results in QA_TEST_PROGRESS.md.

Updated Apr 15, 2026
One-click install
npx skills add https://github.com/CvNoobLrx/rag-mcp-modular-agent --skill qa-tester-cvnooblrx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qa-tester
Source: https://github.com/CvNoobLrx/rag-mcp-modular-agent/tree/main/.claude/skills/qa-tester
Command: npx skills add https://github.com/CvNoobLrx/rag-mcp-modular-agent --skill qa-tester-cvnooblrx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires argparse, shutil, subprocess, sys, pathlib, json, tempfile, time, re, yaml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill removes the burden of manually executing a large, multi-layer QA plan for the Modular RAG MCP Server by automating test selection, execution, validation, and retry-driven fixes.

Core Features & Use Cases

  • End-to-end QA automation: Runs CLI, Dashboard UI, MCP protocol, provider-switch, config-failure, and data-lifecycle tests in a strictly serial workflow.
  • Failure diagnosis and repair: Detects failures, applies minimal fixes, retries up to three times, and records outcomes in QA_TEST_PROGRESS.md.
  • Use case: A developer asks to run the full QA suite after changes, and the Skill executes the plan, validates evidence, and reports pass or fail results with concrete terminal output.

Quick Start

Use the qa-tester skill to run the next pending QA test for this repository and record the result in QA_TEST_PROGRESS.md.

Frequently Asked Questions about qa-tester

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

FAQPage Schema
How do I automate QA test execution and fix failures automatically?

Automating QA test execution and fixing failures involves running serial test workflows with deterministic state setup. This Skill executes repository QA plans across CLI, dashboard, and MCP scenarios, applies retry-based fixes for failures, and records structured outcomes in QA_TEST_PROGRESS.md.

What is stepwise verification in serial test workflows?

Stepwise verification in serial test workflows is a mechanism that validates terminal evidence after each deterministic state setup. It ensures that CLI, dashboard, and MCP protocol tests pass sequentially before moving forward, applying minimal fixes and retrying up to three times on failure.

How do I run end-to-end QA automation for an MCP server?

Running end-to-end QA automation for an MCP server requires executing layered tests including CLI, Dashboard UI, MCP protocol, provider-switch, and data-lifecycle scenarios. This Skill automates this strictly serial workflow, validating terminal evidence and updating progress tracking files.

Does this QA automation tool support Streamlit dashboard testing?

Yes, this QA automation supports Streamlit dashboard testing as part of its end-to-end workflow. It executes dashboard UI tests alongside CLI, MCP protocol, configuration failure, and data-lifecycle scenarios within a strictly serial execution pipeline.

What are the limitations of retry-based fixes in QA testing?

Retry-based fixes in QA testing are limited to three attempts per failed test. If the minimal fixes applied do not resolve the failure after three retries, the workflow stops and records the negative outcome with concrete terminal output in the progress tracking file.