QA Analyst — Testing & QA agent for Claude Code
Test analyst of a /qa test session — writes test cases from the requirements BEFORE the manual run (TMS or files), launched by the QA Manager when test-cases: upfront.
How to install QA Analyst
Installs to ~/.claude/agents/codecube01-qa-cube-qa-analyst.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/codecube01/qa-cube/HEAD/agents/qa-analyst.md -o ~/.claude/agents/codecube01-qa-cube-qa-analyst.md Restart Claude Code, or start a new session, for it to be picked up.
What QA Analyst does
name: qa-analyst description: Test analyst of a /qa test session — writes test cases from the requirements BEFORE the manual run (TMS or files), launched by the QA Manager when `test-cases: upfront`. Never touches the environment, never reads code, never files bugs. Works autonomously, asks the user nothing.
You are the QA Analyst: the test analyst. You run between the manager's plan and the manual round. Your job is to turn the plan's scenarios into test cases written **from the requir
Alternatives in Testing & QA
- Worca Cc Manual Tests Checklist — Manual Tests Checklist author for the orchestrator pipeline 31 ★
- Fullstack Manager — Team orchestrator for fullstack development 17 ★
- Confluence Spec Analyst — Read full Confluence spec page (+ children + images) and produce structured Spec Research Report with requirem 14 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
QA Manual
Manual tester of a /qa test session — checks the feature on the environment per the manual-task.md brief; crea
QA Automator
Automation engineer of a /qa test session — writes the autotest from the manual run's evidence, links it to a
Manual Tester
Manual QA analyst. Explores https://www.automationexercise.com/ like a real user, learns the business rules, a
Tms Agent
Use this agent for anything involving the test management REST API - creating test cases from a specs/ .plan.m
ChatGPT Spec Review
Coordinates ChatGPT spec review in a dedicated session (manual ChatGPT-web, automated OpenAI API, or parallel
Parallel Hunt Finder
Finder for a /parallel-hunt round — investigates the live system for real defects, writes evidence and a faili
Related Skills
Limitbar
AI coding limits in the macOS menu bar — Claude Code, Codex, Gemini (Antigravity), Grok. Never touches your cr
Gemini Summarize
Use Gemini to summarize a file or folder of files. Gemini reads them in its 1M context — Claude never touches
Clifleet
CliFleet — a 3 MB native, portable workbench for running several AI coding CLIs side by side. One folder, many