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
- QA Manual Tester — Use this agent when you need to perform manual quality assurance testing through browser interactions 394 ★
- Resource Manager — Use BEFORE dispatching any TEST-RUNNING subagent (a builder, a fix-subagent, qa-engineer) to get a GO/HOLD ver 71 ★
- Worca Cc Manual Tests Checklist — Manual Tests Checklist author for the orchestrator pipeline 31 ★
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
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
Uft Converter
Assembles the conversion plan for a UFT test from the three upstream artifacts and writes 04-proposal.md plus
AI Tester
Runs the project's tests for a change and classifies the outcome as PASS, EXISTING TEST FAILURE, NEW REGRESSIO
Related Skills
Test Plan Flow
A workflow for turning a tracker issue into reviewed manual test cases — review depth decided by criticality t
Execute Test Cases
Thực thi manual test cases trên browser thật qua Playwright MCP — chấm PASS/FAIL/BLOCKED/SKIPPED, thu evidence
Archive Ticket
Move a resolved per-ticket scratchpad from tickets/ into tickets/archive/, then note the archival in SESSION-L