QA Manual — Testing & QA agent for Claude Code
Manual tester of a /qa test session — checks the feature on the environment per the manual-task.md brief; creates the TMS case when test-cases: inline, and with upfront runs the analyst's ready.
How to install QA Manual
Installs to ~/.claude/agents/codecube01-qa-cube-qa-manual.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/codecube01/qa-cube/HEAD/agents/qa-manual.md -o ~/.claude/agents/codecube01-qa-cube-qa-manual.md Restart Claude Code, or start a new session, for it to be picked up.
What QA Manual does
name: qa-manual description: Manual tester of a /qa test session — checks the feature on the environment per the *manual-task*.md brief; creates the TMS case when `test-cases: inline`, and with `upfront` runs the analyst's ready-made cases. Writes no autotests (that is qa-automator). Works autonomously, asks the user nothing.
You are QA Manual: the manual tester. You work from the brief in the file named in your prompt (`*manual-task*.md` in the session folder). Your job is to check the
Alternatives in Testing & QA
- Fable Verifier — Cold verifier for finished fable deliverables 837 ★
- QA Debug Analyst 597 ★
- QA Manual Tester — Use this agent when you need to perform manual quality assurance testing through browser interactions 394 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
QA Analyst
Test analyst of a /qa test session — writes test cases from the requirements BEFORE the manual run (TMS or fil
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
AI Tester
Runs the project's tests for a change and classifies the outcome as PASS, EXISTING TEST FAILURE, NEW REGRESSIO
Test Case Designer
Invoked after test-coverage-analyst has produced a gap report, or when the user says "design test cases for "
API Exploratory Tester
Performs spec-aware, contract-aware session-based exploratory testing of a live API — REST or GraphQL — given
Related Skills
Execute Test Cases
Thực thi manual test cases trên browser thật qua Playwright MCP — chấm PASS/FAIL/BLOCKED/SKIPPED, thu evidence
Scaffold Plugin Test
Scaffold a headless behavior test for a werkstoff plugin skill — a seeded-defect fixture plus a case in test/p
Test Plan Flow
A workflow for turning a tracker issue into reviewed manual test cases — review depth decided by criticality t