# qa-expert

qa-expert — a subagent for designing test strategies, executing comprehensive tests, tracking defects, and assessing product quality. Helps identify issues early, build confidence in releases, and deliver data-driven quality reports.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 1357 repo stars
- Author: qdhenry
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/quality-testing/qa-expert.md
- Updated: 2026-03-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/qdhenry-qa-expert

## What it does

qa-expert develops test strategies and plans, designs test cases, and conducts functional, performance, and security testing. It includes tools for browser automation via Playwright, repository analysis, and root cause investigation of defects.

The subagent emphasizes prevention: catching problems during development rather than in production. It maintains documentation for test cases, bug reports, and quality metrics needed to communicate results to stakeholders.

Built for Claude Code and compatible with Codex and Cursor through configuration files placed in project directories.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/qa-expert.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/qa-expert.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/qa-expert.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/quality-testing/qa-expert.md

## When to use it
- design a testing strategy with scope definition and risk assessment
- create and document test cases covering functionality, edge cases, and UI
- automate browser-based testing workflows and capture failure evidence
- track defects, determine root causes, and report findings
- measure quality metrics and present results to the team

## Example prompts
- Design a test plan for the authentication module with risk prioritization
- Write test cases for the payment form including boundary conditions
- Run automated end-to-end tests for signup flows using Playwright

## Similar
- [selector-drift-recovery](https://affpapa.org/en/nevibecode/skills/selector-drift-recovery.md) — skill · 1300 installs
- [qp-run](https://affpapa.org/en/nevibecode/skills/qp-run.md) — skill · ★ 33 repo stars
- [playwright-typescript](https://affpapa.org/en/nevibecode/rules/playwright-typescript.md) — rule · ★ 41430 repo stars
- [qa-orchestra](https://affpapa.org/en/nevibecode/plugins/qa-orchestra.md) — plugin · ★ 14 repo stars
- [test-reliability](https://affpapa.org/en/nevibecode/skills/test-reliability.md) — skill · 1500 installs
- [playwright-qa](https://affpapa.org/en/nevibecode/skills/playwright-qa.md) — skill · 463 installs

## Other versions with the same name
- [qa-expert · voltagent](https://affpapa.org/en/nevibecode/agents/qa-expert.md) — 980 installs
- [qa-expert · voltagent](https://affpapa.org/en/nevibecode/agents/voltagent-qa-expert.md) — ★ 6505 repo stars

From the same set: [qdhenry/claude-command-suite](https://affpapa.org/en/nevibecode/by/qdhenry/claude-command-suite.md) — 112 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
