playwright-qa — Claude Code skill: what it does, how to install
playwright-qa organizes QA work around Playwright, from test design and failure triage to manual-case migration and test review.
MIT 463 installs ★ 422 updated 2026-10-12
npx skills add testdino-hq/playwright-skill --skill playwright-qa -a claude-codeWhat playwright-qa does
playwright-qa covers the work around Playwright test code. It turns tickets, PRDs, and acceptance criteria into test cases, ranks risks, and prepares a plan for automation. It can also inspect a failing test or trace and separate an application defect from a test defect, a flake, or an environment problem.
The skill converts manual cases from TestRail, Xray, or CSV into Playwright specs while keeping case IDs attached to the automated tests. Its review workflow covers Playwright tests and pull requests, checks whether a test can actually fail, and uses test.fail() with an issue link for known bugs. Repetition is quantified with --repeat-each=20.
Case IDs are required for traceability during manual-suite migration, so dropping them breaks the link to the original cases.
What it helps with
- turn a ticket or acceptance criteria into test cases
- rank risks and outline an automation plan
- classify a failure from a test or trace
- convert TestRail, Xray, or CSV cases into Playwright specs
- review Playwright tests and pull requests
Example prompts for the agent
- Design test cases and an automation plan from this ticket and its acceptance criteria.
- Inspect this failing test and trace, then classify the issue as an app bug, test bug, flake, or environment problem.
- Convert these CSV cases into Playwright specs and keep their case IDs.
How to install playwright-qa
1Skills CLI (Vercel)
npx skills add testdino-hq/playwright-skill --skill playwright-qa -a claude-code2Manually: put the files in place
~/.claude/skills/qa/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/qa/
1Skills CLI (Vercel)
npx skills add testdino-hq/playwright-skill --skill playwright-qa -a codex2Manually: put the files in place
.agents/skills/qa/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add testdino-hq/playwright-skill --skill playwright-qa -a cursor2Manually: put the files in place
.cursor/skills/qa/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install testdino-hq/playwright-skill qa2Manually: put the files in place
.github/skills/qa/SKILL.md1Skills CLI (Vercel)
npx skills add testdino-hq/playwright-skill --skill playwright-qa -a gemini-cli2Platform CLI
gemini skills install https://github.com/testdino-hq/playwright-skill --path qaManually: put the files in place
.devin/skills/qa/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add testdino-hq/playwright-skill --skill playwright-qa -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about playwright-qa
How do I install playwright-qa in Claude Code?
Run npx skills add testdino-hq/playwright-skill --skill playwright-qa -a claude-code, then check ~/.claude/skills/qa/SKILL.md.
What does playwright-qa do?
It supports test design from requirements, failure triage, manual-case conversion to Playwright, and reviews of Playwright tests and pull requests.
How does playwright-qa preserve manual test traceability?
When cases come from TestRail, Xray, or CSV, the skill keeps their case IDs on the generated automated tests so results map back to the manual suite.
Source text
SKILL.md · MIT
--- name: playwright-qa description: QA engineering workflows on top of Playwright. Use when a QA engineer asks to design test cases from a ticket, PRD or acceptance criteria, decide what to automate, write a bug report from a failing test or trace, convert manual test cases (TestRail, Xray, CSV) into Playwright specs with case-ID traceability, or review Playwright test code and pull requests. --- # Playwright QA Workflows > For **QA engineers**: the work around the test code. What to test, how to report what broke, how to automate a manual suite, and how to judge a test. **4 guides**. They build on the `core/` guides for the Playwright APIs and link to them rather than repeating them. ## Guide Index | What you're doing | Guide | |---|---| | Ticket / PRD / acceptance criteria → test cases, risk ranking, test plan for the generator | [test-design.md](test-design.md) | | Failing test → app bug, test bug or flake; bug report; what to do with the test meanwhile | [bug-reports.md](bug-reports.md) | | Manual test cases or a CSV export → Playwright specs with case IDs | [manual-to-automated.md](manual-to-automated.md) | | Review Playwright tests or a PR; lint rules; prove a test can fail | [test-review.md](test-review.md) | ## Golden Rules 1. **Boundaries and negative paths first**: bugs live at the edges of a rule, not in the happy path. 2. **Lowest layer that proves it**: rules at API level, wiring and critical flows in E2E. 3. **Classify before filing**: app bug, test bug, flake or environment; the trace usually decides. 4. **Frequency is a number**: `--repeat-each=20` gives N/20, never "sometimes". 5. **Known bug → `test.fail()` with an issue link**, never a deleted test or a loosened assertion. 6. **A test that can't fail guards nothing**: break the feature once and watch it fail. 7. **Keep case IDs on automated tests** so results map back to the manual suite.
© testdino-hq · MIT · testdino-hq/playwright-skill