How do I install the Playwright QA skill?

Run npx skillmds@latest add kuker24/playwright-qa in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Playwright QA safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Playwright QA?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Playwright QA free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Apache-2.

Who published Playwright QA?

kuker24 (@kuker24) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Playwright QA by kuker24 — Agent Skill

Name: Playwright QA
Author: kuker24

Playwright QA

Primary exploratory browser QA adapter for web applications under development. Use to navigate local UI, exercise forms, inspect rendered DOM/state, take snapshots and screenshots, and verify visual flows via Playwright CLI. Respects existing project test suites (Playwright Test/Cypress) for regressions. Skip for backend-only tasks, explicit BrowserAct requests, or deep observed-failure diagnostics (chrome-devtools-axi).

kuker24 58061a7 5 files · 8.9 KB Updated Sep 17, 2026

File contents

playwright-qa

OpenCodeBestFriend adapter for exploratory browser QA using Playwright CLI. Adapted from microsoft/playwright-cli (Apache-2.0, Microsoft Corporation).

This skill provides an interactive, token-efficient browser interface for agents to verify UI changes in the application under development without installing large MCP servers or polluting application dependencies.

Core Rules

Primary Exploratory QA: Use Playwright CLI to explore and verify UI changes built in the current session (navigation, form inputs, button clicks, state assertions, screenshots).
Respect Project Test Suites: If the project already configures Playwright Test, Cypress, or another runner, run regressions through the project's own package manager and scripts (e.g. npx playwright test). Never replace or shadow the project's config.
No Phantom Installations: Check actual runtime capabilities before executing browser commands. Never run unguided npx that triggers implicit downloads during discovery.
Isolated Task Sessions: Every browser interaction must use a scoped session name (-s=<task-id>) bound to the current task/workspace. Never use global close-all or kill-all.
Headless & Chromium Default: Default to headless Chromium with an isolated profile. Never bind to personal Google Chrome profiles or force Chrome executables unless explicitly requested.
Port Separation: Port 9223 is reserved for opencode-chromium-cdp / chrome-devtools-axi. Do not force Playwright sessions through port 9223.
Privacy & Hygiene: Storage state, cookies, HAR recordings, traces, and screenshots must never be committed to git or printed with sensitive credentials.
No Browser for Backend: Never start browser sessions when only backend, API, database, or non-UI code changed.

Workflow

Follow the QA loop: understand flow -> run app -> open session -> observe/interact -> assert state -> close session.

# 1. Open isolated task session
playwright-cli -s=task-ui open http://localhost:3000

# 2. Inspect page structure (captures semantic refs e1, e2...)
playwright-cli -s=task-ui snapshot

# 3. Interact using snapshot refs or locators
playwright-cli -s=task-ui click e4
playwright-cli -s=task-ui fill e7 "test user"
playwright-cli -s=task-ui press Enter

# 4. Verify outcome with fresh snapshot or screenshot
playwright-cli -s=task-ui snapshot
playwright-cli -s=task-ui screenshot --filename=artifacts/qa-verify.png

# 5. Clean up task session
playwright-cli -s=task-ui close

References

Operational QA flow & assertions: references/workflow.md
Session isolation & cleanup: references/sessions.md
Setup, runtime discovery, & dependency boundaries: references/setup.md

---name: playwright-qadescription: Primary exploratory browser QA adapter for web applications under development. Use to navigate local UI, exercise forms, inspect rendered DOM/state, take snapshots and screenshots, and verify visual flows via Playwright CLI. Respects existing project test suites (Playwright Test/Cypress) for regressions. Skip for backend-only tasks, explicit BrowserAct requests, or deep observed-failure diagnostics (chrome-devtools-axi).license: Apache-2.0---# playwright-qaOpenCodeBestFriend adapter for exploratory browser QA using Playwright CLI.Adapted from [microsoft/playwright-cli](https://github.com/microsoft/playwright-cli) (Apache-2.0, Microsoft Corporation).This skill provides an interactive, token-efficient browser interface for agents to verify UI changes in the application under development without installing large MCP servers or polluting application dependencies.## Core Rules1. **Primary Exploratory QA**: Use Playwright CLI to explore and verify UI changes built in the current session (navigation, form inputs, button clicks, state assertions, screenshots).2. **Respect Project Test Suites**: If the project already configures Playwright Test, Cypress, or another runner, run regressions through the project's own package manager and scripts (e.g. `npx playwright test`). Never replace or shadow the project's config.3. **No Phantom Installations**: Check actual runtime capabilities before executing browser commands. Never run unguided `npx` that triggers implicit downloads during discovery.4. **Isolated Task Sessions**: Every browser interaction must use a scoped session name (`-s=<task-id>`) bound to the current task/workspace. Never use global `close-all` or `kill-all`.5. **Headless & Chromium Default**: Default to headless Chromium with an isolated profile. Never bind to personal Google Chrome profiles or force Chrome executables unless explicitly requested.6. **Port Separation**: Port 9223 is reserved for `opencode-chromium-cdp` / `chrome-devtools-axi`. Do not force Playwright sessions through port 9223.7. **Privacy & Hygiene**: Storage state, cookies, HAR recordings, traces, and screenshots must never be committed to git or printed with sensitive credentials.8. **No Browser for Backend**: Never start browser sessions when only backend, API, database, or non-UI code changed.## WorkflowFollow the QA loop: **understand flow -> run app -> open session -> observe/interact -> assert state -> close session**.```bash# 1. Open isolated task sessionplaywright-cli -s=task-ui open http://localhost:3000# 2. Inspect page structure (captures semantic refs e1, e2...)playwright-cli -s=task-ui snapshot# 3. Interact using snapshot refs or locatorsplaywright-cli -s=task-ui click e4playwright-cli -s=task-ui fill e7 "test user"playwright-cli -s=task-ui press Enter# 4. Verify outcome with fresh snapshot or screenshotplaywright-cli -s=task-ui snapshotplaywright-cli -s=task-ui screenshot --filename=artifacts/qa-verify.png# 5. Clean up task sessionplaywright-cli -s=task-ui close```## References- Operational QA flow & assertions: [references/workflow.md](references/workflow.md)- Session isolation & cleanup: [references/sessions.md](references/sessions.md)- Setup, runtime discovery, & dependency boundaries: [references/setup.md](references/setup.md)

Frequently asked questions