agentleFS
Sign inStart free
kuker24kuker24/OpenCodeBestFriend/skills/playwright-qa/SKILL.md

playwright-qa

Skill0 starsChanged 2 months agoMITView on GitHub

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).

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Primary Exploratory QA: Use Playwright CLI to explore and verify UI changes built in the current session (navigation, form inputs, button …

    line 17
  2. Very specific:

    Respect Project Test Suites: If the project already configures Playwright Test, Cypress, or another runner, run regressions through the …

    line 18
  3. Very specific:

    No Phantom Installations: Check actual runtime capabilities before executing browser commands.

    line 19
  4. Very specific:

    Isolated Task Sessions: Every browser interaction must use a scoped session name (-s=<task-id>) bound to the current task/workspace.

    line 20
  5. Distinctive:

    Headless & Chromium Default: Default to headless Chromium with an isolated profile.

    line 21
  6. Distinctive:

    No Browser for Backend: Never start browser sessions when only backend, API, database, or non-UI code changed.

    line 24
  7. Distinctive:

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

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

  1. 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.

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free