Works with
Packaged from the source skill for Claude, Codex and 4 more.
About this skill
Playwright Skill is Bryan Lackey's browser automation skill for Claude Code. It guides an agent to write focused JavaScript scripts, run them through the bundled Node.js executor and inspect the resulting page before reporting success.
The package includes run.js, browser helpers, an API reference and npm dependency manifests. It can support targeted checks against a local development server or an explicitly provided website. The Playwright library and browser binaries are separate dependencies installed during setup.
Use this skill when
- You need a repeatable browser check for a website change.
- A form, sign-in flow or navigation path needs validation through visible page behavior.
- You want screenshots at desktop and mobile viewport sizes.
- You need a reusable script for link checks, browser errors or a narrow user journey.
What it can do
- Detect common localhost development-server ports and make the target URL explicit.
- Write file-based or short inline Playwright scripts through the bundled executor.
- Use locators, page readiness checks and assertions to verify observable outcomes.
- Capture screenshots and preserve scripts in caller-selected output directories.
- Configure browser choice, headed or headless mode, request headers and artifact paths.
Typical workflows
- Identify the authorized target URL, required browser and concrete success condition.
- Prepare the Node.js and Playwright dependencies in the skill directory.
- Write a small reusable script for the requested page or flow.
- Run the script, inspect the page or artifacts, and report failures with their reproduction steps.
Inputs and output
Provide a target URL, the user journey to check, expected outcomes and any authorized test-account credentials through the environment. Outputs can include a reusable JavaScript script, screenshots, assertion results and a concise failure report.
Limitations
The upstream setup requires Node.js 20 or newer, npm and network access to install Playwright and browser binaries; those binaries are not included in the ZIP. Some advanced API-reference examples require additional packages such as @playwright/test or axe-playwright. Browser automation can change data and expose an authenticated session, so use authorized test accounts and review scripts before running them. The bundled helper disables Chromium's sandbox when run as root; prefer an unprivileged development account. The catalog has inspected package completeness but has not executed this skill or verified website-specific outcomes.
What is inside the skill
Section headings from the original SKILL.md (about 539 words of instructions). Read the full text in the source repository before installing.
- Path resolution
- Workflow
- Setup
- Minimal example
- Current Playwright patterns
- Common tasks
- Responsive checks
- Login flow
- Save scripts and artifacts
- Connect to an existing Chrome session
- Helpers
- Configuration
Bundled files
API_REFERENCE.mdlib/helpers.jspackage-lock.jsonpackage.jsonrun.jsLICENSE
Example prompts
- Check the local checkout page at http://localhost:3000 using Playwright. Exercise an empty cart and a valid test cart, verify visible success or error messages, and save screenshots at 1440 by 900 and 390 by 844.
- Create a reusable browser test for our staging sign-in flow using the test account supplied through environment variables. Verify the dashboard heading after sign-in and confirm that signing out returns to the public page. Never print the credentials.
- Audit the links on our documentation landing page without submitting any forms. Save a reusable script, report broken destinations and JavaScript errors, and include a screenshot of the mobile navigation.
How to install Playwright Skill
Claude Packaged
- Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files.
- For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
- For Claude apps, upload the ZIP in the Skills section of the capabilities settings.
- Start a new session and describe the task in your own words. Claude picks the skill when the request matches its description.
Codex Packaged
- Download the Codex package. The ZIP contains one folder named after the skill, with SKILL.md and bundled resources.
- Unpack the complete folder into .agents/skills/ inside your repository, or into ~/.agents/skills/ for personal use. Preserve its relative reference-file paths.
- Start a new Codex session and invoke the skill by name or with $skill-name, or describe a matching task.
- AGENTS.md is separate project guidance. The ZIP does not generate or modify that file.
GPT Packaged
- Download the GPT package from the skill page.
- Create or edit a custom GPT (or a ChatGPT project) and paste the contents of SKILL.md into the instructions field.
- Upload the bundled reference files as knowledge so the GPT can consult them.
- Test with one of the example prompts from the skill page and adjust the instructions if your use case differs.
Gemini Packaged
- Download the Gemini package from the skill page.
- For a project, unpack the complete folder into .gemini/skills/ or .agents/skills/. For personal use, use ~/.gemini/skills/ or ~/.agents/skills/.
- Run /skills reload in Gemini CLI, then /skills list to check discovery. There is no need to paste the skill into GEMINI.md.
- Test a matching task and verify the referenced tools and files are available.
Cursor Packaged
- Download the Cursor package from the skill page.
- Unpack the complete skill folder into .cursor/skills/ or .agents/skills/ in your project. For personal local use, ~/.cursor/skills/ and ~/.agents/skills/ are also supported.
- Start a new Cursor session. Type / in Agent chat and select the skill name, or describe a matching task.
- Commit the skill folder and resources for team use. Personal local skills are not automatically available to remote agents or automation runs.
OpenCode Packaged
- Download the OpenCode package from the skill page.
- Unpack the complete folder into .opencode/skills/ in your project, or ~/.config/opencode/skills/ for personal use. OpenCode also supports .agents/skills/ and .claude/skills/ compatibility locations.
- Keep supporting files at their original relative paths. AGENTS.md is separate project-wide guidance and is not generated by this ZIP.
- Start OpenCode in the project and test a matching task with the model and permissions you use.
Permissions & security
Inspect the source, license and declared permissions before use. Read the scripts before running them. Review method
Playwright Skill FAQ
What does the Playwright Skill skill do?
A Playwright skill for Claude Code that creates reusable browser checks, screenshots and login-flow tests, with a Node.js executor and local development-server helpers.
Which AI agents can use Playwright Skill?
Packages for Claude, Codex and 4 more are built from the same source instructions.
How do I install Playwright Skill in Claude?
Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
Who made Playwright Skill and what is the license?
Playwright Skill is published by Bryan Lackey under the MIT license. The source is https://github.com/lackeyjb/playwright-skill/tree/main/skills/playwright-skill. The catalog keeps the original attribution.
What permissions does Playwright Skill need?
Declared permissions: read project files, write generated skill files. Risk level: low. Check the scripts in the source before running them.