Skip to content
SkillMixed1,683 tokens in use

Playwright Skill

Lets a coding agent write and run its own Playwright scripts to test sites, check layouts, fill forms and capture screenshots.

3,306 stars on the repository MIT Licenselackeyjb/playwright-skill · skills/playwright-skill
npx skills add lackeyjb/playwright-skill --skill playwright-skill --global --yes
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Playwright Skill costs

69tokens idle
1,683tokens in use
5,639tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: lib/helpers.js, run.js.

Touches

shelldeclared and detectednetworkdetectedwrites filesdeclared and detectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources3/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−2

    does this on the machine, as the frontmatter declares

    SKILL.md, line 24
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 155
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    lib/helpers.js, line 95
  • Writes files−4

    does this on the machine, as the frontmatter declares

    run.js, line 79

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Fair
  • Development activity40
  • Maintenance44
  • Community48
  • Maturity36
  • Momentum40

Playwright Skill gives an agent a small executor and helper library for browser automation. The agent writes a focused Playwright script for your request, runs it through run.js and reports what happened, with screenshots and console output.

It finds running dev servers on localhost, opens a visible browser by default, and covers responsive checks, login flows, link checks, network interception and attaching to an existing Chrome session. A full API reference loads only when a task needs it.

What You Get

  • A run.js executor that runs script files or inline snippets with Playwright resolved
  • A helper library for dev-server detection, browser launch, contexts, cookie banners and screenshots
  • A step-by-step workflow with locator guidance and a rule to confirm the page before claiming success
  • An API reference covering network interception, authentication state, video, device emulation and CI patterns

Common Use Cases

  • Test a local site after a change and capture screenshots
  • Check a layout at desktop and mobile viewport sizes
  • Run a login flow with test credentials and verify the dashboard
  • Find broken links or check that images load
  • Fill and submit a form to see how validation behaves

What Makes It Unique

The skill treats the script as the product. Scripts can be kept and rerun by setting a save folder, dev-server detection picks the local URL for you, and the browser is visible by default so you can watch. The README points to Microsoft’s playwright-cli and playwright-mcp for simple interactive browsing and positions this skill for cases where the automation code itself is worth keeping.

Under The Hood

SKILL.md allows the agent to run node and npm commands and to read and write files. First setup runs npm install and downloads Playwright and Chromium over the network. The agent then writes scripts to your temp folder, or to a folder you choose, and runs them with run.js, which starts a Node child process with the skill’s modules on the path. The browser it launches can open any URL you give it, including localhost sites, and the dev-server helper checks local ports for running servers. The skill can also attach to an existing Chrome session with remote debugging, which shares that browser’s cookies, and it warns against using that for secrets unless you ask. Test credentials are read from environment variables you provide.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers