New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Playwright CLI

by Asymmetric-al in Asymmetric-al/core

Use Playwright CLI for ad hoc browser automation and interactive verification of Core UI: opening local routes, navigating, inspecting snapshots, using element refs, checking console/network…

AGPL-3.0Auto-check passedTesting & QA

Install Playwright CLI

skills CLI
$ npx skills add Asymmetric-al/core --skill playwright-cli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Asymmetric-al/core playwright-cli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Asymmetric-al/core.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/playwright-cli .claude/skills/playwright-cli && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
playwright-cli
GitHub stars
381
Token cost
~1.2k tokens
SKILL.md length
516 words
Files
2 (incl. references)
Skills in repo
41
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Use Playwright CLI for ad hoc browser automation and interactive verification of Core UI: opening local routes, navigating, inspecting snapshots, using element refs, checking console/network…

  • Works in 6 steps: Find the target. Check whether the… → Open and snapshot. Open the route and… → Act through user-facing controls. Prefer… → …
  • Tasks that involve Browser testing
  • SKILL.md covers Boundary, Workflow, Compact command set and Checklist, plus 1 more section
  • Calls bunx

What it does

Playwright CLI is an agent skill from Asymmetric-al/core. Use Playwright CLI for ad hoc browser automation and interactive verification of Core UI: opening local routes, navigating, inspecting snapshots, using element refs, checking console/network activity, capturing evidence, tracing, and reproducing flows. Do not use it as a substitute for committed @playwright/test coverage or for non-browser unit tests.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/upstream.md`).

It sits in Testing & QA, covering Browser testing, Browser automation and Unit testing. It works with Playwright. The repository describes itself as: A high-performance, enterprise-grade Next.js 16 application for mission-focused non-profit organizations. Built for high impact teams. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Browser testing
  • Tasks that involve Browser automation
  • Tasks that involve Unit testing

Example prompts

  • “/playwright-cli”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Find the target. Check whether the relevant Core dev server is already
  2. Open and snapshot. Open the route and save a shallow snapshot under
  3. Act through user-facing controls. Prefer snapshot refs or role locators.
  4. Observe the result. Confirm visible state and URL, then inspect console
  5. Capture bounded evidence. Store screenshots, traces, videos, PDFs, and
  6. Close the session. Close browsers and clean up disposable routes/mocks.

What it can do on your machine

Read from SKILL.md and the folder at commit 21e861c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bunx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use bunx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Playwright CLI loads about 1.2k tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 516 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Asymmetric-al/core at commit 21e861c, republished under its AGPL-3.0 licence (© Asymmetric-al). 516 words, ~1,181 tokens.

Download SKILL.mdSave it as .claude/skills/playwright-cli/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
playwright-cli
description
Use Playwright CLI for ad hoc browser automation and interactive verification of Core UI: opening local routes, navigating, inspecting snapshots, using element refs, checking console/network activity, capturing evidence, tracing, and reproducing flows. Do not use it as a substitute for committed `@playwright/test` coverage or for non-browser unit tests.

Playwright CLI in Core

Use Playwright CLI as a token-efficient interactive browser driver. Keep Core's committed Playwright Test suites as the regression and CI source of truth.

Boundary

  • Use this skill to inspect a running app, reproduce a UI problem, exercise a flow, or gather browser evidence.
  • Use docs/ai/skills/playwright-best-practices/SKILL.md when authoring or repairing @playwright/test specs.
  • Use docs/ai/skills/accessibility-review/SKILL.md for accessibility review; a CLI snapshot is useful evidence but is not an axe or WCAG audit.
  • Do not add @playwright/cli to package.json for one-off agent work. Prefer an available playwright-cli binary; otherwise use a Bun one-off invocation.
  • The CLI compares .agents/skills/playwright-cli and .claude/skills/playwright-cli byte-for-byte with its bundled generic skill. Core's repository-adapted skill intentionally differs, so the CLI may print a version-mismatch notice. Do not run its suggested install --skills command; that would overwrite generated mirrors. Refresh the canonical skill and run Core's sync workflow instead.

Start by checking the live command surface:

bash
playwright-cli --help
# If the binary is unavailable:
bunx --bun @playwright/cli@latest --help

Use the same available command prefix for the rest of the session. Help output is authoritative because the CLI evolves independently of Core's pinned @playwright/test package.

Workflow

  1. Find the target. Check whether the relevant Core dev server is already running before starting one. Confirm the exact local URL and expected app state; use Next.js devtools when it can answer route/runtime questions.
  2. Open and snapshot. Open the route and save a shallow snapshot under ignored test-results/; the CLI's default .playwright-cli/ output would dirty this repository. Use find or a focused element snapshot rather than loading an unnecessarily large page tree.
  3. Act through user-facing controls. Prefer snapshot refs or role locators. Refresh the snapshot after navigation or material DOM changes because refs are session state, not durable test selectors.
  4. Observe the result. Confirm visible state and URL, then inspect console messages and network requests when the claim depends on runtime behavior. Use tracing only for failures that need a timeline.
  5. Capture bounded evidence. Store screenshots, traces, videos, PDFs, and saved auth state only under ignored test-results/ or .auth/ paths. Never print, persist, or commit credentials, cookies, service tokens, or Vercel bypass secrets.
  6. Close the session. Close browsers and clean up disposable routes/mocks. If the behavior can regress, convert the proof into a committed Playwright Test spec and run the applicable Core package script.
Show full SKILL.md (139 more words)Show less

Compact command set

bash
playwright-cli open http://localhost:3000
playwright-cli snapshot --filename=test-results/playwright-cli/snapshot.yaml --depth=4
playwright-cli find "Sign in"
playwright-cli click e15
playwright-cli fill e21 "demo value"
playwright-cli press Enter
playwright-cli console error
playwright-cli requests
playwright-cli screenshot --filename=test-results/playwright-cli/result.png
playwright-cli close

For multiple roles or apps, use named sessions (-s=<name>) rather than sharing cookies or page state. Prefer demo/test accounts and Core's existing auth helpers. Do not use eval or storage mutation to bypass the behavior being verified; reserve them for narrow inspection or explicitly tested setup.

Checklist

  • The task needs live browser interaction rather than a unit test or static read.
  • An existing dev server and the exact route were checked first.
  • The CLI help for the available version was consulted.
  • Interactions use current refs or user-facing locators and verify outcomes.
  • Console/network/trace evidence is collected only when relevant.
  • Artifacts and auth state stay in ignored paths with no secrets in output.
  • The session is closed, and regression-worthy behavior becomes a test.

Provenance

See references/upstream.md for the reviewed official source, Apache-2.0 license, Core adaptations, and refresh workflow.

© Asymmetric-al, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .agents/skills/playwright-cli of Asymmetric-al/core.

  • SKILL.md
  • references/upstream.md

Open the folder on GitHubat commit 21e861c

Compare with similar skills

Playwright CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Playwright CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Playwright CLI this skillAsymmetric-al/core381—~1.2kAutomated safety check: PassAGPL-3.0
Playwright Testingchongdashu/vibejam-starter-pack149—~2.2kAutomated safety check: PassNone
Dotnet Testingnovotnyllc/dotnet-artisan233—~972Automated safety check: PassMIT
E2E Agent Browserjh941213/my-cc-harness126—~3.1kAutomated safety check: NotesNone
PlaywrightEliasOulkadi/shokunin114—~3.6kAutomated safety check: NotesMIT
playwright-cli Browser Automationgithub/gh-aw5.4k24 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Playwright Testing

    chongdashu/vibejam-starter-pack

    Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y.

    149 GitHub stars~2.2k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed

  • Dotnet Testing

    novotnyllc/dotnet-artisan

    Defines .NET test strategy and implementation patterns across xUnit v3 (Facts, Theories, fixtures, IAsyncLifetime), integration testing (WebApplicationFactory, Testcontainers), Aspire testing…

    233 GitHub stars~972 tokensUpdated today
    Testing & QAAuto-check passed

  • E2E Agent Browser

    jh941213/my-cc-harness

    E2E test automation using agent-browser CLI. An agent skill from jh941213/my-cc-harness.

    126 GitHub stars~3.1k tokensUpdated 2 mo ago
    Testing & QAAuto-check: notes

  • Playwright

    EliasOulkadi/shokunin

    Browser automation, web scraping, E2E testing, and visual regression with Playwright.

    114 GitHub stars~3.6k tokensUpdated 3 days ago
    Testing & QAAuto-check: notes

  • playwright-cli Browser Automation

    github/gh-aw

    Official

    Drives a real browser from the command line with playwright-cli to open pages, interact, mock requests, save state and work with Playwright tests.

    5.4k GitHub starsUsed in 24 repos~2.8k tokens
    Testing & QAAuto-check passed

  • Debug Playwright Prow

    quay/quay

    Deep-dive diagnosis of a Playwright test failure already isolated to one Quay Prow/OpenShift CI run: downloads its GCS artifacts (results.json, JUnit, build/pod logs, Jaeger traces), classifies real…

    2.8k GitHub stars~2.2k tokensUpdated today
    Testing & QAAuto-check passed

More from Asymmetric-al/core

All 41 skills in this repo

  • Idempotency Handling

    Asymmetric-al/core

    Implement idempotency keys and handling to ensure operations can be safely retried without duplicate effects.

    381 GitHub stars~867 tokensUpdated today
    Auto-check passed

  • Accessibility Review

    Asymmetric-al/core

    Audit and fix accessibility in Core UI. An agent skill from Asymmetric-al/core.

    381 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Agent Email Inbox

    Asymmetric-al/core

    A skill your agent uses when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted…

    381 GitHub stars~4.1k tokensUpdated today
    Auto-check: notes

  • Components Build

    Asymmetric-al/core

    Build modern, composable, and accessible React UI components following the components.build specification.

    381 GitHub stars~2.1k tokensUpdated today
    Auto-check passed

  • Create Agent

    Asymmetric-al/core

    Guides a one-question-at-a-time design interview, captures alignment in agent/EVE-BRIEF.md, then scaffolds and implements a runnable eve agent with verbose teaching comments.

    381 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes

  • Emil Design Engineering

    Asymmetric-al/core

    Design engineering principles and patterns for building polished, accessible web interfaces.

    381 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Playwright CLI

What does Playwright CLI do?

Use Playwright CLI for ad hoc browser automation and interactive verification of Core UI: opening local routes, navigating, inspecting snapshots, using element refs, checking console/network…. Playwright CLI is an agent skill from Asymmetric-al/core. Use Playwright CLI for ad hoc browser automation and interactive verification of Core UI: opening local routes, navigating, inspecting snapshots, using element refs, checking console/network activity, capturing evidence, tracing, and reproducing flows.

When should I use Playwright CLI?

Playwright CLI fits situations like: tasks that involve Browser testing; tasks that involve Browser automation; tasks that involve Unit testing.

How do I install Playwright CLI in Claude Code?

Run `npx skills add Asymmetric-al/core --skill playwright-cli -a claude-code`. Or copy the skill folder (.agents/skills/playwright-cli in Asymmetric-al/core) into .claude/skills/playwright-cli in your project. Claude Code loads it when a task matches its description.

How do I install Playwright CLI in Codex?

Run `npx skills add Asymmetric-al/core --skill playwright-cli -a codex`. Or copy the skill folder (.agents/skills/playwright-cli in Asymmetric-al/core) into .agents/skills/playwright-cli in your project. Codex loads it when a task matches its description.

Can I use Playwright CLI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Asymmetric-al/core --skill playwright-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/playwright-cli, .gemini/skills/playwright-cli, .github/skills/playwright-cli and .opencode/skills/playwright-cli in your project.

What does Playwright CLI need to run?

Going by SKILL.md and its folder, Playwright CLI needs the command-line tools its instructions call (bunx).

Does Playwright CLI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Playwright CLI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Playwright CLI use?

Playwright CLI is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Playwright CLI use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 451 tokens, read only when the agent opens those files.

What are the alternatives to Playwright CLI?

Skills that share tags, products or a category with Playwright CLI: Playwright Testing (chongdashu/vibejam-starter-pack, 149 stars), Dotnet Testing (novotnyllc/dotnet-artisan, 233 stars), E2E Agent Browser (jh941213/my-cc-harness, 126 stars) and Playwright (EliasOulkadi/shokunin, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Playwright CLI?

Asymmetric-al (a GitHub organization) maintains it in Asymmetric-al/core, which has 381 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 8, 2026.

Source: Asymmetric-al/core on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.