How do I install the Playwright skill?

Run npx skillmds@latest add kiku-jw/playwright 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 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?

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 free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Playwright?

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

Playwright by kiku-jw — Agent Skill

Name: Playwright
Author: kiku-jw

Playwright

Drive a real browser from the terminal with the bundled Playwright CLI wrapper. Use when the task requires navigation, form filling, snapshots, screenshots, data extraction, or UI-flow debugging without turning the job into a Playwright test suite.

kiku-jw 4f5e184 9 files · 20.7 KB Updated Sep 17, 2026

File contents

Playwright CLI Skill

Metadata

Trigger when: the user needs browser automation or browser-state inspection from the terminal.
Do not use when: the task is to author Playwright test files or when a different built-in browser tool already solves the job better.

Skill Purpose

Provide a deterministic CLI-first browser workflow that always starts from a fresh snapshot and uses stable element refs instead of ad hoc DOM poking.

Instructions

Check prerequisites first: command -v npx >/dev/null 2>&1. If npx is missing, stop and ask the user to install Node/npm. Otherwise use the exact wrapper script at ~/.codex/skills/playwright/scripts/playwright_cli.sh.
Run the core loop through the wrapper: open the page, snapshot, interact using refs from the latest snapshot, and snapshot again after navigation or major DOM change. Use ~/.codex/skills/playwright/references/cli.md for command reference and ~/.codex/skills/playwright/references/workflows.md for troubleshooting only when needed.
Capture artifacts such as screenshots, PDFs, or traces when they help. Keep the workflow explicit and CLI-based; do not pivot into Playwright test code unless the user explicitly asked for test files.

Non-Negotiable Acceptance Criteria

Always snapshot before using element refs like e12.
Re-snapshot after navigation, modal changes, tab switches, or any UI change that could stale refs.
Prefer explicit CLI commands over eval/custom code when the wrapper can already do the job.
Use --headed when a visual check materially helps.

Output

A concise command sequence or workflow summary.
Latest relevant element refs or artifact paths when the task depends on them.
A short note on whether the flow succeeded, stalled on stale refs, or needs a new snapshot.

---name: playwrightdescription: Drive a real browser from the terminal with the bundled Playwright CLI wrapper. Use when the task requires navigation, form filling, snapshots, screenshots, data extraction, or UI-flow debugging without turning the job into a Playwright test suite.---# Playwright CLI Skill## Metadata- Trigger when: the user needs browser automation or browser-state inspection from the terminal.- Do not use when: the task is to author Playwright test files or when a different built-in browser tool already solves the job better.## Skill PurposeProvide a deterministic CLI-first browser workflow that always starts from a fresh snapshot and uses stable element refs instead of ad hoc DOM poking.## Instructions1. Check prerequisites first: `command -v npx >/dev/null 2>&1`. If `npx` is missing, stop and ask the user to install Node/npm. Otherwise use the exact wrapper script at `~/.codex/skills/playwright/scripts/playwright_cli.sh`.2. Run the core loop through the wrapper: open the page, snapshot, interact using refs from the latest snapshot, and snapshot again after navigation or major DOM change. Use `~/.codex/skills/playwright/references/cli.md` for command reference and `~/.codex/skills/playwright/references/workflows.md` for troubleshooting only when needed.3. Capture artifacts such as screenshots, PDFs, or traces when they help. Keep the workflow explicit and CLI-based; do not pivot into Playwright test code unless the user explicitly asked for test files.## Non-Negotiable Acceptance Criteria- Always snapshot before using element refs like `e12`.- Re-snapshot after navigation, modal changes, tab switches, or any UI change that could stale refs.- Prefer explicit CLI commands over `eval`/custom code when the wrapper can already do the job.- Use `--headed` when a visual check materially helps.## Output- A concise command sequence or workflow summary.- Latest relevant element refs or artifact paths when the task depends on them.- A short note on whether the flow succeeded, stalled on stale refs, or needs a new snapshot.

Frequently asked questions