AgentSkills.site

Skill profile

playwright

Drives a real browser from the terminal for navigation, form filling, screenshots, and data extraction — CLI-first, and won't write @playwright/test files unless asked.

Official OpenAI

Verified

openai/skills (curated)

What it actually does

  • Drives a real browser from the terminal for navigation, form filling, screenshots, and data extraction, using a bundled wrapper script so it works even without `playwright-cli` installed globally.

When to use it — and when not to

Use it when

  • You want the agent to actually operate a browser — click through a flow, take a screenshot, extract data — from the terminal.

Not for

  • You want a `@playwright/test` test suite written — its instructions are explicit that it won't pivot to that unless you ask; "automate the browser" and "write me a test suite" are treated as different requests.

Agent compatibility

  • Codex

Confirmed means the skill’s own source or vendor states it works with that agent. Portable means it only reaches that agent through the shared SKILL.md format and a directory convention — real, but a weaker claim. An agent with no entry here isn’t known to be unsupported; it simply isn’t documented either way, so nothing is claimed. Full model on Agent Skills Compatibility.

Requirements and operational surface

What it actually does at runtime

  • Drives a real browser
  • Reads pages and can extract data from them

Related skills

  • Cursor browser QA skillsThe equivalent job on Cursor, built on Cursor's own browser and accessibility tree instead of a CLI wrapper.

Evidence and provenance

Maintained by OpenAI (official). Primary source: openai/skills (curated), last checked against this page’s claims on . This page summarizes and analyzes that source — it isn’t a copy of its SKILL.md or README, and installation happens at the source, not here.

Also covered in The Best Codex Skills, part of the Codex guide.