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.
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.