openai-playwright — Claude Code skill for browser automation
openai-playwright is a Claude Code skill that controls a real browser from the terminal. It runs for page navigation, form entry, data collection, screenshots, and UI debugging.
Apache-2.0 ★ 540 updated 2026-07-14
/plugin marketplace add trailofbits/skills-curated
/plugin install openai-playwright@skills-curatedWhat openai-playwright does
openai-playwright drives a browser with playwright-cli: it opens pages, interacts with page elements, and captures screenshots, PDFs, or traces. It takes a page snapshot to identify elements before using them. After navigation or major UI changes, it takes another snapshot because old element references can go stale.
The wrapper requires npx, which comes with Node.js/npm. If npx is missing, the skill asks for Node.js/npm to be installed; a global playwright-cli installation is optional. This workflow uses CLI commands rather than generating @playwright/test specs, unless those are explicitly requested. In this repository, captured artifacts go in output/playwright/.
What it helps with
- navigate through a page and interact with its controls
- fill in and submit a web form
- capture a page screenshot or PDF
- collect data from a browser page
- record a UI flow for debugging
Example prompts for the agent
- Open the page and show me its snapshot.
- Fill out the form on this page and submit it.
- Record this UI flow and save a screenshot.
How to install openai-playwright
1Plugin marketplace
/plugin marketplace add trailofbits/skills-curated/plugin install openai-playwright@skills-curatedThis installs the whole openai-playwright plugin with all its skills
2Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-playwright -a claude-code3Manually: put the files in place
~/.claude/skills/openai-playwright/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/openai-playwright/
1Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-playwright -a codex2Manually: put the files in place
.agents/skills/openai-playwright/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-playwright -a cursor2Manually: put the files in place
.cursor/skills/openai-playwright/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install trailofbits/skills-curated plugins/openai-playwright/skills/openai-playwright2Manually: put the files in place
.github/skills/openai-playwright/SKILL.md1Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-playwright -a gemini-cli2Platform CLI
gemini skills install https://github.com/trailofbits/skills-curated --path plugins/openai-playwright/skills/openai-playwrightManually: put the files in place
.devin/skills/openai-playwright/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about openai-playwright
How do I install openai-playwright in Claude Code?
Add the marketplace with /plugin marketplace add trailofbits/skills-curated, then install the skill with /plugin install openai-playwright@skills-curated.
What does openai-playwright do?
It controls a browser from the terminal through playwright-cli. It can navigate pages, fill forms, collect data, and capture screenshots or traces.
What does openai-playwright need to run?
Its wrapper needs npx, provided by Node.js/npm. A global playwright-cli install is an optional alternative.
Source text
SKILL.md · Apache-2.0
---
name: openai-playwright
description: Use when the task requires automating a real browser from the terminal (navigation, form
filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled
wrapper script. Originally from OpenAI's curated skills catalog.
allowed-tools:
- Bash
- Read
- Grep
- Glob
- Write
- Edit
---
# Playwright CLI Skill
Drive a real browser from the terminal using `playwright-cli`. Prefer the bundled wrapper script so the CLI works even when it is not globally installed.
Treat this skill as CLI-first automation. Do not pivot to `@playwright/test` unless the user explicitly asks for test files.
## Prerequisite check (required)
Before proposing commands, check whether `npx` is available (the wrapper depends on it):
```bash
command -v npx >/dev/null 2>&1
```
If it is not available, pause and ask the user to install Node.js/npm (which provides `npx`). Provide these steps verbatim:
```bash
# Verify Node/npm are installed
node --version
npm --version
# If missing, install Node.js/npm, then:
npm install -g @playwright/cli@latest
playwright-cli --help
```
Once `npx` is present, proceed with the wrapper script. A global install of `playwright-cli` is optional.
Scripts and references are located under `{baseDir}/`.
## Quick start
Use the wrapper script:
```bash
"$PWCLI" open https://playwright.dev --headed
"$PWCLI" snapshot
"$PWCLI" click e15
"$PWCLI" type "Playwright"
"$PWCLI" press Enter
"$PWCLI" screenshot
```
If the user prefers a global install, this is also valid:
```bash
npm install -g @playwright/cli@latest
playwright-cli --help
```
## Core workflow
1. Open the page.
2. Snapshot to get stable element refs.
3. Interact using refs from the latest snapshot.
4. Re-snapshot after navigation or significant DOM changes.
5. Capture artifacts (screenshot, pdf, traces) when useful.
Minimal loop:
```bash
"$PWCLI" open https://example.com
"$PWCLI" snapshot
"$PWCLI" click e3
"$PWCLI" snapshot
```
## When to snapshot again
Snapshot again after:
- navigation
- clicking elements that change the UI substantially
- opening/closing modals or menus
- tab switches
Refs can go stale. When a command fails due to a missing ref, snapshot again.
## Recommended patterns
### Form fill and submit
```bash
"$PWCLI" open https://example.com/form
"$PWCLI" snapshot
"$PWCLI" fill e1 "[email protected]"
"$PWCLI" fill e2 "password123"
"$PWCLI" click e3
"$PWCLI" snapshot
```
### Debug a UI flow with traces
```bash
"$PWCLI" open https://example.com --headed
"$PWCLI" tracing-start
# ...interactions...
"$PWCLI" tracing-stop
```
### Multi-tab work
```bash
"$PWCLI" tab-new https://example.com
"$PWCLI" tab-list
"$PWCLI" tab-select 0
"$PWCLI" snapshot
```
## Wrapper script
The wrapper script uses `npx --package @playwright/cli playwright-cli` so the CLI can run without a global install:
```bash
"$PWCLI" --help
```
Prefer the wrapper unless the repository already standardizes on a global install.
## References
Open only what you need:
- CLI command reference: `references/cli.md`
- Practical workflows and troubleshooting: `references/workflows.md`
## Guardrails
- Always snapshot before referencing element ids like `e12`.
- Re-snapshot when refs seem stale.
- Prefer explicit commands over `eval` and `run-code` unless needed.
- When you do not have a fresh snapshot, use placeholder refs like `eX` and say why; do not bypass refs with `run-code`.
- Use `--headed` when a visual check will help.
- When capturing artifacts in this repo, use `output/playwright/` and avoid introducing new top-level artifact folders.
- Default to CLI commands and workflows, not Playwright test specs.
## When to Use
<!-- TODO: review -->
## When NOT to Use
<!-- TODO: review -->
© OpenAI · Apache-2.0 · trailofbits/skills-curated