home / skills / openai / skills / playwright

This skill automates real browser tasks via the Playwright CLI from the terminal, enabling navigation, form filling, and artifact capture.

npx playbooks add skill openai/skills --skill playwright

Review the files below or copy the command above to add this skill to your agents.

Files (9)
SKILL.md
3.7 KB
---
name: "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."
---


# 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.

## Skill path (set once)

```bash
export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export PWCLI="$CODEX_HOME/skills/playwright/scripts/playwright_cli.sh"
```

User-scoped skills install under `$CODEX_HOME/skills` (default: `~/.codex/skills`).

## 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.

Overview

This skill automates a real browser from the terminal using the Playwright CLI wrapper. It provides commands for navigation, form filling, clicks, snapshots, screenshots, traces, multi-tab control, and artifact capture. Use the bundled wrapper script so the CLI runs even without a global install. The workflow is CLI-first: open, snapshot, interact with element refs, and capture artifacts as needed.

How this skill works

The wrapper runs the Playwright CLI via npx so you can drive headed or headless browser sessions from shell commands. It takes a snapshot to generate stable element refs (e.g., e3), then runs interactions (click, fill, type, press) against those refs. You re-snapshot after navigation or major DOM changes and capture screenshots, PDFs, or traces into the designated output folder.

When to use it

  • Automating browser flows directly from the terminal without writing test specs.
  • Filling forms, clicking through UI flows, and extracting page content programmatically.
  • Debugging UI interactions with headed mode and traces for visual inspection.
  • Taking reproducible screenshots or PDFs of pages as part of a CI or local workflow.
  • Managing multi-tab flows and simple browser orchestration from scripts.

Best practices

  • Verify npx is available before running the wrapper; prompt user to install Node/npm if missing.
  • Always run snapshot before using element refs and re-snapshot after navigation or big DOM changes.
  • Prefer the bundled wrapper script (uses npx --package) so a global install is unnecessary.
  • Use --headed when you need visual confirmation; use tracing-start/stop for deeper debugging.
  • Store artifacts under output/playwright/ to keep repository artifacts organized.

Example use cases

  • Open a site, snapshot, click a sequence of elements, then screenshot the resulting state.
  • Fill and submit a login form using fill and click, then re-snapshot to confirm successful navigation.
  • Capture a trace while reproducing a flaky UI flow to investigate performance or timing issues.
  • Create a script that opens multiple tabs, switches between them, and extracts data from each page.
  • Run headed sessions locally for manual debugging, then run headless in CI for automated snapshots and screenshots.

FAQ

What if npx is not installed?

Pause and ask the user to install Node.js/npm. Verify with node --version and npm --version, then either install the CLI globally with npm install -g @playwright/cli@latest or use the wrapper after npm is available.

When should I snapshot again?

Snapshot after any navigation, actions that substantially change the UI (modals, menus, tab switches), or when a command fails due to a missing ref.

Should I prefer the wrapper or a global install?

Prefer the wrapper for portability; a global install is optional if your environment standardizes on it.