---
name: playwriter
description: Control the user's currently open Chrome tab through the Playwriter CLI (no new browser launch). Use when you need to inspect live UI state, run scripted browser actions, capture console output, or reproduce frontend issues directly in the user's tab.
title: playwriter
canonical_url: https://skilld.dev/gh/brianlovin/agent-config/playwriter
last_updated: 2026-09-29T08:33:34.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [agents/openai.yaml](https://skilld.dev/api/skills-raw/brianlovin/agent-config/playwriter/agents/openai.yaml).
>
> If the user asked to install this Skill, run `npx skilld install brianlovin/agent-config/playwriter`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/playwriter`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/brianlovin/agent-config/playwriter) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/playwriter`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/playwriter --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/playwriter --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Playwriter

Use this skill to drive the user's active Chrome tab via Playwriter.

Full documentation is available here: https://playwriter.dev/

## Quick Start

1. Ensure the Playwriter extension is enabled (green) on the target tab.
2. Ensure CLI is available:

```bash
playwriter --version || npx -y playwriter --version
```

3. Create/attach a session:

```bash
playwriter session new
```

4. Run commands against that session:

```bash
playwriter -s 1 -e "console.log(await page.url())"
```

## Core Workflow

1. Confirm connection and correct tab:

```bash
playwriter -s <session> -e "console.log(await page.url()); console.log(await page.title());"
```

2. Collect page structure when needed:

```bash
playwriter -s <session> -e "console.log(await accessibilitySnapshot({ page }))"
```

3. Execute targeted actions (click/type/hover/fetch/evaluate).
4. Pull logs and structured state via `page.evaluate`.
5. Summarize findings with exact IDs, timestamps, and observed state transitions.

## Useful Commands

Get list rows/options from current app UI:

```bash
playwriter -s <session> -e "const rows = await page.getByRole('option').all(); console.log(rows.length);"
```

Read popup/hover content:

```bash
playwriter -s <session> -e "const row = page.getByRole('option').nth(0); await row.hover(); await page.waitForTimeout(700); console.log(await page.locator('[data-side]').first().innerText());"
```

Run arbitrary in-page debug code:

```bash
playwriter -s <session> -e "const out = await page.evaluate(() => ({ href: location.href })); console.log(out);"
```

## Troubleshooting

- If the session attaches to the wrong tab, click the extension icon on the intended tab and re-run `playwriter session new`.
- If `playwriter` command is missing, use `npx -y playwriter ...` or install globally.
- If execution errors suggest stale connection, create a fresh session.

## Guardrails

- Prefer read-only inspection unless the task requires mutation.
- Announce destructive UI actions before running them.
- When capturing logs, redact sensitive tokens/user data in summaries.