AGENT SKILL

playwriter

Browser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.

License 许可
MIT
最近更新
2026-09-26
Stars
★ 0
Forks
0

01 前言 Front Matter

hats
[ "developer", "qa_tester" ]
name
playwriter
metadata
{ "internal": true }
description
Browser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.

03 SKILL.md 正文

Playwriter

Overview

Use Playwriter to run Playwright Page scripts against your local Chrome session. This preserves logins, cookies, and extensions, which is ideal for web dashboard testing and authenticated flows.

When to Use

  • Validating the Ralph web dashboard UI
  • Navigating authenticated pages without re-logging in
  • Testing flows that require browser extensions or saved state
  • Capturing accessibility snapshots for element discovery

Prerequisites

  • Install the CLI:
    npm i -g playwriter
    
  • Install the Playwriter Chrome extension (see the Playwriter repo instructions)
  • Ensure Chrome is running and the extension is enabled

Core Workflow

  1. Create a session:
    playwriter session new
    
  2. List sessions and copy the session id:
    playwriter session list
    
  3. Execute Playwright code against that session:
    playwriter -s <session_id> -e "await page.goto('https://example.com')"
    

Execution Environment

Within -e, these are available in scope:

  • page (Playwright Page)
  • context (BrowserContext)
  • state (persistent object across calls in the same session)
  • require (for loading helper modules)

Example state persistence:

playwriter -s <session_id> -e "state.lastUrl = page.url()"
playwriter -s <session_id> -e "console.log(state.lastUrl)"

Common Patterns

Navigate + click

playwriter -s <session_id> -e "await page.goto('http://localhost:3000'); await page.getByRole('button', { name: 'Run' }).click();"

Fill forms

playwriter -s <session_id> -e "await page.getByLabel('Email').fill('qa@example.com'); await page.getByLabel('Password').fill('secret'); await page.getByRole('button', { name: 'Sign in' }).click();"

Accessibility snapshots (labeled)

playwriter -s <session_id> -e "const { screenshotWithAccessibilityLabels } = require('playwriter'); await screenshotWithAccessibilityLabels(page, { path: '/tmp/a11y.png' });"

Network interception

playwriter -s <session_id> -e "await page.route('**/api/**', async route => { const res = await route.fetch(); const body = await res.json(); await route.fulfill({ json: { ...body, injected: true } }); });"

Read page content

playwriter -s <session_id> -e "const text = await page.locator('main').innerText(); console.log(text);"

Tips

  • Prefer getByRole and getByLabel for stable selectors.
  • Use accessibility snapshots to discover reliable roles and labels.
  • Keep sessions focused: reset or close them if state becomes messy.
  • For multi-step flows, store intermediate data on state.

04 同仓库更多 Skills

flaviomartil
flaviomartil/ralph-jev

ralph-loop

Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.

★ 0
flaviomartil
flaviomartil/ralph-jev

ralph-hats

Create, inspect, validate, explain, and improve Ralph hat collections. Use this skill whenever the user asks to make or refine a `.ralph/hats/*.yml` workflow, debug hat routing, explain event topology, or tune a multi-hat Ralph run.

★ 0
flaviomartil
flaviomartil/ralph-jev

ralph-docs

Introspect, explain, and improve ralph-jev using the documentation shipped in its repository. Use this skill whenever the user asks questions about Ralph's behavior, wants to understand how a Ralph internal works (event loop, completion gate, judge evidence, Jev hooks, parallel loops, configuration), debug an unfamiliar failure mode, or propose a code change to the ralph-jev repo. The skill teaches the agent to answer from the repo's docs and source before guessing, and to scope improvements through the documented architecture rather than the local checkout alone.

★ 0
flaviomartil
flaviomartil/ralph-jev

complex-test-skill

A directory-style test skill for smoke testing

★ 0
flaviomartil
flaviomartil/ralph-jev

tui-validate

Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG/SVG) and text-based validation modes.

★ 0
flaviomartil
flaviomartil/ralph-jev

tui-debug-in-pane

Use when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and capturing live output.

★ 0