Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Playwright Skill
TestDino Playwright Skill: AI-powered guides for Playwright best practices, made by testdino.com.
Install
$
npx skills add testdino-hq/playwright-skillClaude Code
claude mcp add playwright-skill -- npx skills add testdino-hq/playwright-skillCursor / Claude Desktop (mcp.json)
{
"mcpServers": {
"playwright-skill": {
"command": "npx",
"args": [
"skills",
"add",
"testdino-hq/playwright-skill"
]
}
}
}Install command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →██████╗ ██╗ █████╗ ██╗ ██╗██╗ ██╗██████╗ ██╗ ██████╗ ██╗ ██╗████████╗
██╔══██╗██║ ██╔══██╗╚██╗ ██╔╝██║ ██║██╔══██╗██║██╔════╝ ██║ ██║╚══██╔══╝
██████╔╝██║ ███████║ ╚████╔╝ ██║ █╗ ██║██████╔╝██║██║ ███╗███████║ ██║
██╔═══╝ ██║ ██╔══██║ ╚██╔╝ ██║███╗██║██╔══██╗██║██║ ██║██╔══██║ ██║
██║ ███████╗██║ ██║ ██║ ╚███╔███╔╝██║ ██║██║╚██████╔╝██║ ██║ ██║
╚═╝ ╚══════╝╚═╝ ╚═╝ ╚═╝ ╚══╝╚══╝ ╚═╝ ╚═╝╚═╝ ╚═════╝ ╚═╝ ╚═╝ ╚═╝
███████╗██╗ ██╗██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║
███████╗█████╔╝ ██║██║ ██║
╚════██║██╔═██╗ ██║██║ ██║
███████║██║ ██╗██║███████╗███████╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝
by testdino.com — Purpose built for debugging, managing, and improving Playwright tests with AI
Playwright Skill Guides
Production-tested Playwright guides for E2E, API, component, visual, accessibility, and security testing, plus CI/CD, CLI automation, trace-report debugging, page objects, and migration. 79 guides with TypeScript examples throughout and JavaScript in most core guides.
These are Agent Skills — Markdown guides an AI coding agent loads on demand. Install them with the skills CLI and your agent pulls the right guide when you ask it to write, debug, or scale Playwright tests. SKILL.md is the canonical index the agent reads, including the Golden Rules and architecture-decision guides.
Playwright 1.64 coverage: locator.within() for combining a target and a container locator (with per-parent nth() for column queries), WebMCP testing via page.webmcp.tools() / callTool() in a dedicated webmcp-testing.md guide, --shuffle for exposing order-dependent tests, default: false projects with --project="*" and config.filteredProjects, test.describe.configure({ lock }), 60fps videos with CSS-styled action callouts and VP9 encoding, toHaveScreenshot: { type: 'webp' }, page.getByRef(), APIRequestContext cookie methods, passkey signCount, and page.content({ includeShadow }). Breaking changes flagged where they bite: device screen forwarding, --update-snapshots=missing now passing, elements in hidden iframes counting as hidden, and JSX following tsconfig.json.
From 1.63: test lock for serializing contention on a shared resource, locator.visible() replacing the :visible pseudo-class, aria and screen snapshots in traces (snapshots: { dom, aria, screen }), --add-reporter for appending rather than replacing reporters, the perfetto reporter, typed request.get<User>(), and ariaSnapshotJSON(). From 1.62: reporter.preprocess() for selecting tests before execution, retryStrategy: 'isolated', WebP screenshots with a quality parameter, AbortSignal on actions and assertions, locator.waitForFunction(), apiResponse.timing(), and the stories-and-galleries component testing model that replaces the deprecated experimental CT packages. A dedicated dynamic-test-selection.md guide covers driving quarantine from an external flakiness API.
Install
Add every skill pack to your project:
npx skills add testdino-hq/playwright-skill
Or add individual packs:
Similar plugs
Open-source AI job search agent and job finder: scan job boards, score each job 1-5 against your CV before you apply, tailor an ATS-friendly resume and cover letter, get…
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in…