Best browser testing skills for Claude Code, Codex and other agents.

Explores a web app with the agent-browser CLI to find bugs and UX problems, then writes a report with screenshots, repro videos and step-by-step reproduction for each issue.

vercel-labs/agent-browser

Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

anthropics/skills

Automates a real browser through short TypeScript scripts that keep page state between runs, for navigating, filling forms, taking screenshots and extracting data.

MemTensor/MemOS

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

sanity-io/sanity

Drives a real browser from the command line with playwright-cli to open pages, interact, mock requests, save state and work with Playwright tests.

github/gh-aw

Writes a Playwright end-to-end test from a prompt, runs it against a live Appsmith deployment and retries with fixes up to three times until it passes.

appsmithorg/appsmith

Core usage guide for the agent-browser CLI: the snapshot-and-ref workflow for navigating, clicking, filling forms, extracting data and running parallel sessions.

vercel-labs/agent-browser

Guides changes and reviews of the Cucumber and Playwright end-to-end suite under `e2e/`: feature files, step definitions, support code, tags, locators and assertions.

langgenius/dify

Write and review Playwright E2E tests for Langflow. An agent skill from langflow-ai/langflow.

langflow-ai/langflow

Connects an agent to a real Chrome instance through the Chrome DevTools MCP server, so it can inspect the DOM, read console errors and profile performance directly.

addyosmani/agent-skills

Drives a real browser through the omowright library, either the user's own signed-in browser or a separate browser the code launches, for forms, QA, screenshots and scraping.

code-yeongyu/oh-my-openagent

Automates a Chrome or Chromium browser through the agent-browser CLI: navigate, fill forms, click, screenshot and extract data using element refs.

sipeed/picoclaw

This skill should be used when the user is writing Go code and needs guidance on Go-specific pedantry: error wrapping with fmt.Errorf and %w, interface design (accept interfaces return structs)…

chromedp/chromedp

Drives a web browser from the shell with the agent-browser CLI: open pages, read an element snapshot, click and fill by reference, grab text and screenshots.

nanocoai/nanoclaw

Fixes failing Playwright specs by reading the error, classifying the cause in the test code and applying corrections that follow project conventions.

appsmithorg/appsmith

Guides writing and changing Playwright end-to-end tests for Handsontable using page objects, data-testid hooks and deterministic waits.

handsontable/handsontable

Runs the json_repair docs demo against a local Flask API and static server, so changes to docs/app.py or the docs UI are checked end to end before publishing.

mangiucugna/json_repair

A skill your agent uses when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli…

JetBrains/skills

Starts a Dozzle dev server on a port derived from the current worktree so you can test by hand in a browser, without disturbing instances started elsewhere.

amir20/dozzle

Step-by-step procedure for debugging browser automation failures on complex sites such as LinkedIn, Twitter/X, single-page apps and Shadow DOM pages.

aden-hive/hive

Drives a real browser from the shell with the agent-browser CLI: open pages, snapshot elements by ref, click, fill and extract, for testing web flows.

slopus/happy

Extract structured data from websites and produce an executable Playwright script plus extracted data.

actionbook/actionbook

Deep-dive diagnosis of a Playwright test failure already isolated to one Quay Prow/OpenShift CI run: downloads its GCS artifacts (results.json, JUnit, build/pod logs, Jaeger traces), classifies real…

quay/quay

A skill your agent uses when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with…

freestylefly/wesight

A skill your agent uses when creating, modifying, debugging, deploying, or testing Redis Insight Workbench visualization plugins, plugin manifests, package.json visualizations, activationMethod…

redis/RedisInsight

Complete browser automation with Playwright. An agent skill from lackeyjb/playwright-skill.

lackeyjb/playwright-skill

This skill should be used when the user asks to "add an E2E test", "run live E2E", "run mock-LLM tests", "debug Playwright CI", "test the Docker image", or changes tests/e2e, Playwright configs, E2E…

OpenHands/OpenHands

Regenerates Playwright visual snapshots for Dozzle after an intentional UI change, running them through Docker Compose so filenames match the Linux CI platform.

amir20/dozzle

Run the AI Search Hub browser automation scripts for Yuanbao, LongCat, Doubao, Qwen, Gemini, Grok, and MiniMax.

minsight-ai-info/AI-Search-Hub

Drives a real browser through Aside so the agent can open a page, read it, click through a flow, take screenshots and check console errors.

garrytan/gstack

Launches a visible AI-controlled Chromium window with a sidebar extension, so you can watch each agent action in a live activity feed and chat panel.

garrytan/gstack

A skill your agent uses when adding or updating documentation pages in an existing docs site.

TracecatHQ/tracecat

Converts RStudio Python Selenium electron tests into TypeScript Playwright tests, checking each against a live RStudio before counting it as migrated.

rstudio/rstudio

Run the pre-release end-to-end sweep of every user-facing surface — the 33 samples under samples/ (booted from their packaged artifacts and driven in a real browser via chrome-devtools MCP), the…

Atmosphere/atmosphere

Opens a live BrowserStack session on a real Android, iOS or desktop browser for a local or public URL, tunneling localhost through Cloudflare when needed.

handsontable/handsontable

Write and maintain Playwright end-to-end tests for the Onyx application.

onyx-dot-app/onyx

A skill your agent uses for every Kortix test task, behavior change, bug fix, refactor, API route change, CLI change, SDK change, browser journey, test failure, coverage question, local benchmark…

kortix-ai/suna

Writes and reviews Geb browser automation specs with Spock, using Page Objects, at checkers, Modules and explicit waits, for Groovy and Gradle projects.

apache/groovy-geb

Diagnose any Quay Prow job failure end to end: prowjob.json - top-level build log - JUnit - resolved failing step - Playwright results.json when the failing step is Playwright, continuing through…

quay/quay

When you need a browser, read this Skill by default. An agent skill from kwakseongjae/oh-my-design.

kwakseongjae/oh-my-design

Opens pages, takes screenshots, reads the console, clicks and types in the browser panes of a Superset workspace, with Browser Use as a fallback for other browsers.

superset-sh/superset

Pure-web protocol reverse skill: turn hostile browser clients into browser-free Python collectors.

aoyunyang/spider-king-skill

Record polished UI demo videos using Playwright. An agent skill from sanity-io/ui.

sanity-io/ui

スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。

yohey-w/multi-agent-shogun

A skill your agent uses for Pest PHP testing in Laravel projects only.

luadotsh/lua

Grida Desktop Electron shell and release-impact work: BrowserWindow, preload, window.grida, menus, protocol/deep links, file associations, Forge, path-scoped bridge security, Electron-only UI bugs…

gridaco/grida

将任意文本、网页或 URL 生成符合 Claude/Anthropic 设计语言的 HTML 信息卡片，通过 Playwright 截图为 PNG。

geekjourneyx/claude-design-card

A skill your agent uses when you need direct browser control - teaches Chrome DevTools Protocol for controlling existing browser sessions, multi-tab management, form automation, and content…

obra/superpowers-chrome