Best browser automation skills, page 6

Drive the in-app browser — open a page, read it as an accessibility tree, click, type, fill forms, screenshot, and verify what the page really shows.

kunpengtalk/PeakCode

Boss 直聘岗位搜索的完整操作手册。触发场景：用户说"找工作"/"看岗位"/"搜招聘"/"投简历"/"跳槽"/"Boss 直聘"/"看看有什么工作"/"帮我看下 XX 岗位"等。前提：必须走 browserbridge（Boss 需要用户 Chrome 登录态；browseruse 独立环境登不上）。包含 URL 模板、城市编码表、Vue data 抽取…

guyi-a/pi-ling

A skill your agent uses when measuring what the Trilium client loads at startup — "what loads at boot?", "did this change reduce the startup bundle?", "is <dependency lazy?", or any before/after…

TriliumNext/Trilium

Control, inspect, or audit Horizon browser panels through public browser MCP tools.

peters/horizon

Publish text, image and video posts or long-form Markdown headline articles to Weibo through a real Chrome session, with the final review left to you.

JimLiu/baoyu-skills

Operates desktop apps and isolated or disposable browsers on registered computers through an observe, act, verify loop, separate from driving the user's own signed-in Chrome.

codewhale-hq/Codewhale

Connect to and control Google Chrome browser using agent-browser with CDP (Chrome DevTools Protocol).

appleweiping/WEIPING_WIKI

HyperFrames CLI and Minis rendering. An agent skill from OpenMinis/MinisSkills.

OpenMinis/MinisSkills

Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser.

google-deepmind/science-skills

Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…

antibrow/anti-detect-browser-skills

Choose the right Interceptor surface. An agent skill from Hacker-Valley-Media/Interceptor.

Hacker-Valley-Media/Interceptor

Tests OrchardCore CMS features through browser automation. An agent skill from OrchardCMS/OrchardCore.

OrchardCMS/OrchardCore

Scrapes the Hacker News front page and returns the top 30 stories as JSON with rank, title, link, points and comment count.

garrytan/gstack

Lets another AI agent drive your browser: one command creates a setup key and prints connection instructions for the remote agent.

garrytan/gstack

Extracts data from a web page through the Aside browser, using your real signed-in sessions, and returns one JSON document without changing anything.

garrytan/gstack

Use kuri-server to automate Chrome via HTTP API — navigate pages, get a11y snapshots, interact with elements, capture network traffic (HAR), extract cookies, and bypass bot protection.

justrach/kuri

Use Link CLI's identity commands when a service requests a Link Agent Attestation Token (AAT) or signed user claims such as email.

stripe/link-cli

Operates the visible browser pane of a Cherry Studio Agent session through live browser tools: navigation, snapshots, screenshots, forms and clicks, verifying outcomes.

CherryHQ/cherry-studio

This skill provides tools and techniques for e-commerce website automation.

MassLab-SII/open-agent-skills

Start the local @remotion/convert app and open it in the Codex browser.

remotion-dev/remotion

Start the Remotion docs site and open it in the Codex browser.

remotion-dev/remotion

Start the @remotion/player example app and open it in the Codex browser.

remotion-dev/remotion

Start Remotion Studio from packages/example and open it in the Codex browser.

remotion-dev/remotion

Automates browser and Electron app interactions for user-flow validation.

Intelligent-Internet/zenith

Drive a live browser from the CLI with playwright-cli to navigate, interact, snapshot, and capture evidence.

fugazi/test-automation-skills-agents

Searches Amazon products and groceries, reads product pages and cart contents, and adds explicitly named items to cart, stopping short of checkout.

browsing-skills/browsing-skills

QA Tracecat product features in a real local cluster. An agent skill from TracecatHQ/tracecat.

TracecatHQ/tracecat

Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.

paperclipai/paperclip

Design patterns for building autonomous coding agents. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Drives a live browser through the Playwright MCP server to navigate, inspect, fill forms and screenshot pages, with snapshot-first habits and output-size care.

Hainrixz/editor-pro-max

Shared workflow for browser-based review of user-visible frontend changes in Langfuse.

langfuse/langfuse

Generate a branded HTML artifact from Egregore data (quest, handoff, activity, board, network, or any document) and open it in the browser.

egregore-labs/egregore

浏览器自动化技能，通过 browseraction 工具控制 Chrome 浏览器执行多步骤网页操作任务。支持页面导航、元素点击与输入、页面状态提取、截图分析、控制台错误与网络请求监控查询等。适用于网页数据采集、表单自动填写、网页信息查询、多步骤网页交互等场景。

cigery-useio/useio-skills

Extracts icons, metadata, text, forms, videos and social links from any web page with playwright-cli, with SVG icon classification and cleanup.

adobe/skills

Produce polished, mobile-friendly product demo videos of the eva app with Remotion — 1280×720, snappy beat-synced hard cuts, lo-fi music that swells on every cut, and footage captured from the REAL…

vvedantb/eva

Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection.

vercel/vercel-plugin

Run QA tests using agent-browser and post results to the qabot dashboard.

shapeshift/web

Routes a web request through the cheapest tier that can finish it, from headless extraction with WAF bypass up to a real stealth or signed-in browser, with screenshots as proof.

code-yeongyu/oh-my-openagent

Observable browser automation using Chrome MCP tools. An agent skill from disler/bowser.

disler/bowser

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

Factory-AI/factory-plugins

Run automated post-deploy UI verification with a browser automation MCP (claude-in-chrome, Playwright, or Puppeteer): console-error and Core Web Vitals smoke checks, form and auth-flow interaction…

affaan-m/ECC

A skill your agent uses when the user needs browser automation, including opening web pages, taking screenshots, extracting page content, clicking elements, filling forms, or testing web flows.

infometa/workbuddyskills

Use when opening, inspecting, clicking, filling, snapshotting, or otherwise automating web pages for this repo, including local dev servers and…

pierrecomputer/pierre

Controls the user's Chrome through Qwen Code's Node REPL and Browser SDK, with the Qwen Code Chrome extension, profile binding and tab ownership handling.

QwenLM/qwen-code

Complete browser automation with Playwright. An agent skill from AratKruglik/claude-laravel.

AratKruglik/claude-laravel

Creates Open Graph / social share images (1200x630) for blog posts and announcements by rendering HTML in a headless browser.

bonny/WordPress-Simple-History

Inspect live Vue 3 component state via agent-browser eval - no Devtools extension, no console.log.

scott-fryxell/brayness

Playwright modern end-to-end testing framework with cross-browser automation, auto-wait, and built-in test runner

activepieces/activepieces