Каталог навыков агентов

Edge browser automation via Chrome DevTools Protocol (CDP). List tabs, navigate, take screenshots, extract page content/...

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, na...

Browser automation via the `agent-browser` CLI. Use when the user needs to drive websites or Electron apps — navigating,...

浏览器自动化技能。支持打开网页、网页截图、搜索、提取内容、填写表单、点击元素等。当用户要求“打开网页”、“搜索”、“爬取数据”、“点击按钮”、“截图”或“自动化操作浏览器”时使用。

Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, form...

Web browser automation with AI-optimized snapshots for claude-flow agents

Web browser automation with AI-optimized snapshots for Codex-flow agents

Interactive browser automation via playwright-cli. Use when you need to navigate a site, click elements, fill forms, tak...

Use when the user already has browser automation and wants it unblocked or run in the cloud: Playwright, Puppeteer, Sele...

Headless browser automation via agent-browser (Playwright/Chromium) - navigate, snapshot, click, type, screenshot, eval,...

Browse via node .rulesync/scripts/browser.mjs (Lightpanda). App e2e uses Playwright.

Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects...

Use to verify Toolcraft generated apps in a real local browser after implementation.

Browser automation and desktop UI. Use for web-page reads and interaction, screenshots, browser tests, login or session...

Browser control, navigation loops, elements locating, and scraping.

Browser automation CLI for AI agents. Use when testing web UIs, filling forms, taking screenshots, visual verification,...

Open and inspect pages with NewBrain browser preview for navigation and local web verification.

Lightweight browser automation using Puppeteer Core. Connect to running Chrome via remote debugging for fast screenshots...

Debug-first browser automation with always-on visibility. Console logs, network requests, and errors captured by default...

Opens browser at URL for E2E testing via playwright-cli. Provides CLI commands for navigation, screenshots, and interact...

用于浏览器自动化与网页抓取的最小 Chrome DevTools Protocol 工具集。当你需要启动 Chrome、导航页面、执行 JavaScript、截图或交互式选择 DOM 元素时使用。触发词包括 “browse website”...

Browser and device automation: pick the right engine (the host's preview panel first, an anti-detect browser over MCP fo...

Simple headless Puppeteer browser for rendering JavaScript-heavy pages and extracting clean text content. Use when user...

Atlas skill, code-first browser automation and web verification. USE WHEN browser, screenshot, navigate, web testing, ve...

Drive a managed Chrome session via CDP. Navigate, click, fill forms, read the DOM, take screenshots, run JS.

Use BrowserAct for authenticated browser automation, JS-rendered extraction, screenshots, parallel sessions, verificatio...

Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first....

Forge website capabilities into reusable Skills via browser automation — discovers API endpoints or DOM patterns, then g...

Build web agents using human-inspired browser actions (scrolling, clicking, typing) operated directly on raw HTML via Pl...

Autonomous browser agent for complex multi-step web tasks. WHEN: User needs complex web automation, multi-page workflows...

Autonomous human-like browser control and professional QA/QC testing. Powered by agent-browser (Rust native CDP, zero Pl...

Control a real browser via Oya Browser MCP tools. Use this skill when the user asks you to browse the web, interact with...

Orchestrates web browser agent tasks with strict token economy: OAuth verification, dashboard checks, URL flows, and ext...

Drive a browser with Playwright for agents: grounding in DOM/ARIA, robust locators, network waits, prompt-injection defe...

Run the pre-flight checklist before an agent drives a browser — the untrusted-web-content threat (every page is attacker...

Review AI browser agents for DOM injection attacks, credential harvesting via web automation, malicious web content that...

You are a coding standards expert specializing in browser api usage rules.

Minimal Chrome DevTools Protocol tools for browser automation and scraping. Use when you need to start Chrome, navigate...

Complete a sign-up, listing, claim or console task on a third-party site AS you, by driving Chrome on a copy of your own...

Run a pre-deploy browser audit of a live, preview, or local web page for accessibility, SEO, Lighthouse quality, and cri...

Browser testing with agent-browser CLI and auth token injection. Loaded via test skill.

Browser automation with 1Password credential integration for authenticated workflows

Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual co...

Probe a site's authentication flow for redirect leaks, missing CSRF, weak session cookies, and OAuth misconfiguration; p...

Automate web browser interactions, scraping, testing, and workflow automation with Puppeteer/Playwright

Built-in browser automation skill for AgentForge agents. Navigate web pages, interact with elements, extract content, an...

Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured d...

Local Python-based browser automation toolkit using Playwright. Provides command-line tools for navigating, interacting...

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a...

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a...

Use when the agent must open a URL, fill a form, click through a flow, screenshot a page, or extract data from a live pa...

Use for browser automation (QA, element interaction, screencapture/snapshot, network capture) or to work across the user...

You are a browser automation expert who has debugged thousands of flaky tests and built scrapers that run for years with...

Browser automation toolkit using Playwright. Supports interacting with web applications, form filling, capturing screens...

Automates browser interactions for web testing, form filling, screenshots and data extraction. Use when the user needs t...

Automate browser interactions using Playwright or Puppeteer

统一自动化入口。覆盖浏览器自动化（Playwright）和 Windows 桌面应用自动化（OpenReverse）。 浏览器场景：打开网页、点击、填表、爬取、截图、自动化登录、渗透页面交互。 桌面场景：操作 IDA/x64dbg 等 GU...

AI browser automation - navigate, interact, extract, verify via browser-use MCP

Web and desktop automation with layered escalation (Fetch, Genesis Browser, Remote CDP, On-Demand MCP, Desktop), anti-de...

Automate web browsers for AI agents using agent-browser CLI with deterministic element selection.

General-purpose patterns for reliable browser automation (selectors, waiting, scrolling, overlays, HITL).

Use when debugging web applications or automating browser tasks. Leverage Chrome DevTools MCP for inspection, performanc...

Browser automation - control browser sessions, scrape pages, and run AI agents

Choose the narrowest reliable browser surface across Codex Browser, signed-in Chrome, Playwright CLI, and platform scrip...

Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sess...

Control Firefox browser from the command line. Use for web automation, scraping, testing, or any browser interaction tas...

Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wra...

浏览器 viewport / headless / 超时分层配置。触发：viewport、浏览器配置、导航超时、headless、slow_mo、incognito。

Confirm an Opus-flagged true-positive chain in a real browser (live via Caido proxy or mock_backend). Run when opus-deep...

Capture content from JavaScript-rendered pages, login-protected sites, and multi-page documentation using agent-browser...

Infer runtime browser context — CSP, Trusted Types, rendering model, framework family, sandbox iframes. Writes browser_c...

Control a dedicated browser in Claude Code using Playwright scripts. Use when the user asks to open web pages, inspect p...

Full browser control for authenticated web interactions using Playwright scripts

Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only...

Use when cron sweeps drive browsers against anti-bot sites.

Reconstruct browser-side credential transforms and encrypted management requests from JavaScript, captures, and firmware...

Use browser automation MCP tools to inspect pages for errors, console warnings, and visual issues.

Browser runtime debugging toolkit — prioritize browser DevTools and CDP tools for runtime inspection and control when de...

Systematically tests UI functionality, validates design fidelity with AI visual analysis, monitors console output, track...

Debug front-end problems in the browser with Chrome DevTools: Console, Sources breakpoints, Network, Elements/computed s...

This skill should be used when working with browser-rendered artifacts (i.e. Bun, React/React Native) to proactively val...

Browser debugging and automation using Playwright. Use for web debugging, console monitoring, network analysis, screensh...

Integrating Chrome DevTools and browser automation via MCP for live UI inspection, screenshot-to-code workflows, and vis...

Use this skill for browser verification, console/network errors, layout checks, user-flow QA, DevTools evidence. Trigger...

Browser automation for documentation discovery. Use when curl fails on JS-rendered sites, when detecting available brows...

Shared domain knowledge convention for all browser automation tools. Stores per-host notes (login flows, selector quirks...

Download files from authenticated web sessions. Use when the browser tool cannot directly download files (attachments, e...

Drive a real browser to navigate, fill, click and extract from live pages, or name the blocker.

Web application and browser E2E audit testing routes, user journeys, console errors, responsive layouts, and accessibili...

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like Li...

Beginner-friendly reverse-engineering workflow for Browser Env Emulation. Use it to collect evidence, choose static or d...

ブラウザ拡張機能の開発を支援するスキル。Chrome (Manifest V3) と Firefox に対応したブラウザ拡張を設計・実装する。以下の状況で使用: (1) ユーザーが「ブラウザ拡張を作って」「Chrome拡張を実装して」「Fi...

Master specialized skill for building 2025/2026-grade browser extensions. Deep expertise in Manifest v3, Service Worker...

Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers e...

You extend the browser to give users superpowers. You understand the unique constraints of extension development - permi...