7,463 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Digidai/website2markdown-skills
Skill Claude Code
Convert web pages to clean Markdown using the Website2Markdown API (md.genedai.me). Use when you need to fetch, read, extract, or analyze web page content — especially when WebFetch fails, returns incomplete content, or the target is JS-heavy/paywalled. Supports 21 platform adapters (WeChat, Zhihu, Feishu, Twitter/X…
Skill Claude Code
Automate browser interactions, test web pages and work with Playwright tests.
2018wzh/windows-sandbox-computer-use
Skill Claude CodeCodex
Execute commands, batch tasks, share directories, inspect and visually control an authorized Windows Sandbox using wsb and IronRDP. Use only for Windows Sandbox, never ordinary RDP hosts or local desktop apps.
superagents-lab/search1api-cli
Skill Claude CodeCodex
Live web search, agentic search, Google Maps place search, page retrieval, whole-site crawling, news, sitemap discovery, trending topics, and turning a URL into a reusable Agent Skill — all through the Search1API CLI (s1). Use this skill whenever the user wants to search the web, look something up, research a topic…
Skill Claude CodeCodex
Fast browser automation CLI for AI agents. Chrome/Chromium via CDP, no Playwright or Puppeteer dependency. Accessibility-tree snapshots with compact @eN refs let agents interact with pages in 200-400 tokens instead of parsing raw HTML.
Skill Codex
Control the user's already-running, logged-in Google Chrome through Playwright CLI and the official Playwright Extension. Use when the user explicitly asks to use Playwright with their active, current, existing, or signed-in Chrome session; asks to inspect or operate a website through that rendered browser UI; or…
MCP server Claude CodeCodexCursor +2
MCP server "browser-bridge" as configured in arikw/rx-browser-bridge-mcp. Runs ./mcp/dist/server.js with node.
Ljhhhhhh/user-facing-only-skill
Skill Codex
Keep finished deliverables limited to what their intended users need. Use when demo instructions, mock details, implementation rationale, temporary shortcuts, or superseded requirements might leak into user-facing pages, reports, exports, documentation, APIs, or CLI output. Do not use for general UX or code-quality…
Skill Claude CodeCodex
Use Playwright for browser testing, responsive verification, screenshots, console and network checks, forms, navigation, and important user flows.
Skill Claude CodeCodex
Drive the browser the user is already signed into, instead of a cold automation profile. Use when a task lives behind a login — a dashboard, an admin console, an internal tool, a ticket queue, a bank or billing page, webmail, a social account — or when a scripted login is failing on SSO, MFA, CAPTCHA or bot detection.…
Plugin Claude Code
Marketplace for Claude Bridge: autonomous browser handoff for Claude Code.
Skill Claude CodeCodex
Use Pursr for browser screenshots, scripted visual operation, visual regression, accessibility audits, DOM inspection, and MCP-driven browser sessions. Use when a user asks an agent to inspect a site, operate an existing browser session, fill or draft UI content, record a tutorial, compare visuals, debug layout, or…
Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 0 tokens together
Human-in-the-loop review interface for Claude Code - request structured feedback on plans, PRs, and implementations via browser UI.
Skill Claude CodeCodex needs its repo
Browser automation via MCP using your real Chrome browser. Use when the user asks to navigate websites, scrape data, fill forms, take screenshots, or automate browser tasks. Unlike headless browsers, helm controls the user's actual Chrome via a lightweight extension.
Skill Claude Code
Create adaptive interfaces and real-time experiences via the pub CLI, with live P2P browser sessions.
Skill Claude CodeCodex
QUESTPIE Probe — dev testing CLI for AI coding agents. Start servers, test APIs, control browsers via agent-browser, record and replay regression tests with zero tokens. Use when testing web apps, starting dev servers, reading logs, debugging errors, making API calls, checking browser console/network, or composing…
Skill Claude CodeCodex
Mirror live websites to your local machine using a combination of wget and Playwright. Supports static, dynamic single‑page and dynamic multi‑page capture and is designed for Google Antigravity's agentic development environment.
bakhtiersizhaev/chromewire-mcp
Skill Claude CodeCodex
Install and verify ChromeWire MCP, the local bridge between the official Codex Chrome Extension and MCP-compatible AI CLI tools.
Skill Claude CodeCodex
An automated testing setup for web applications that uses Playwright to control a real browser and checks complete user journeys with the live backend.
Skill Claude CodeCodex
An internet research skill for requests to search, investigate, or find information online, including requests involving specific websites and platforms.
Skill Claude CodeCodex
Control Chrome browser with AI using MCP protocol. Use when users want to automate browser tasks, take screenshots, fill forms, click elements, navigate pages, search browsing history, manage bookmarks, or perform any browser-based automation. Works with your existing Chrome browser and login sessions.
Skill Claude CodeCodex
Use when the user wants to scrape, crawl, or extract data from a website or URL. Triggers on: 'scrape this site', 'get data from this URL', 'crawl this page', 'extract data from the web', 'pull data from this link', 'download data from this website', 'I need data from [URL]', or any request involving collecting…
Skill Codex
Drive the real app end to end through Chrome DevTools MCP, with video proof. Trigger 'e2e it through codex'.
Skill Claude Code
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: