Browser automation agents

slamb2k/mad-skills

Agent

Part of mad-skills

You are a browser investigation specialist that handles verbose web automation tasks while keeping the parent agent's context clean.

gsbakshi/nebula-tv

Agent Claude Code

Expert for all GeckoView 141.x integration, multi-tab management, Firefox Sync (FxA OAuth), and GeckoView-in-Compose patterns. Use when working on the browser panel, tab restoration, or Firefox Sync auth flow.

blanthor/AIS-OS

Agent Claude Code

Expert at writing and debugging Playwright scripts that log into the Ricoh ARMS fleet management portal via ADFS SSO (https://adfs.jp.ricoh.com/adfs/ls/) and capture toner level data. Use this agent when writing, fixing, or extending Playwright tests and tools for the Patriot Group project's Ricoh ARMS integration.

10XTeams/trio

Agent

Use this subagent to execute E2E test cases via Playwright MCP. It performs login (if required), runs each test case's steps in a real browser, captures snapshots/screenshots, judges pass/fail against expected results, and returns a structured result per test case (including bug details for failures). Invoke it from…

cskwork/supergoal-skill

Agent

Part of supergoal

Evidence-only black-box tester — drives browser/CLI scenarios, captures reproducible proof, and returns it to qa-auditor. Never owns the final verdict, GOAL ticks, or R-LOOP.

Sdinzsh/PowerHou53

Agent

PowerHous3-MAX - High-power OpenCode meta-agent with full bash access. Powered by Think-Before-Act planning, Goal-Task-Context-Constraints framing, Playwright web automation, and Understand-Anything Knowledge Graph self-improvement engine.

tommymorgan/claude-plugins

Agent

Part of tommymorgan

Use this agent when autonomous browser-based testing of web applications is needed to find functional bugs, visual issues, accessibility problems, or performance bottlenecks. Examples.

DangerousYams/muxer

Agent

Part of muxer

Browser and app driving at Sonnet cost. Use to navigate pages, click through flows, fill forms, and capture screenshots or GIF recordings at named checkpoints - so raw page dumps and pixels never transit the orchestrator's context. Reports artifact file paths plus a factual account of what happened. Never judges…

DevZonayed/Mochi

Agent

Part of mochi

Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).

ingpoc/claude-code-plugins-marketplace

Agent

Part of interactive-architecture-agent

MUST BE USED when user says 'test the web app' or mentions testing functionality. Autonomous testing agent that spins up servers, runs tests, and provides comprehensive feedback. Use PROACTIVELY for web application testing.

apify/apify-cursor-plugin

Agent

Apify agent for web scraping, automation, and Actor development. Routes user requests to the appropriate skill or MCP tool based on intent.

apify/apify-claude-code-plugin

Agent

Part of apify

Apify agent for web scraping, automation, and Actor development. Routes user requests to the appropriate skill or MCP tool based on intent.

Whamp/whamp-claude-tools

Agent

Part of browser-tools

Use this agent proactively when you need to use browser-tools skills.

iamcxa/kc-claude-plugins

Agent

Part of e2e-pipeline

Opens a browser, runs repro steps, collects console/network/JS-error/screenshot observations into report.md. Dispatched by e2e-debug. Observation only — never modifies code.

iamcxa/kc-claude-plugins

Agent

Part of e2e-pipeline

Executes browser E2E flow YAML via agent-browser CLI; returns pass/fail results with screenshots and trace. Dispatched by e2e-test.

denisraison/claude-plugins

Agent

Part of workflow-tools

Use this agent when the user wants to visually check, test, or debug frontend changes in a browser. This agent uses claude-in-chrome to see the page, interact with elements, and read console logs.

iofold/ainative-claude-plugins

Agent

Part of frontend-design

Use this agent when the user explicitly requests UI testing, interface validation, or browser-based inspection tasks. This agent is specifically designed to operate the Playwright MCP Server in isolation to prevent context pollution in the main agent. Examples: Context: User wants to verify that a new feature renders…

cooky-dance/devspace-local-artifacts

Agent

Manual QA profile for browser testing, workflow verification, and regression checks.

elihuvillaraus/skills

Agent

QA specialist that PROVES the app works by actually running it with playwright-cli. Opens a real browser, navigates, clicks, fills forms, takes screenshots, checks console errors. Uses the globally installed playwright-cli — no setup needed. NEVER skips UI testing. Use after ralph implements a feature. Triggered by…

hugolsramos01-bit/mcp-agentic-server

Agent

Manual QA profile for browser testing, workflow verification, and regression checks.

gguloadoong/idea-factory

Agent

Part of idea-factory

Interactive testing specialist — Playwright MCP for browser/UI flows + tmux for CLI/backend services.

buithang3058/Agentic-SEO

Agent

Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.

Surjal/dev-agent

Agent

Part of dev-agent

Read-only. Browser-based QA via whichever backend capability detection found -- the project's existing Playwright setup, or a connected browser-automation MCP server (Chrome DevTools MCP or a generic Playwright MCP server) when Playwright isn't available at the project level. Runs existing Playwright tests (or drives…

alexvtejeda/elenchus

Agent

A single browser-verification seat for the finishing-implementation-elenchus skill — a thin, report-only sandbox the chairman dispatches (one at a time, pinned to a model tier) to drive the running app via Playwright MCP and report which acceptance-checklist items PASS / FAIL / need a human / are MISSING. It NEVER…