QA-test any website or app with a real browser and return a 1-5 score with evidence. Drives a Browser Use cloud browser (tunnels localhost automatically). Requires the browser-harness CLI (the skill installs it itself if missing).
AI-powered visual testing and accessibility setup for iOS/SwiftUI apps. Build, launch in Simulator, test with computer use, detect crashes, analyze memory leaks, and add accessibility identifiers.
★not rated 23 6mo agoA
tokens not measured
originalMIT
Persona-based user testing agent that simulates realistic user interactions with web applications. Embodies different user archetypes (Boomers, Millennials, Gen Z, Gen Alpha) with authentic behaviors, timing patterns, and frustration triggers to identify UX issues before real users do.
★not rated 21▲
+1 9mo agoA
tokens not measured
originalMIT
Four agent skills for Playwright and Cypress end-to-end tests: generate new Playwright coverage with live exploration only on local/disposable or externally isolated approved non-production targets, review existing specs or PR diffs, and debug failed runs.
Currents gives AI agents the test results your CI records, from Playwright, Vitest, Jest and more. Self-healing tests: an agent gets the errors, traces and history behind a failure, finds the root cause and fixes the test, flaky ones included. Proof of work for any change, not just tests: before-and-after screenshots.
★not rated 21 4d agoA
tokens not measured
originalApache-2.0
Real-browser E2E acceptance for your coding agent: test the flows you changed and open the PR with screenshots. Built for flows other tools can't reach: managed test identities with live inboxes (magic links, email OTP and 2FA, verification mail, password resets), an encrypted secret store for login and test…
★not rated 16
changed yesterdayA
tokens not measured
originalMIT
Skills for Momentic end-to-end testing. They cover writing browser and mobile app tests, running them, and fixing them when they break, and they connect the local Momentic MCP server.
Turn Claude Code into a meticulous QA engineer: every Pass/Fail verdict must cite an observed artifact. Testing framework with 1000 checks, Playwright test review, test-case generation, Jira bug reports.
Desktop and browser automation for Claude Code. Control any macOS/Windows app, automate social media, run QA tests, edit video, design in Figma/Canva, scrape the web, and orchestrate multi-agent workflows — 111 MCP tools.
★not rated 15 6mo agoA
tokens not measured
AGPL-3.0
Playwright E2E test debugging and interactive browser exploration. Runs tests with action capture (DOM snapshots, network, console, screenshots), diagnoses failures, and provides browser tools for navigating, clicking, and inspecting pages through ARIA snapshots.
Virtual QA lead: turns requirements into TestRail-ready test cases in one conversation, plus a runnable Postman collection when the spec describes an API.
★not rated 11 18d agoA
tokens not measured
originalMIT
Ripplo reviews pull requests by driving your app end to end in a real browser and reporting what broke, with the evidence. This plugin connects an app to Ripplo and lets Claude Code fix what a review found and add what a review could not cover.
★not rated 7
changed 20d agoA
tokens not measured
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: