E2E testing agents

GuillemRoca/agent-skills-android

Agent

Part of agent-skills-android

Android QA engineer specialized in test strategy, test design, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.

openshift-online/gcp-hcp

Agent

Part of gcp-hcp

Triages CI failures on PRs, fixes blocking issues, and retests flaky e2e tests.

marcbenito/claude_workshop_ensenyament

Agent Claude Code

Valida l'aplicació de Reserva de Sessions de Treball obrint-la al navegador amb Chrome DevTools MCP. Comprova que els fluxos principals (registre/login, explorar professors, reservar sessió, veure i cancel·lar reserves) funcionen correctament i sense errors de consola o de xarxa. Usa'l després de canvis a app/ que…

konveyor-ecosystem/playpen-pf-mig-skills

Agent

Execute runtime validation steps against the golden truth and each migration attempt. Captures evidence (screenshots, test output, logs, HTTP responses) for use by adversarial review agents.

cwijayasundara/claude_harness_eng_v1

Agent Claude Code

Part of claude-harness-engine

Skeptical verifier that runs the application and checks sprint contract criteria via API tests, Playwright interaction, and schema validation.

de6eling/user-testing-agent

Agent Claude Code

Usability test agent that navigates a web app as a specific persona using Chrome browser tools. Launch with: claude --chrome --agent user-tester.

DynamoDS/DynamoHome

Agent Claude Code

Use when creating or maintaining end-to-end Playwright tests, implementing Page Object Model classes, or investigating test failures in tests/e2e/.

bohorquezod/agentlink

Agent

Designs, writes, and updates automated tests for agentlink with the correct unit-vs-e2e boundary, repository conventions, and regression-focused assertions. Use when the user asks to add test coverage, fix failing tests, or strengthen test quality.

mercuryPark/oc-setup

Agent

A testing-focused coding agent that writes and runs tests for software. It covers unit, integration, and end-to-end tests, including TDD, where tests are written before the code they check.

eliottvalette/Anthropic-Voodoo-Hackathon

Agent Claude Code

Headless browser tester and root-cause diagnostician for the proto-pipeline-m single-file HTML playables. Runs Playwright on the playable, captures the state trajectory and console errors, cross-references symptoms with the source sketches in 04sketches.json and the 04plan.json contract, and returns a structured…

stoeier87/stoeier87.github.io

Agent Claude Code

Verifies a deployed rung end to end — HTTP status, every expected page present, assets resolving under the deploy prefix, and no root-absolute paths escaping the environment onto production. Read-only. Use after a deploy, when a preview URL looks wrong, or when asked whether an environment is actually healthy.

keychain-io/trustable-ai

Agent Claude Code

Generate comprehensive blackbox acceptance test plans for EPICs AND execute acceptance tests against implemented functionality. Operates in two modes: Plan Generation (create test plans) and Test Execution (execute tests and generate results).

damian-demasi-aligent/ai-agent-tool-chain-generic

Agent Claude Code

Run frontend and backend preflight checks (lint, types, build, a11y, runtime smoke test via Playwright, PHP quality) and report results. Use before committing or pushing to verify the codebase is clean.

rungchan2/frontend-skills

Agent

Part of e2e-testing

An agent that runs end-to-end test scenarios in a real browser using agent-browser. End-to-end testing checks whether a complete user journey works from start to finish.

MichiBl/Claude-Code-Default-Repo

Agent Claude Code

Leitet aus den Acceptance Criteria eine Coverage-Map ab, schreibt echte Testdateien und führt sie zusammen mit den Projekt-Gates (Lint, Typecheck, Tests) aus. Wird in der Feature-Pipeline zweimal gerufen — VOR der Implementierung (RED-Phase: Tests aus den AC, die rot sein müssen) und NACH einem APPROVED Code-Review…

azam-sdet/10xquality

Agent

Converts recorded natural language test scripts into Playwright + Cucumber BDD tests (feature files, page objects, step definitions). Use when asked to "convert to BDD", "generate Playwright tests", or "create Cucumber features from this script".

azam-sdet/10xquality

Agent

Records manual browser interactions and generates natural language test scripts with rich locator metadata and assertion capture. Use when asked to "record a test", "capture actions", or "record UI steps".

azam-sdet/10xquality

Agent

Generates structured test cases from any URL or content. Auto-detects source type — Confluence PRD, Figma design, or pasted text. Use when the user provides a URL and asks to "generate test cases", "create test cases", "write tests", or simply pastes a Confluence/Figma link.

pnakhat/qa-ai-repo

Agent

Use to set up or repair Playwright visual regression tests for a UI. Give it the views or components to cover; it makes screenshots deterministic (disable animations, freeze the clock, seed data, pin fonts/viewport/device-scale), adds a stabilization fixture, chooses masking and thresholds, establishes container-based…

jy315189/everything-cursor

Agent Cursor

You are an E2E testing expert using Playwright. You write reliable, maintainable end-to-end tests that validate critical user journeys without being flaky.

rajconnects/founder-stack

Agent

Part of founder-stack

Use PROACTIVELY when the mission tick procedure dispatches user-flow testing on a feature whose scrutiny has PASSed and whose contract declares user flows. You drive a real browser via Playwright MCP, execute each flow against the preview URL, and emit a PASS/FAIL verdict with screenshots and console capture.

KaelSensei/MagicAIBuilder

Agent Codex

Specialized agent that runs the full Playwright e2e suite in the project's Dockerized Chromium environment (docker-compose.e2e.yml) and reports pass/fail. Use before pushing to GitHub to guarantee e2e never regresses on main. Trigger on "run e2e", "e2e before push", "playwright check", or invoked by the pre-push git…

alexmmatos/arthur-mcp

Agent Claude Code

Backend test engineer for Arthur MCP. Use when writing, reviewing, debugging, or improving backend tests for NestJS services, controllers, guards, repositories, DTO validation, dynamic MCP execution, persistence behavior, and API/e2e flows.

amghanekar-deloitte/AEP-MCP_SERVER

Agent Claude Code

Activation QA agent — validates AJO activation workflow (segments, campaigns, journeys). Handles test case generation (/qa read activation) and execution (/qa run activation) for SEG-, CAM-, and JRN- prefixed tests. Tests segment definitions, campaign configuration, and journey orchestration. Dispatches to…