E2E testing agents

millsymills-com/flipperzero-mcp

Agent

Captures real Flipper CLI/RPC byte exchanges once and replays them offline in CI, mirroring the workspace VCR-cassette discipline. It proves the parsing, framing, gating, and integrity logic against bytes a physical device actually produced — without hardware in CI.

WeftCut/WeftCut

Agent

Where WeftCut's tests live, why they're split the way they are, and how to run each layer. There is no single tests/ directory — that's deliberate (see Why not one directory). Tests are grouped by runner, not scattered by neglect.

mean-weasel/bullhorn

Agent Claude Code

You are reviewing Playwright E2E specs in the Bullhorn repo for selector stability, race conditions, and maintainability patterns. Your job is to flag fragile tests before they land in main and become someone's 2am debugging session.

mean-weasel/bullhorn

Agent Claude Code

You are an iOS testing agent for the Bullhorn project — a Next.js 14 social media post scheduler built with Supabase, Zustand, and Tailwind CSS, running in Safari via Capacitor on the iOS Simulator.

moasq/ios-dev-agent

Agent Codex

Investigates and fixes runtime crashes detected by smoke walker tests. Reads test failure output, harvests crash logs, symbolicates backtraces, applies fix, reruns failing test, and updates the error ledger.

fattain-naime/engineering-docs

Agent

Part of engineering-docs

Create comprehensive test strategies for software projects. User says: "Create a test strategy for our e-commerce platform" User says: "What tests should we write for the payment flow?" User says: "Review our test coverage and suggest improvements".

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.

bop-clocktower/canary

Agent

Part of canary

Generate production-ready test code from natural-language requirements across Playwright (E2E), Vitest (JS/TS unit and component), Pytest (Python unit and API), and k6 (performance). Use when the user wants to create new tests — phrases like "write a test for...", "generate an E2E test", "I need a unit test that…

fastslack/mtw-e2e-runner

Agent

Part of e2e-runner

Use this agent to diagnose E2E test failures, analyze flaky tests, investigate network errors, and provide stability insights. Best used after running tests to understand why they failed and how to fix them.

fastslack/mtw-e2e-runner

Agent

Part of e2e-runner

Use this agent to create new E2E tests by exploring the application UI, analyzing source code, and designing test actions. Best used when you need to write tests for a new feature, page, or user flow.

fastslack/mtw-e2e-runner

Agent

Part of e2e-runner

Use this agent to improve existing E2E tests — refactor verbose evaluate actions into built-in alternatives, extract duplicated sequences into modules, replace brittle selectors, add missing waits/retries for flaky tests, and eliminate hardcoded delays. Best used when tests work but need cleanup.

QuantGeekDev/google-calendar-mcp-app

Agent Claude Code

PROACTIVELY use when adding new calendar features or modifying event handlers. Specializes in writing comprehensive test suites for Google Calendar MCP tools, including edge cases like timezone conversions, recurring events, multi-calendar scenarios, and error conditions. Ensures >90% code coverage.

superduke/ganvil

Agent

Part of ganvil

Frontend QA evaluator. Reviews frontend sprint output against acceptance criteria using five dimensions: design quality, originality, craft, UX-usability, and functional completeness (closed-loop). Interacts with the running app via browser automation to test real user flows and verifies feature loops close…

ByeongminLee/nextjs-claude-code

Agent Claude Code

Part of nextjs-claude-code

Orchestrates NCC plugin E2E tests. Supports quick (Phase 1), full (Phase 1+2), install-test (npx vs marketplace), security, a11y, codequality, and custom modes. Spawns executor+reviewer pairs per project, writes aggregated reports.

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.).

kangraemin/ai-bouncer

Agent

An agent for writing end-to-end tests, which test a complete user flow through an application. Its description also mentions restoring context, collecting scenarios, and following a work sequence.

reuvenaor/israel-statistics-mcp

Agent Claude Code

Exercises the built MCP server end-to-end through the MCP Inspector CLI and reports a per-tool pass/fail matrix. Use proactively after changes under src/ (handlers, schemas, fetcher, server) and before commits that touch the MCP surface.

iamcxa/kc-claude-plugins

Agent

Part of e2e-pipeline

Runs E2E flows in browser, auto-repairs broken selectors/URLs, and produces PR-ready reports with screenshots + trace. Dispatched by e2e-flow.

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.

JeonJe/claude-plugins

Agent

Part of ma-pipeline

Inspects: AC pass, user scenarios, edge cases, UX.

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…

punkadillo/figma-code-composer

Agent Claude Code

Writes unit + integration tests for components built by component-builder, and Playwright E2E suites when tests.e2e.enabled. Branches on configSnapshot.framework + tests.unit.framework + tests.unit.testingLibrary + tests.e2e.enabled. Spawned in parallel with story-author after component-builder.

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…