Testing plugins

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

Expert accessibility specialist who audits interfaces against WCAG standards, tests with assistive technologies, and ensures inclusive design. Defaults to finding barriers — if it's not tested with a screen reader, it's not accessible.

1 agent

Expert API testing specialist focused on comprehensive API validation, performance testing, and quality assurance across all systems and third-party integrations

1 agent

Screenshot-obsessed, fantasy-allergic QA specialist - Default to finding 3-5 issues, requires visual proof for everything

1 agent

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

Verify the behaviour of a change to a web interface with the component tests of the project, then give the user a short click-through for what tests cannot show, such as layout, styles and visible focus. The agent does not run the app or a browser. It fixes the steps that the user reports as failed.

1 skill

Ebitengine desktop driver for the qa plugin: /qa:run tests Ebitengine (v2.10.5 or later) games headless in the background through exp/vmhost. Requires qa 3.1.0 or later from av-marketplace.

1 skill

Build a manual test plan for the ticket you're on, as a web page to tick through: cases written from the spec, not the code, with real records from your local database.

1 skill

Agentic STLC: from a Jira ticket, PRD or PR to reviewed, CI-proven E2E tests in 12 resumable phases

1 skill

Create Playwright E2E tests using Chrome browser exploration for real selector discovery and Page Object Model patterns

1 skill

Create Playwright API tests based on a playwright e2e test, it will test the corner cases missed by the e2e test

1 skill

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

Check rendered HTML/CSS or Canvas game UI against approved baselines with slicewright/browser and the slicewright/playwright matchers.

1 skill

Verify any browser flow from your terminal in natural language. Real Chrome, evidence-backed.

1 skill

Quality assurance tools and testing utilities

AI-driven game testing with TITAN-inspired agent architecture. Automates Unity game testing via HTTP Bridge SDK — state inspection, action scripting, coverage tracking, visual regression, and autonomous exploration.

Visual regression testing for Textual apps with pytest and snapshot testing

Official Microsoft Playwright MCP server for direct browser control, debugging, and test automation

Multi-agent QA toolkit with 10 specialized agents covering the full QA lifecycle — orchestrator, environment-manager, functional-reviewer, test-scenario-designer, browser-validator, automation-writer, manual-validator, bug-reporter, release-analyzer, and smart-test-selector. Stack-agnostic, output-chained, designed around live validation via Chrome MCP.

Multi-agent QA toolkit with 10 specialized agents covering the full QA lifecycle — orchestrator, environment-manager, functional-reviewer, test-scenario-designer, browser-validator, automation-writer, manual-validator, bug-reporter, release-analyzer, and smart-test-selector. Stack-agnostic, output-chained, designed around live validation via Chrome MCP.

Multi-agent QA toolkit with 10 specialized agents covering the full QA lifecycle — orchestrator, environment-manager, functional-reviewer, test-scenario-designer, browser-validator, automation-writer, manual-validator, bug-reporter, release-analyzer, and smart-test-selector. Stack-agnostic, output-chained, designed around live validation via Chrome MCP.

Unit and integration test automation for Python and JavaScript with debugging support

Watches kane-cli (KaneAI) runs in Claude Code: a band above the prompt with the kane mascot, a pane for runs, steps, failures and assurance coverage, and a nudge to test what Claude just changed.

Multi-model rating for AI evaluation: measures agreement among model raters (Fleiss' κ, Kendall's W) to find contested items for expert review. Agreement is reliability, not validity. Maintenance mode.

Agent Assurance by TestMu AI (rook): test how your AI agents behave across workflows, tools and actions, before they ship.