Testing plugins

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

1 command · 2 agents

The qa-happy-path, qa-chaos-monkey, and qa-bug-fixer agents, plus a project installer.

3 agents

Locks working behavior behind a test baseline so agent-made changes cannot silently break what already worked. Stack-agnostic; every project-specific fact lives in a generated manifest.

1 skill · hooks

Plan and generate PHPUnit / Pest tests for PHP, Laravel and Symfony code.

2 skills

One-shot a complete visual record of any web app — every screen, email, and social preview, plus a video — laid out as a browsable flow canvas (Figma export optional).

2 skills

Generate Xray test cases end-to-end: parse requirements, present test matrix, deliver as CSV import file, direct Jira API creation, or both. Includes the /xray-tests slash command.

1 skill · 1 command

E2E testing with Playwright MCP: playbook execution or ad-hoc bug hunting.

2 commands

QAIA core: from a user story or an OpenAPI spec to a prioritized, traceable, atomic Gherkin test book with stable IDs and a coverage matrix - every assumption carries an ID.

2 skills

Browser tests, application surveys, and reproducible evidence with headless or isolated headed execution

2 skills

General-purpose browser automation with Playwright. Auto-detects dev servers, writes test scripts to /tmp, supports responsive testing and form automation.

1 skill · 1 command

Comprehensive WCAG 2.1 accessibility auditing with axe-core runtime scanning and eslint-plugin-jsx-a11y static analysis.

1 skill · 1 command

Skills for running tests and checking coverage

2 skills

Test a first-party or third-party AdCP sales agent with governed buyer workflows.

1 skill · 1 MCP server

Pytest-native regression testing for the AI agent being built — the onboard skill records golden baselines and generates a test spec; the check skill runs trace-diff regression, multi-run stability with verdict-flip attribution, and LLM-judge audits after every agent change.

2 skills

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

2 MCP servers

The ShadowPTY MCP server plus a skill that teaches Claude to start, drive, wait on, read and screenshot terminal apps.

1 skill · 1 MCP server

Hook-enforced scoped test runs, capped output, a loop breaker and a test-writer subagent for Claude Code.

1 agent · hooks

playwright-tester and playwright-expert skills for writing, running and stabilising Playwright E2E tests

2 skills

Agents run td test instead of a full dotnet test, and the tests a session's changes can affect run before the agent hands back

1 skill · hooks

The e2e-testing skill (expected behaviour first, case list, cheapest layer, the framework, running, judging, agents) and a PreToolUse hook that refuses commands which would read the kit's staging dir, .env files, a process environment or a secret manager. A backstop, not a boundary.

1 skill · hooks

Playwright functional tests + headless bridge + Lighthouse CLI/CI + axe. No Chrome DevTools MCP. TDD loop (haiku), audits and performance deep-dive (opus, report-only). .agent-progress/ optional progress_log_path.

1 skill · 1 agent

Run, debug and triage tests on the TestMu AI cloud through the hosted MCP server (HyperExecute, failure triage, SmartUI, accessibility, Test Manager), plus the Kane CLI and Rook CLI skills

2 skills

Pytest-native regression testing for the AI agent being built — the onboard skill records golden baselines and generates a test spec; the check skill runs trace-diff regression, multi-run stability with verdict-flip attribution, and LLM-judge audits after every agent change.

2 skills

Every agent tests its own copy of your web or Electron app, in its own worktree, on its own ports, attached over CDP with agent-browser.

1 skill

Ask QA Wolf for test coverage, run flows, read results, and drive a cloud browser from your editor.

1 skill

Drive, inspect, and debug the running AiMarketingtool-pro React Native app on an Android device via a vendored offline react-native-mcp-kit MCP server.

1 MCP server

Write and update test checklists for the Axygen Checklist NVDA add-on: JSON files a screen-reader tester walks by ear.

1 skill

Test skill for verifying local skill installation in the ai-tdd container.

1 skill

Skill for the encfixture CLI: generate dummy media files (image / video / audio) for ffmpeg encoding tests, run batch jobs, assert file properties with verify --expect, and diagnose the environment with doctor.

1 skill

Analyze recent commits, navigate affected UI routes in Chrome, take screenshots, check console logs and network requests, and produce a structured issues report. Works with any web framework.

1 skill